update for v0.0.7

Unraid installation instructions

.dockerignore

@@ -17,5 +17,8 @@ venv/
 # Unneeded graphics
 assets/*
 
+# Unneeded docs
+docs/*
+
 # for local testing only
 testing.sh

.github/workflows/lint_python.yml

@@ -0,0 +1,23 @@
+name: lint_python
+on: [pull_request, push]
+jobs:
+  lint_python:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+      - run: pip install --upgrade pip wheel
+      - run: pip install bandit black codespell flake8 flake8-bugbear
+                         flake8-comprehensions isort
+      - run: bandit --recursive  --skip B105,B108,B404,B603,B607 .
+      - run: black --check --diff --line-length 79 .
+      - run: codespell
+      - run: flake8 . --count --max-complexity=12 --max-line-length=79
+                      --show-source --statistics
+      - run: isort --check-only --line-length 79 --profile black .
+      # - run: pip install -r tubearchivist/requirements.txt
+      # - run: mkdir --parents --verbose .mypy_cache
+      # - run: mypy --ignore-missing-imports --install-types --non-interactive .
+      # - run: python3 tubearchivist/manage.py test || true
+      # - run: shopt -s globstar && pyupgrade --py36-plus **/*.py || true
+      # - run: safety check

.gitignore

@@ -3,6 +3,3 @@ __pycache__
 
 # django testing db
 db.sqlite3
-
-# frontend fonts
-*ttf.woff

CONTRIBUTING.md

@@ -0,0 +1,57 @@
+## Contributing to Tube Archivist
+
+Welcome, and thanks for showing interest in improving Tube Archivist!  
+If you haven't already, the best place to start is the README. This will give you an overview on what the project is all about.
+
+## Report a bug
+
+If you notice something is not working as expected, check to see if it has been previously reported in the [open issues](https://github.com/bbilly1/tubearchivist/issues).
+If it has not yet been disclosed, go ahead and create an issue.  
+If the issue doesn't move forward due to a lack of response, I assume it's solved and will close it after some time to keep the list fresh. 
+
+## Wiki
+
+The wiki is where all user functions are explained in detail. These pages are mirrored into the **docs** folder of the repo. This allows for pull requests and all other features like regular code. Make any changes there, and I'll sync them with the wiki tab.
+
+## Development Environment
+
+I have learned the hard way, that working on a dockerized application outside of docker is very error prone and in general not a good idea. So if you want to test your changes, it's best to run them in a docker testing environment.  
+
+This is my setup I have landed on, YMMV:
+- Clone the repo, work on it with your favorite code editor in your local filesystem. *testing* branch is the where all the changes are happening, might be unstable and is WIP.
+- Then I have a VM on KVM hypervisor running standard Ubuntu Server LTS with docker installed. The VM keeps my projects separate and offers convenient snapshot functionality. The VM also offers ways to simulate lowend environments by limiting CPU cores and memory. But you could also just run docker on your host system.
+- The `Dockerfile` is structured in a way that the actual application code is in the last layer so rebuilding the image with only code changes utilizes the build cache for everything else and will take just 2-3 secs.
+- Take a look at the `deploy.sh` file. I have my local DNS resolve `tubearchivist.local` to the IP of the VM for convenience. To deploy the latest changes and rebuild the application to the testing VM run:
+```bash
+./deploy.sh test
+```
+- The command above will also copy the file `tubarchivist/testing.sh` into the working folder of the container. Running this script will install additional debugging tools I regularly use in testing. 
+- The `test` argument takes another optional argument to build for a specific architecture valid options are: `amd64`, `arm64` and `multi`, default is `amd64`.
+- This `deploy.sh` file is not meant to be universally usable for every possible environment but could serve as an idea on how to automatically rebuild containers to test changes - customize to your liking. 
+
+## Working with Elasticsearch
+Additionally to the required services as listed in the example docker-compose file, the **Dev Tools** of [Kibana](https://www.elastic.co/guide/en/kibana/current/docker.html) are invaluable for running and testing Elasticsearch queries.  
+
+If you want to run queries in on the Elasticsearch container directly from your host with for example `curl` or something like *postman*, you might want to **publish** the port 9200 instead of just **exposing** it.
+
+## Implementing a new feature
+
+Do you see anything on the roadmap that you would like to take a closer look at but you are not sure, what's the best way to tackle that? Or anything not on there yet you'd like to implement but are not sure how? Open up an issue and we try to find a solution together.
+
+## Making changes
+
+To fix a bug or implement a feature, fork the repository and make all changes to the testing branch. When ready, create a pull request.
+
+## Releases
+
+Everything on the master branch is what's in the latest release and is what you get in your container when you `pull` either the *:latest* tag or the newest named version. If you want to test the newest changes and improvements, clone the repository and build the docker container with the Dockerfile from the testing branch.
+
+## Code formatting and linting
+
+To keep things clean and consistent for everybody, there is a github action setup to lint and check the changes. You can test your code locally first if you want. For example if you made changes in the **download** module, run
+
+```shell
+./deploy.sh validate tubearchivist/home/src/download.py
+```
+
+to validate your changes. If you omit the path, all the project files will get checked. This is subject to change as the codebase improves. 

Dockerfile

@@ -1,16 +1,30 @@
 # build the tube archivist image from default python slim image
 
 FROM python:3.9.7-slim-bullseye
+ARG TARGETPLATFORM
 
 ENV PYTHONUNBUFFERED 1
 
 # install distro packages needed
 RUN apt-get clean && apt-get -y update && apt-get -y install --no-install-recommends \
     build-essential \
-    ffmpeg \
     nginx \
     curl && rm -rf /var/lib/apt/lists/*
 
+# get newest patched ffmpeg and ffprobe builds for amd64 fall back to repo ffmpeg for arm64
+RUN if [ "$TARGETPLATFORM" = "linux/amd64" ] ; then \
+    curl -s https://api.github.com/repos/yt-dlp/FFmpeg-Builds/releases/latest \
+        | grep browser_download_url \
+        | grep linux64-gpl-4.4.tar.xz \
+        | cut -d '"' -f 4 \
+        | xargs curl -L --output ffmpeg.tar.xz && \
+        tar -xf ffmpeg.tar.xz --strip-components=2 --no-anchored -C /usr/bin/ "ffmpeg" && \
+        tar -xf ffmpeg.tar.xz --strip-components=2 --no-anchored -C /usr/bin/ "ffprobe" && \
+        rm ffmpeg.tar.xz \
+    ; elif [ "$TARGETPLATFORM" = "linux/arm64" ] ; then \
+        apt-get -y update && apt-get -y install --no-install-recommends ffmpeg && rm -rf /var/lib/apt/lists/* \
+    ; fi
+
 # copy config files
 COPY nginx.conf /etc/nginx/conf.d/
 

README.md

@@ -1,10 +1,23 @@
 ![Tube Archivist](assets/tube-archivist-banner.jpg?raw=true "Tube Archivist Banner")  
 
-<center><h1>Your self hosted Youtube media server</h1></center>
+<center><h1>Your self hosted YouTube media server</h1></center>
 
+## Table of contents:
+* [Wiki](https://github.com/bbilly1/tubearchivist/wiki) for a detailed documentation
+* [Core functionality](#core-functionality)
+* [Screenshots](#screenshots)
+* [Problem Tube Archivist tries to solve](#problem-tube-archivist-tries-to-solve)
+* [Installing and updating](#installing-and-updating)
+* [Getting Started](#getting-started)
+* [Potential pitfalls](#potential-pitfalls)
+* [Roadmap](#roadmap)
+* [Known limitations](#known-limitations)
+* [Donate](#donate)
+
+------------------------
 
 ## Core functionality
-* Subscribe to your favourite Youtube channels
+* Subscribe to your favorite YouTube channels
 * Download Videos using **yt-dlp**
 * Index and make videos searchable
 * Play videos
@@ -27,58 +40,49 @@
 *Downloads Page*
   
 ## Problem Tube Archivist tries to solve
-Once your Youtube video collection grows, it becomes hard to search and find a specific video. That's where Tube Archivist comes in: By indexing your video collection with metadata from Youtube, you can organize, search and enjoy your archived Youtube videos without hassle offline through a convenient web interface.
+Once your YouTube video collection grows, it becomes hard to search and find a specific video. That's where Tube Archivist comes in: By indexing your video collection with metadata from YouTube, you can organize, search and enjoy your archived YouTube videos without hassle offline through a convenient web interface.
 
-## Installation
+## Installing and updating
 Take a look at the example `docker-compose.yml` file provided. Tube Archivist depends on three main components split up into separate docker containers:  
 
 ### Tube Archivist
 The main Python application that displays and serves your video collection, built with Django.
   - Serves the interface on port `8000`
-  - Needs a mandatory volume for the video archive at **/youtube**
-  - And another recommended volume to save the cache for thumbnails and artwork at **/cache**.
+  - Needs a volume for the video archive at **/youtube**
+  - And another volume to save application data at **/cache**.
   - The environment variables `ES_URL` and `REDIS_HOST` are needed to tell Tube Archivist where Elasticsearch and Redis respectively are located.
-  - The environment variables `HOST_UID` and `HOST_GID` allows Tube Archivist to `chown` the video files to the main host system user instead of the container user.
+  - The environment variables `HOST_UID` and `HOST_GID` allows Tube Archivist to `chown` the video files to the main host system user instead of the container user. Those two variables are optional, not setting them will disable that functionality. That might be needed if the underlying filesystem doesn't support `chown` like *NFS*. 
+  - Change the environment variables `TA_USERNAME` and `TA_PASSWORD` to create the initial credentials. 
+  - `ELASTIC_PASSWORD` is for the password for Elasticsearch. The environment variable `ELASTIC_USER` is optional, should you want to change the username from the default *elastic*.
 
 ### Elasticsearch
-Stores video metadata and makes everything searchable. Also keeps track of the download queue.
+Stores video meta data and makes everything searchable. Also keeps track of the download queue.
   - Needs to be accessible over the default port `9200`
   - Needs a volume at **/usr/share/elasticsearch/data** to store data
 
 Follow the [documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for additional installation details.
 
 ### Redis JSON
-Functions as a cache and temporary link between the application and the filesystem. Used to store and display messages and configuration variables.
+Functions as a cache and temporary link between the application and the file system. Used to store and display messages and configuration variables.
   - Needs to be accessible over the default port `6379`
-  - Takes an optional volume at **/data** to make your configuration changes permanent.
+  - Needs a volume at **/data** to make your configuration changes permanent.
 
-## Getting Started
-1. Go through the **settings** page and look at the available options. Particularly set *Download Format* to your desired video quality before downloading. **Tube Archivist** downloads the best available quality by default.
-2. Subscribe to some of your favourite Youtube channels on the **channels** page. 
-3. On the **downloads** page, click on *Rescan subscriptions* to add videos from the subscribed channels to your Download queue or click on *Add to download queue* to manually add Video IDs, links, channels or playlists.
-4. Click on *Download queue* and let Tube Archivist to it's thing. 
-5. Enjoy your archived collection!
-  
-## Import your existing library
-So far this depends on the video you are trying to import to be still available on youtube to get the metadata. Add the files you like to import to the */cache/import* folder. Then start the process from the settings page *Manual media files import*. Make sure to follow one of the two methods below.
+### Redis on a custom port
+For some architectures it might be required to run Redis JSON on a nonstandard port. To for example change the Redis port to **6380**, set the following values:
+- Set the environment variable `REDIS_PORT=6380` to the *tubearchivist* service.
+- For the *archivist-redis* service, change the ports to `6380:6380`
+- Additionally set the following value to the *archivist-redis* service: `command: --port 6380 --loadmodule /usr/lib/redis/modules/rejson.so`
 
-### Method 1:
-Add a matching *.json* file with the media file. Both files need to have the same base name, for example:
-- For the media file: \<base-name>.mp4
-- For the JSON file: \<base-name>.info.json
-- Alternate JSON file: \<base-name>.json
+### Updating Tube Archivist
+You will see the current version number of **Tube Archivist** in the footer of the interface so you can compare it with the latest release to make sure you are running the *latest and greatest*.  
+* There can be breaking changes between updates, particularly as the application grows, new environment variables or settings might be required for you to set in the your docker-compose file. *Always* check the **release notes**: Any breaking changes will be marked there.  
+* All testing and development is done with the Elasticsearch version number as mentioned in the provided *docker-compose.yml* file. This will be updated when a new release of Elasticsearch is available. Running an older version of Elasticsearch is most likely not going to result in any issues, but it's still recommended to run the same version as mentioned.
 
-**Tube Archivist** then looks for the 'id' key within the JSON file to identify the video.
-
-### Method 2:
-Detect the Youtube ID from filename, this accepts the default yt-dlp naming convention for file names like:
-- \<base-name>[\<youtube-id>].mp4
-- The Youtube ID in square brackets at the end of the filename is the crucial part.
-
-### Some notes:
-- This will **consume** the files you put into the import folder: Files will get converted to mp4 if needed (this might take a long time...) and moved to the archive, *.json* files will get deleted upon completion to avoid having doublicates on the next run.
-- Maybe start with a subset of your files to import to make sure everything goes well...
-- Follow the logs to monitor progress and errors: `docker-compose logs -f tubearchivist`.
+### Alternative installation instructions:
+- **arm64**: Newest Tube Archivist container is multi arch, so is Elasticsearch. RedisJSON doesn't offer arm builds, you can use `bbilly1/rejson`, an unofficial rebuild for arm64.
+  - NOTE: This is untested, looking for feedback.
+- **Synology**: There is a [discussion thread](https://github.com/bbilly1/tubearchivist/discussions/48) with Synology installation instructions.
+- **Unraid**: The three containers needed are all in the Community Applications. First install `TubeArchivist RedisJSON` followed by `TubeArchivist ES`, and finally you can install `TubeArchivist`. If you have unraid specific issues, report those to the [support thread](https://forums.unraid.net/topic/114073-support-crocs-tube-archivist/ "support thread").
 
 
 ## Potential pitfalls
@@ -103,27 +107,52 @@ chown 1000:0 /path/to/mount/point
 ```
 This will match the permissions with the **UID** and **GID** of elasticsearch within the container and should fix the issue.
 
+## Getting Started
+1. Go through the **settings** page and look at the available options. Particularly set *Download Format* to your desired video quality before downloading. **Tube Archivist** downloads the best available quality by default. To support iOS or MacOS a compatible format must be specified. For example:
+```
+bestvideo[VCODEC=avc1]+bestaudio[ACODEC=mp4a]/mp4
+```
+2. Subscribe to some of your favorite YouTube channels on the **channels** page. 
+3. On the **downloads** page, click on *Rescan subscriptions* to add videos from the subscribed channels to your Download queue or click on *Add to download queue* to manually add Video IDs, links, channels or playlists.
+4. Click on *Start download* and let **Tube Archivist** to it's thing. 
+5. Enjoy your archived collection!
+  
 ## Roadmap
 This should be considered as a **minimal viable product**, there is an extensive list of future functions and improvements planned.
 
 ### Functionality
-- [ ] Access control
 - [ ] User roles
-- [ ] Delete videos and channel
 - [ ] Create playlists
-- [ ] Backup and restore
 - [ ] Podcast mode to serve channel as mp3
 - [ ] Implement [PyFilesystem](https://github.com/PyFilesystem/pyfilesystem2) for flexible video storage
-- [X] Scan your filesystem to index already downloaded videos [2021-09-14]
+- [ ] Optional automatic deletion of watched items after a specified time
+- [ ] Subtitle download & indexing
+- [X] Access control [2021-11-01]
+- [X] Delete videos and channel [2021-10-16]
+- [X] Add thumbnail embed option [2021-10-16]
+- [X] Un-ignore videos [2021-10-03]
+- [X] Dynamic download queue [2021-09-26]
+- [X] Backup and restore [2021-09-22]
+- [X] Scan your file system to index already downloaded videos [2021-09-14]
 
 ### UI
 - [ ] Show similar videos on video page
 - [ ] Multi language support
-- [ ] Grid and list view for both channel and video list pages
 - [ ] Show total video downloaded vs total videos available in channel
+- [X] Grid and list view for both channel and video list pages [2021-10-03]
+- [X] Create a github wiki for user documentation [2021-10-03]
 
 
 ## Known limitations
 - Video files created by Tube Archivist need to be **mp4** video files for best browser compatibility.
 - Every limitation of **yt-dlp** will also be present in Tube Archivist. If **yt-dlp** can't download or extract a video for any reason, Tube Archivist won't be able to either.
-- For now this is meant to be run in a trusted network environment.
+- For now this is meant to be run in a trusted network environment. Not everything is properly authenticated.
+- There is currently no flexibility in naming of the media files.
+
+
+## Donate
+The best donation to **Tube Archivist** is your time, take a look at the [contribution page](CONTRIBUTING.md) to get started.  
+Second best way to support the development is to provide for caffeinated beverages:
+* [Paypal.me](https://paypal.me/bbilly1) for a one time coffee
+* [Paypal Subscription](https://www.paypal.com/webapps/billing/plans/subscribe?plan_id=P-03770005GR991451KMFGVPMQ) for a monthly coffee
+* [co-fi.com](https://ko-fi.com/bbilly1) for an alternative platform

deploy.sh

@@ -5,11 +5,19 @@
 # blackhole for local production
 # docker to publish
 
+# create builder:
+# docker buildx create --name tubearchivist
+# docker buildx use tubearchivist
+# docker buildx inspect --bootstrap
+
+# more details:
+# https://github.com/bbilly1/tubearchivist/issues/6
+
 set -e
 
 function sync_blackhole {
 
-    # docker commands need sudo
+    # docker commands need sudo, only build amd64
     host="blackhole.local"
 
     read -sp 'Password: ' remote_pw
@@ -23,7 +31,7 @@ function sync_blackhole {
         --exclude "db.sqlite3" \
         . -e ssh "$host":tubearchivist
 
-    echo "$PASS" | ssh "$host" 'sudo -S docker build -t bbilly1/tubearchivist:latest tubearchivist 2>/dev/null'
+    echo "$PASS" | ssh "$host" 'sudo -S docker buildx build --platform linux/amd64 -t bbilly1/tubearchivist:latest tubearchivist --load 2>/dev/null'
     echo "$PASS" | ssh "$host" 'sudo -S docker-compose up -d 2>/dev/null'
 
 }
@@ -31,6 +39,8 @@ function sync_blackhole {
 function sync_test {
 
     # docker commands don't need sudo in testing vm
+    # pass argument to build for specific platform
+
     host="tubearchivist.local"
 
     rsync -a --progress --delete-after \
@@ -43,7 +53,17 @@ function sync_test {
 
     rsync -r --progress --delete docker-compose.yml -e ssh "$host":docker
 
-    ssh "$host" 'docker build -t bbilly1/tubearchivist:latest tubearchivist'
+    if [[ $1 = "amd64" ]]; then
+        platform="linux/amd64"
+    elif [[ $1 = "arm64" ]]; then
+        platform="linux/arm64"
+    elif [[ $1 = "multi" ]]; then
+        platform="linux/amd64,linux/arm64"
+    else
+        platform="linux/amd64"
+    fi
+
+    ssh "$host" "docker buildx build --platform $platform -t bbilly1/tubearchivist:latest tubearchivist --load"
     ssh "$host" 'docker-compose -f docker/docker-compose.yml up -d'
 
     ssh "$host" 'docker cp tubearchivist/tubearchivist/testing.sh tubearchivist:/app/testing.sh'
@@ -52,18 +72,74 @@ function sync_test {
 }
 
 
+# run same tests and checks as with github action but locally
+# takes filename to validate as optional argument
+function validate {
+
+    if [[ $1 ]]; then
+        check_path="$1"
+    else
+        check_path="."
+    fi
+
+    echo "run validate on $check_path"
+    
+    echo "running bandit"
+    bandit --recursive --skip B105,B108,B404,B603,B607 "$check_path"
+    echo "running black"
+    black --diff --color --check -l 79 "$check_path"
+    echo "running codespell"
+    codespell --skip="./.git" "$check_path"
+    echo "running flake8"
+    flake8 "$check_path" --count --max-complexity=12 --max-line-length=79 \
+        --show-source --statistics
+    echo "running isort"
+    isort --check-only --diff --profile black -l 79 "$check_path"
+    printf "    \n> all validations passed\n"
+
+}
+
+
 function sync_docker {
 
+    # check things
+    if [[ $(git branch --show-current) != 'master' ]]; then
+        echo 'you are not on master, dummy!'
+        return
+    fi
+
     if [[ $(systemctl is-active docker) != 'active' ]]; then
         echo "starting docker"
         sudo systemctl start docker
     fi
 
-    sudo docker build -t bbilly1/tubearchivist:latest .
-    sudo docker push bbilly1/tubearchivist:latest
+    echo "latest tags:"
+    git tag
+
+    echo "latest docker images:"
+    sudo docker image ls bbilly1/tubearchivist
+
+    printf "\ncreate new version:\n"
+    read -r VERSION
+
+    echo "build and push $VERSION?"
+    read -rn 1
+
+    # start build
+    sudo docker buildx build \
+        --platform linux/amd64,linux/arm64 \
+        -t bbilly1/tubearchivist:latest \
+        -t bbilly1/tubearchivist:"$VERSION" --push .
+
+    # create release tag
+    echo "commits since last version:"
+    git log "$(git describe --tags --abbrev=0)"..HEAD --oneline
+    git tag -a "$VERSION" -m "new release version $VERSION"
+    git push all "$VERSION"
 
 }
 
+
 # check package versions in requirements.txt for updates
 python version_check.py
 
@@ -71,11 +147,13 @@ python version_check.py
 if [[ $1 == "blackhole" ]]; then
     sync_blackhole
 elif [[ $1 == "test" ]]; then
-    sync_test
+    sync_test "$2"
+elif [[ $1 == "validate" ]]; then
+    validate "$2"
 elif [[ $1 == "docker" ]]; then
     sync_docker
 else
-    echo "valid options are: blackhole | test | docker"
+    echo "valid options are: blackhole | test | validate | docker"
 fi
 
 

docker-compose.yml

@@ -15,6 +15,9 @@ services:
       - REDIS_HOST=archivist-redis
       - HOST_UID=1000
       - HOST_GID=1000
+      - TA_USERNAME=tubearchivist
+      - TA_PASSWORD=verysecret
+      - ELASTIC_PASSWORD=verysecret
     depends_on:
       - archivist-es
       - archivist-redis
@@ -22,17 +25,19 @@ services:
     image: redislabs/rejson:latest
     container_name: archivist-redis
     restart: always
-    ports:
-      - 6379:6379
+    expose:
+      - "6379"
     volumes:
       - ./volumes/tubearchivist/redis:/data
     depends_on:
       - archivist-es
   archivist-es:
-    image: docker.elastic.co/elasticsearch/elasticsearch:7.14.1
+    image: docker.elastic.co/elasticsearch/elasticsearch:7.15.1
     container_name: archivist-es
     restart: always
     environment:
+      - "xpack.security.enabled=true"
+      - "ELASTIC_PASSWORD=verysecret"
       - "discovery.type=single-node"
       - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
     ulimits:
@@ -41,5 +46,5 @@ services:
         hard: -1
     volumes:
       - ./volumes/tubearchivist/es:/usr/share/elasticsearch/data
-    ports:
-      - 9200:9200
+    expose:
+      - "9200"

docs/Channels.md

@@ -0,0 +1,24 @@
+# Channels Overview and Channel Detail Page
+
+The channels are organized on two different levels:
+
+## Channels Overview
+Accessible at `/channel/` of your Tube Archivist, the **Overview Page** shows a list of all channels you have indexed. 
+- You can filter that list to show or hide subscribed channels from the drop down menu. Clicking on the channel banner or the channel name will direct you to the *Channel Detail Page*.
+- If you are subscribed to a channel a *Unsubscribe* button will show.
+
+The **Subscribe to Channels** button <img src="assets/icon-add.png?raw=true" alt="add icon" width="20px" style="margin:0 5px;"> opens a text field to subscribe to a channel. You have a few options:
+- Enter the YouTube channel ID, a 25 character alphanumeric string. For example *UCBa659QWEk1AI4Tg--mrJ2A*
+- Enter the URL to the channel page on YouTube. For example *https://www.youtube.com/channel/UCBa659QWEk1AI4Tg--mrJ2A*
+- Enter the channel name for example: *https://www.youtube.com/c/TomScottGo*.
+- Enter the video URL for any video and let Tube Archivist extract the channel ID for you. For example *https://www.youtube.com/watch?v=2tdiKTSdE9Y*
+- Add one per line.
+
+The search icon <img src="assets/icon-search.png?raw=true" alt="search icon" width="20px" style="margin:0 5px;"> opens a text box to search for indexed channel names. Possible matches will show as you type. 
+
+## Channel Detail
+Each channel will get a dedicated channel detail page accessible at `/channel/<channel-id>/` of your Tube Archivist. This page shows all the videos you have downloaded from this channel plus additional metadata. 
+- If you are subscribed to the channel, an *Unsubscribe* button will show.
+- You can *Show* the channel description, that matches with the *About* tab on YouTube.
+- The **Mark as Watched** button will mark all videos of this channel as watched.
+- The button **Delete Channel** will delete the channel plus all videos of this channel, both media files and metadata.

docs/Downloads.md

@@ -0,0 +1,35 @@
+# Downloads Page
+Accessible at `/downloads/` of your Tube Archivist, this page handles all the download functionality.
+
+
+## Rescan Subscriptions
+The **Rescan Subscriptions** icon <img src="assets/icon-rescan.png?raw=true" alt="rescan icon" width="20px" style="margin:0 5px;"> will start a background task to look for new videos from the channels you are subscribed to. You can define the channel page size on the [settings page](Settings#subscriptions). With the default channel page size, expect this process to take around 2-3 seconds for each channel you are subscribed to. A status message will show the progress.
+
+Then for every video found, **Tube Archivist** will skip the video if it has already been downloaded or if you added it to the *ignored* list before. All the other videos will get added to the download queue. Expect this to take around 1 second for each video as **Tube Archivist** needs to grab some additional metadata. New videos will get added at the bottom of the download queue.
+
+## Download Queue
+The **Start Download** icon <img src="assets/icon-download.png?raw=true" alt="download icon" width="20px" style="margin:0 5px;"> will start the download process starting from the top of the queue. Take a look at the relevant settings on the [Settings Page](Settings#downloads). Once the process started, a progress message will show with additional details and controls: 
+- The stop icon <img src="assets/icon-stop.png?raw=true" alt="stop icon" width="20px" style="margin:0 5px;"> will gracefully stop the download process, once the current video has been finished successfully.
+- The cancel icon <img src="assets/icon-close-red.png?raw=true" alt="close icon" width="20px" style="margin:0 5px;"> is equivalent to killing the process and will stop the download immediately. Any leftover files will get deleted, the canceled video will still be available in the download queue.
+
+## Add to Download Queue
+The **Add to Download Queue** icon <img src="assets/icon-add.png?raw=true" alt="add icon" width="20px" style="margin:0 5px;"> opens a text field to manually add videos to the download queue. You have a few options:
+- Add a link to a YouTube video. For example *https://www.youtube.com/watch?v=2tdiKTSdE9Y*.
+- Add a YouTube video ID. For example *2tdiKTSdE9Y*.
+- Add a link to a YouTube video by providing the shortened URL, for example *https://youtu.be/2tdiKTSdE9Y*.
+- Add a Channel ID or Channel URL to add every available video to the download queue. This will ignore the channel page size as described before and is meant for an initial download of the whole channel. You can still ignore selected videos before starting the download.
+- Add a channel name like for example *https://www.youtube.com/c/TomScottGo*.
+- Add a playlist ID or URL to add every available video in the list to the download queue, for example *https://www.youtube.com/playlist?list=PL96C35uN7xGLLeET0dOWaKHkAlPsrkcha* or *PL96C35uN7xGLLeET0dOWaKHkAlPsrkcha*. Note that when you add a link to a video in a playlist, Tube Archivist assumes you want to download only the specific video and not the whole playlist, for example *https://www.youtube.com/watch?v=CINVwWHlzTY&list=PL96C35uN7xGLLeET0dOWaKHkAlPsrkcha* will only add one video *CINVwWHlzTY* to the queue.
+- Add one link per line.
+
+## The Download Queue
+Below the three buttons you find the download queue. New items will get added at the bottom of the queue, the next video to download once you click on **Start Download** will be the first in the list.
+
+Every video in the download queue has two buttons:
+- **Ignore**: This will remove that video from the download queue and this video will not get added again, even when you **Rescan Subscriptions**.
+- **Download now**: This will give priority to this video. If the download process is already running, the prioritized video will get downloaded as soon as the current video is finished. If there is no download process running, this will start downloading this single video and stop after that.
+
+You can flip the view by activating **Show Only Ignored Videos**. This will show all videos you have previously *ignored*.  
+Every video in the ignored list has two buttons:
+- **Forget**: This will delete the item form the ignored list.
+- **Add to Queue**: This will add the ignored video back to the download queue.

docs/Home.md

@@ -0,0 +1,27 @@
+# Tube Archivist Wiki
+Welcome to the official Tube Archivist Wiki. This is an up-to-date documentation of user functionality.
+
+Table of contents:
+* [Main](Main): Tube Archivist landing page
+* [Channels](Channels): Browse your channels, handle subscriptions
+* [Downloads](Downloads): Scanning subscriptions, handle download queue
+* [Settings](Settings): All the configuration options
+* [Users](Users): User management admin interface
+
+## Getting Started
+1. [Subscribe](Channels#channels-overview) to some of your favourite YouTube channels.
+2. [Scan](Downloads#rescan-subscriptions) subscriptions to add the latest videos to the download queue.
+3. [Add](Downloads#add-to-download-queue) additional videos, channels or playlist - ignore the ones you don't want to download.
+4. [Download](Downloads#download-queue) and let **Tube Archivist** do it's thing.
+5. Sit back and enjoy your archived and indexed collection!
+
+## General Navigation
+* Clicking on the channel name or the channel icon brings you to the dedicated channel page to show videos from that channel.
+* Clicking on a video title brings you to the dedicated video page and shows additional details.
+* Clicking on a video thumbnail opens the video player and starts streaming the selected video.
+* Hover over the playing video to show additional control options.
+
+
+An empty checkbox icon <img src="assets/icon-unseen.png?raw=true" alt="unseen icon" width="20px" style="margin:0 5px;"> will show for videos you haven't marked as watched. Click on it and the icon will change to a filled checkbox <img src="assets/icon-seen.png?raw=true" alt="seen icon" width="20px" style="margin:0 5px;"> indicating it as watched - click again to revert.
+
+When available the <img src="assets/icon-gridview.png?raw=true" alt="gridview icon" width="20px" style="margin:0 5px;"> gridview icon will display the list in a grid, the <img src="assets/icon-listview.png?raw=true" alt="listview icon" width="20px" style="margin:0 5px;"> listview icon will arrange the items in a list.

docs/Main.md

@@ -0,0 +1,10 @@
+# Tube Archivist Home Page Functionality
+
+This is the landing page, when you first open **Tube Archivist**. You have a few options to sort and filter that view:
+- With the **Sort Order** you can select how the "Recent Videos" are sorted: 
+  - **Date Published**: Sorts the list by date when the video was published on YouTube, newest on top.
+  - **Date Downloaded**: Sorts the list based on when you have downloaded the video to your archive, newest on top.
+- With **Hide Watched** you can filter out videos you have already marked as watched to only show unwatched videos. 
+- You can use those two options together to for example filter the list to *Hide Watched* videos **and** sort by date downloaded.
+
+Additionally the search icon <img src="assets/icon-search.png?raw=true" alt="search icon" width="20px" style="margin:0 5px;"> opens a text field to search your collection.

docs/Settings.md

@@ -0,0 +1,73 @@
+# Settings Page
+Accessible at `/settings/` of your **Tube Archivist**, this page holds all the configurations and additional functionality related to the database.
+
+Click on **Update Settings** at the bottom of the form to apply your configurations.
+
+## Color scheme
+Switch between the easy on the eyes dark theme and the burning bright theme.
+
+## Archive View
+- **Page Size**: Defines how many results get displayed on a given page. Same value goes for all archive views.
+
+## Subscriptions
+Settings related to the channel management.
+- **Channel Page Size**: Defines how many pages will get analyzed by **Tube Archivist** each time you click on *Rescan Subscriptions*. The default page size used by yt-dlp is **50**, that's also the recommended value to set here. Any value higher will slow down the rescan process, for example if you set the value to 51, that means yt-dlp will have to go through 2 pages of results instead of 1 and by that doubling the time that process takes.
+
+## Downloads
+Settings related to the download process.
+- **Download Limit**: Stop the download process after downloading the set quantity of videos.
+- **Download Speed Limit**: Set your download speed limit in KB/s. This will pass the option `--limit-rate` to yt-dlp.
+- **Throttled Rate Limit**: Restart download if the download speed drops below this value in KB/s. This will pass the option `--throttled-rate` to yt-dlp. Using this option might have a negative effect if you have an unstable or slow internet connection.
+- **Sleep Interval**: Time in seconds to sleep between requests to YouTube. It's a good idea to set this to **3** seconds. Might be necessary to avoid throttling.
+
+## Download Format
+Additional settings passed to yt-dlp.
+- **Format**: This controls which streams get downloaded and is equivalent to passing `--format` to yt-dlp. Use one of the recommended one or look at the documentation of [yt-dlp](https://github.com/yt-dlp/yt-dlp#format-selection). Please note: The option `--merge-output-format mp4` is automatically passed to yt-dlp to guarantee browser compatibility.
+- **Embed Metadata**: This saves the available tags directly into the media file by passing `--embed-metadata` to yt-dlp.
+- **Embed Thumbnail**: This will save the thumbnail into the media file by passing `--embed-thumbnail` to yt-dlp.
+
+
+# Actions
+Additional database functionality.
+
+## Manual Media Files Import
+So far this depends on the video you are trying to import to be still available on YouTube to get the metadata. Add the files you like to import to the */cache/import* folder. Then start the process from the settings page *Manual Media Files Import*. Make sure to follow one of the two methods below.
+
+### Method 1:
+Add a matching *.json* file with the media file. Both files need to have the same base name, for example:
+- For the media file: \<base-name>.mp4
+- For the JSON file: \<base-name>.info.json
+- Alternate JSON file: \<base-name>.json
+
+**Tube Archivist** then looks for the 'id' key within the JSON file to identify the video.
+
+### Method 2:
+Detect the YouTube ID from filename, this accepts the default yt-dlp naming convention for file names like:
+- \<base-name>[\<youtube-id>].mp4
+- The YouTube ID in square brackets at the end of the filename is the crucial part.
+
+### Some notes:
+- This will **consume** the files you put into the import folder: Files will get converted to mp4 if needed (this might take a long time...) and moved to the archive, *.json* files will get deleted upon completion to avoid having duplicates on the next run.
+- Maybe start with a subset of your files to import to make sure everything goes well...
+- Follow the logs to monitor progress and errors: `docker-compose logs -f tubearchivist`.
+
+## Embed thumbnails into media file
+This will write or overwrite all thumbnails in the media file using the downloaded thumbnail. This is only necessary if you didn't download the files with the option *Embed Thumbnail* enabled or want to make sure all media files get the newest thumbnail. Follow the docker-compose logs to monitor progress.
+
+## Backup Database
+This will backup your metadata into a zip file. The file will get stored at *cache/backup* and will contain the necessary files to restore the Elasticsearch index formatted **nd-json** files plus a complete export of the index in a set of conventional **json** files.  
+
+BE AWARE: This will **not** backup any media files, just the metadata from the Elasticsearch.
+
+## Restore From Backup
+The restore functionality will expect the same zip file in *cache/backup* as created from the **Backup database** function. This will recreate the index from the snapshot. If there are multiple backup files in the folder, the newest one will take priority. 
+
+BE AWARE: This will **replace** your current index with the one from the backup file. This won't restore any media files.
+
+## Rescan Filesystem
+This function will go through all your media files and looks at the whole index to try to find any issues:
+- Should the filename not match with the indexed media url, this will rename the video files correctly and update the index with the new link.
+- When you delete media files from the filesystem outside of the Tube Archivist interface, this will delete leftover metadata from the index.
+- When you have media files that are not indexed yet, this will grab the metadata from YouTube like it was a newly downloaded video. This can be useful when restoring from an older backup file with missing metadata but already downloaded mediafiles. NOTE: This only works if the media files are named in the same convention as Tube Archivist does, particularly the YouTube ID needs to be at the same index in the filename, alternatively see above for *Manual Media Files Import*.
+
+BE AWARE: There is no undo.

docs/Users.md

@@ -0,0 +1,20 @@
+# User Management
+
+For now, **Tube Archivist** is a single user application. You can create multiple users with different names and passwords, they will share the same videos and permissions but some interface configurations are on a per user basis. *More is on the roadmap*.
+
+## Superuser
+The first user gets created with the environment variables **TA_USERNAME** and **TA_PASSWORD** from your docker-compose file. That first user will automatically have *superuser* privileges. 
+
+## Admin Interface
+When logged in from your *superuser* account, you are able to access the admin interface from the settings page or at `/admin/`. This interface holds all functionality for user management.
+
+## Create additional users
+From the admin interface when you click on *Accounts* you will get a list of all users. From there you can create additional users by clicking on *Add Account*, provide a name and confirm password and click on *Save* to create the user.
+
+## Changing users
+You can delete or change permissions and password of a user by clicking on the username from the *Accounts* list page and follow the interface from there. Changing the password of the *superuser* here will overwrite the password originally set with the environment variables.
+
+## Reset
+Delete all user configurations by deleting the file `cache/db.sqlite3` and restart the container. This will create the superuser again from the environment variables.
+
+NOTE: Future improvements here will most likely require such a reset.

run.sh

@@ -1,19 +1,38 @@
 #!/bin/bash
 # startup script inside the container for tubearchivist
 
+# check environment
+if [[ -z "$ELASTIC_USER" ]]; then
+    export ELASTIC_USER=elastic
+fi
+
+ENV_VARS=("TA_USERNAME" "TA_PASSWORD" "ELASTIC_PASSWORD" "ELASTIC_USER")
+for each in "${ENV_VARS[@]}"; do
+    if ! [[ -v $each ]]; then
+        echo "missing environment variable $each"
+        exit 1
+    fi
+done
+
+# wait for elasticsearch
 counter=0
-until curl "$ES_URL" -fs; do
+until curl -u "$ELASTIC_USER":"$ELASTIC_PASSWORD" "$ES_URL" -fs; do
     echo "waiting for elastic search to start"
     counter=$((counter+1))
     if [[ $counter -eq 12 ]]; then
-        # fail after 1 min
+        # fail after 2 min
         echo "failed to connect to elastic search, exiting..."
         exit 1
     fi
-    sleep 5
+    sleep 10
 done
 
+# start python application
+python manage.py makemigrations
 python manage.py migrate
+export DJANGO_SUPERUSER_PASSWORD=$TA_PASSWORD && \
+    python manage.py createsuperuser --noinput --name "$TA_USERNAME"
+
 python manage.py collectstatic --noinput -c
 nginx &
 celery -A home.tasks worker --loglevel=INFO &

tubearchivist/config/asgi.py

@@ -11,6 +11,6 @@ import os
 
 from django.core.asgi import get_asgi_application
 
-os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "config.settings")
 
 application = get_asgi_application()

tubearchivist/config/settings.py

@@ -10,8 +10,11 @@ For the full list of settings and their values, see
 https://docs.djangoproject.com/en/3.2/ref/settings/
 """
 
+import hashlib
+from os import environ, path
 from pathlib import Path
-from os import environ
+
+from home.src.config import AppConfig
 
 # Build paths inside the project like this: BASE_DIR / 'subdir'.
 BASE_DIR = Path(__file__).resolve().parent.parent
@@ -20,68 +23,70 @@ BASE_DIR = Path(__file__).resolve().parent.parent
 # Quick-start development settings - unsuitable for production
 # See https://docs.djangoproject.com/en/3.2/howto/deployment/checklist/
 
-# SECURITY WARNING: keep the secret key used in production secret!
-SECRET_KEY = 'Fvid^aUL6LohRZz*kZFvq85B&JW&kB9o*#jdzWsdWE8*XkCLR8'
+PW_HASH = hashlib.sha256(environ.get("TA_PASSWORD").encode())
+SECRET_KEY = PW_HASH.hexdigest()
 
 # SECURITY WARNING: don't run with debug turned on in production!
-DEBUG = bool(environ.get('DJANGO_DEBUG'))
+DEBUG = bool(environ.get("DJANGO_DEBUG"))
 
-ALLOWED_HOSTS = ['*']
+ALLOWED_HOSTS = ["*"]
 
 
 # Application definition
 
 INSTALLED_APPS = [
-    'home.apps.HomeConfig',
-    'django.contrib.admin',
-    'django.contrib.auth',
-    'django.contrib.contenttypes',
-    'django.contrib.sessions',
-    'django.contrib.messages',
-    'whitenoise.runserver_nostatic',
-    'django.contrib.staticfiles',
-    'django.contrib.humanize'
+    "home.apps.HomeConfig",
+    "django.contrib.admin",
+    "django.contrib.auth",
+    "django.contrib.contenttypes",
+    "django.contrib.sessions",
+    "django.contrib.messages",
+    "whitenoise.runserver_nostatic",
+    "django.contrib.staticfiles",
+    "django.contrib.humanize",
 ]
 
 MIDDLEWARE = [
-    'django.middleware.security.SecurityMiddleware',
-    'django.contrib.sessions.middleware.SessionMiddleware',
-    'whitenoise.middleware.WhiteNoiseMiddleware',
-    'django.middleware.common.CommonMiddleware',
-    'django.middleware.csrf.CsrfViewMiddleware',
-    'django.contrib.auth.middleware.AuthenticationMiddleware',
-    'django.contrib.messages.middleware.MessageMiddleware',
-    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+    "django.middleware.security.SecurityMiddleware",
+    "django.contrib.sessions.middleware.SessionMiddleware",
+    "whitenoise.middleware.WhiteNoiseMiddleware",
+    "django.middleware.common.CommonMiddleware",
+    "django.middleware.csrf.CsrfViewMiddleware",
+    "django.contrib.auth.middleware.AuthenticationMiddleware",
+    "django.contrib.messages.middleware.MessageMiddleware",
+    "django.middleware.clickjacking.XFrameOptionsMiddleware",
 ]
 
-ROOT_URLCONF = 'config.urls'
+ROOT_URLCONF = "config.urls"
 
 TEMPLATES = [
     {
-        'BACKEND': 'django.template.backends.django.DjangoTemplates',
-        'DIRS': [],
-        'APP_DIRS': True,
-        'OPTIONS': {
-            'context_processors': [
-                'django.template.context_processors.debug',
-                'django.template.context_processors.request',
-                'django.contrib.auth.context_processors.auth',
-                'django.contrib.messages.context_processors.messages',
+        "BACKEND": "django.template.backends.django.DjangoTemplates",
+        "DIRS": [],
+        "APP_DIRS": True,
+        "OPTIONS": {
+            "context_processors": [
+                "django.template.context_processors.debug",
+                "django.template.context_processors.request",
+                "django.contrib.auth.context_processors.auth",
+                "django.contrib.messages.context_processors.messages",
             ],
         },
     },
 ]
 
-WSGI_APPLICATION = 'config.wsgi.application'
+WSGI_APPLICATION = "config.wsgi.application"
 
 
 # Database
 # https://docs.djangoproject.com/en/3.2/ref/settings/#databases
 
+CACHE_DIR = AppConfig().config["application"]["cache_dir"]
+DB_PATH = path.join(CACHE_DIR, "db.sqlite3")
 DATABASES = {
-    'default': {
-        'ENGINE': 'django.db.backends.sqlite3',
-        'NAME': BASE_DIR / 'db.sqlite3',
+    "default": {
+        "ENGINE": "django.db.backends.sqlite3",
+        "NAME": DB_PATH,
     }
 }
 
@@ -91,54 +96,44 @@ DATABASES = {
 
 AUTH_PASSWORD_VALIDATORS = [
     {
-        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+        "NAME": "django.contrib.auth.password_validation.UserAttributeSimilarityValidator",  # noqa: E501
     },
     {
-        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+        "NAME": "django.contrib.auth.password_validation.MinimumLengthValidator",  # noqa: E501
     },
     {
-        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+        "NAME": "django.contrib.auth.password_validation.CommonPasswordValidator",  # noqa: E501
     },
     {
-        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+        "NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",  # noqa: E501
     },
 ]
 
+AUTH_USER_MODEL = "home.Account"
+
 
 # Internationalization
 # https://docs.djangoproject.com/en/3.2/topics/i18n/
 
-LANGUAGE_CODE = 'en-us'
-
-TIME_ZONE = 'UTC'
-
+LANGUAGE_CODE = "en-us"
+TIME_ZONE = "UTC"
 USE_I18N = True
-
 USE_L10N = True
-
 USE_TZ = True
 
 
 # Static files (CSS, JavaScript, Images)
 # https://docs.djangoproject.com/en/3.2/howto/static-files/
 
-STATIC_URL = '/static/'
-
-# STATICFILES_DIRS = [
-#     str(BASE_DIR.joinpath('static')),
-#     '/cache/'
-# ]
-
-# STATIC_URL = '/static/'
-STATICFILES_DIRS = (str(BASE_DIR.joinpath('static')),)
-# MEDIA_ROOT = str(BASE_DIR.joinpath('media'))
-# MEDIA_URL = '/media/'
-
-STATIC_ROOT = str(BASE_DIR.joinpath('staticfiles'))
-
-STATICFILES_STORAGE = 'whitenoise.storage.CompressedManifestStaticFilesStorage'
+STATIC_URL = "/static/"
+STATICFILES_DIRS = (str(BASE_DIR.joinpath("static")),)
+STATIC_ROOT = str(BASE_DIR.joinpath("staticfiles"))
+STATICFILES_STORAGE = "whitenoise.storage.CompressedManifestStaticFilesStorage"
 
 # Default primary key field type
 # https://docs.djangoproject.com/en/3.2/ref/settings/#default-auto-field
 
-DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
+DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
+
+LOGIN_URL = "/login/"
+LOGOUT_REDIRECT_URL = "/login/"

tubearchivist/config/urls.py

@@ -14,9 +14,9 @@ Including another URLconf
     2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
 """
 from django.contrib import admin
-from django.urls import path, include
+from django.urls import include, path
 
 urlpatterns = [
-    path('', include('home.urls')),
-    path('admin/', admin.site.urls),
+    path("", include("home.urls")),
+    path("admin/", admin.site.urls),
 ]

tubearchivist/config/wsgi.py

@@ -11,6 +11,6 @@ import os
 
 from django.core.wsgi import get_wsgi_application
 
-os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "config.settings")
 
 application = get_wsgi_application()

tubearchivist/home/__init__.py

@@ -1,40 +1,5 @@
-""" handle startup """
-
-import os
-
-from home.src.config import AppConfig
-from home.src.helper import set_message
-from home.src.index_management import index_check
+""" handle celery startup """
 
 from .tasks import app as celery_app
 
-
-def sync_redis_state():
-    """ make sure redis gets the config.json values """
-    print('sync redis')
-    config = AppConfig().config
-    sort_order = config['archive']['sort']
-    set_message('sort_order', sort_order, expire=False)
-    hide_watched = bool(int(config['archive']['hide_watched']))
-    set_message('hide_watched', hide_watched, expire=False)
-    show_subed_only = bool(int(config['archive']['show_subed_only']))
-    set_message('show_subed_only', show_subed_only, expire=False)
-
-
-def make_folders():
-    """ make needed cache folders here so docker doesn't mess it up """
-    folders = ['download', 'channels', 'videos', 'import', 'backup']
-    config = AppConfig().config
-    cache_dir = config['application']['cache_dir']
-    for folder in folders:
-        folder_path = os.path.join(cache_dir, folder)
-        try:
-            os.makedirs(folder_path)
-        except FileExistsError:
-            continue
-
-
-__all__ = ('celery_app',)
-make_folders()
-sync_redis_state()
-index_check()
+__all__ = ("celery_app",)

tubearchivist/home/admin.py

@@ -1,3 +1,36 @@
-from django.contrib import admin
+"""custom admin classes"""
 
-# Register your models here.
+from django.contrib import admin
+from django.contrib.auth.admin import UserAdmin as BaseUserAdmin
+
+from .models import Account
+
+
+class HomeAdmin(BaseUserAdmin):
+    """register in admin page"""
+
+    list_display = ("name", "is_staff", "is_superuser")
+    list_filter = ("is_superuser",)
+
+    fieldsets = (
+        (None, {"fields": ("is_staff", "is_superuser", "password")}),
+        ("Personal info", {"fields": ("name",)}),
+        ("Groups", {"fields": ("groups",)}),
+        ("Permissions", {"fields": ("user_permissions",)}),
+    )
+    add_fieldsets = (
+        (
+            None,
+            {"fields": ("is_staff", "is_superuser", "password1", "password2")},
+        ),
+        ("Personal info", {"fields": ("name",)}),
+        ("Groups", {"fields": ("groups",)}),
+        ("Permissions", {"fields": ("user_permissions",)}),
+    )
+
+    search_fields = ("name",)
+    ordering = ("name",)
+    filter_horizontal = ()
+
+
+admin.site.register(Account, HomeAdmin)

tubearchivist/home/apps.py

@@ -1,6 +1,52 @@
+"""handle custom startup functions"""
+
+import os
+
 from django.apps import AppConfig
+from home.src.config import AppConfig as ArchivistConfig
+from home.src.helper import RedisArchivist
+from home.src.index_management import index_check
+from home.src.thumbnails import validate_thumbnails
+
+
+def sync_redis_state():
+    """make sure redis gets new config.json values"""
+    print("sync redis")
+    config_handler = ArchivistConfig()
+    config_handler.load_new_defaults()
+
+
+def make_folders():
+    """make needed cache folders here so docker doesn't mess it up"""
+    folders = ["download", "channels", "videos", "import", "backup"]
+    config = ArchivistConfig().config
+    cache_dir = config["application"]["cache_dir"]
+    for folder in folders:
+        folder_path = os.path.join(cache_dir, folder)
+        try:
+            os.makedirs(folder_path)
+        except FileExistsError:
+            continue
+
+
+def release_lock():
+    """make sure there are no leftover locks set in redis on container start"""
+    all_locks = ["manual_import", "downloading", "dl_queue", "dl_queue_id"]
+    for lock in all_locks:
+        response = RedisArchivist().del_message(lock)
+        if response:
+            print("deleted leftover key from redis: " + lock)
 
 
 class HomeConfig(AppConfig):
-    default_auto_field = 'django.db.models.BigAutoField'
-    name = 'home'
+    """call startup funcs"""
+
+    default_auto_field = "django.db.models.BigAutoField"
+    name = "home"
+
+    def ready(self):
+        release_lock()
+        index_check()
+        sync_redis_state()
+        make_folders()
+        validate_thumbnails()

tubearchivist/home/config.json

@@ -1,25 +1,33 @@
 {
     "archive": {
-        "sort": "published",
-        "hide_watched": false,
-        "show_subed_only": false,
+        "sort_by": "published",
+        "sort_order": "desc",
         "page_size": 12
     },
+    "default_view": {
+        "home": "grid",
+        "channel": "list",
+        "downloads": "list"
+    },
     "subscriptions": {
         "auto_search": false,
         "auto_download": false,
         "channel_size": 50
     },
     "downloads": {
-        "limit_count": 5,
+        "limit_count": false,
         "limit_speed": false,
         "sleep_interval": 3,
-        "format": false
+        "format": false,
+        "add_metadata": false,
+        "add_thumbnail": false,
+        "throttledratelimit": false
     },
     "application": {
+        "app_root": "/app",
         "cache_dir": "/cache",
         "videos": "/youtube",
         "file_template": "%(id)s_%(title)s.mp4",
         "colors": "dark"
     }
-}
+}

tubearchivist/home/forms.py

@@ -0,0 +1,114 @@
+"""functionality:
+- hold all form classes used in the views
+"""
+
+from django import forms
+from django.contrib.auth.forms import AuthenticationForm
+from django.forms.widgets import PasswordInput, TextInput
+
+
+class CustomAuthForm(AuthenticationForm):
+    """better styled login form"""
+
+    username = forms.CharField(
+        widget=TextInput(attrs={"placeholder": "Username"}), label=False
+    )
+    password = forms.CharField(
+        widget=PasswordInput(attrs={"placeholder": "Password"}), label=False
+    )
+
+
+class UserSettingsForm(forms.Form):
+    """user configurations values"""
+
+    CHOICES = [
+        ("", "-- change color scheme --"),
+        ("dark", "Dark"),
+        ("light", "Light"),
+    ]
+
+    colors = forms.ChoiceField(
+        widget=forms.Select, choices=CHOICES, required=False
+    )
+    page_size = forms.IntegerField(required=False)
+
+
+class ApplicationSettingsForm(forms.Form):
+    """handle all application settings"""
+
+    METADATA_CHOICES = [
+        ("", "-- change metadata embed --"),
+        ("0", "don't embed metadata"),
+        ("1", "embed metadata"),
+    ]
+
+    THUMBNAIL_CHOICES = [
+        ("", "-- change thumbnail embed --"),
+        ("0", "don't embed thumbnail"),
+        ("1", "embed thumbnail"),
+    ]
+
+    subscriptions_channel_size = forms.IntegerField(required=False)
+    downloads_limit_count = forms.IntegerField(required=False)
+    downloads_limit_speed = forms.IntegerField(required=False)
+    downloads_throttledratelimit = forms.IntegerField(required=False)
+    downloads_sleep_interval = forms.IntegerField(required=False)
+    downloads_format = forms.CharField(required=False)
+    downloads_add_metadata = forms.ChoiceField(
+        widget=forms.Select, choices=METADATA_CHOICES, required=False
+    )
+    downloads_add_thumbnail = forms.ChoiceField(
+        widget=forms.Select, choices=THUMBNAIL_CHOICES, required=False
+    )
+
+
+class VideoSearchForm(forms.Form):
+    """search videos form"""
+
+    searchInput = forms.CharField(
+        label="Search your videos",
+        widget=forms.TextInput(attrs={"autocomplete": "off"}),
+    )
+
+
+class ChannelSearchForm(forms.Form):
+    """search for channels"""
+
+    searchInput = forms.CharField(
+        label="",
+        widget=forms.TextInput(
+            attrs={
+                "oninput": "searchChannels(this.value)",
+                "autocomplete": "off",
+                "list": "resultBox",
+            }
+        ),
+    )
+
+
+class AddToQueueForm(forms.Form):
+    """text area form to add to downloads"""
+
+    vid_url = forms.CharField(
+        label=False,
+        widget=forms.Textarea(
+            attrs={
+                "rows": 4,
+                "placeholder": "Enter Video Urls or IDs here...",
+            }
+        ),
+    )
+
+
+class SubscribeToChannelForm(forms.Form):
+    """text area form to subscribe to multiple channels"""
+
+    subscribe = forms.CharField(
+        label=False,
+        widget=forms.Textarea(
+            attrs={
+                "rows": 3,
+                "placeholder": "Input channel ID, URL or Video of a channel",
+            }
+        ),
+    )

tubearchivist/home/models.py

@@ -1,3 +1,53 @@
+"""custom models"""
+from django.contrib.auth.models import (
+    AbstractBaseUser,
+    BaseUserManager,
+    PermissionsMixin,
+)
 from django.db import models
 
-# Create your models here.
+
+class AccountManager(BaseUserManager):
+    """manage user creation methods"""
+
+    use_in_migrations = True
+
+    def _create_user(self, name, password, **extra_fields):
+        """create regular user private"""
+        values = [name, password]
+        field_value_map = dict(zip(self.model.REQUIRED_FIELDS, values))
+        for field_name, value in field_value_map.items():
+            if not value:
+                raise ValueError(f"The {field_name} value must be set")
+
+        user = self.model(name=name, **extra_fields)
+        user.set_password(password)
+        user.save(using=self._db)
+        return user
+
+    def create_user(self, name, password):
+        """create regular user public"""
+        return self._create_user(name, password)
+
+    def create_superuser(self, name, password, **extra_fields):
+        """create super user"""
+        extra_fields.setdefault("is_staff", True)
+        extra_fields.setdefault("is_superuser", True)
+
+        if extra_fields.get("is_staff") is not True:
+            raise ValueError("Superuser must have is_staff=True.")
+        if extra_fields.get("is_superuser") is not True:
+            raise ValueError("Superuser must have is_superuser=True.")
+
+        return self._create_user(name, password, **extra_fields)
+
+
+class Account(AbstractBaseUser, PermissionsMixin):
+    """handle account creation"""
+
+    name = models.CharField(max_length=150, unique=True)
+    is_staff = models.BooleanField(default=False)
+    objects = AccountManager()
+
+    USERNAME_FIELD = "name"
+    REQUIRED_FIELDS = ["password"]

tubearchivist/home/src/config.py

@@ -8,53 +8,145 @@ Functionality:
 import json
 import os
 
-from home.src.helper import get_message, set_message
+from home.src.helper import RedisArchivist
 
 
 class AppConfig:
-    """ handle user settings and application variables """
+    """handle user settings and application variables"""
 
-    def __init__(self):
+    def __init__(self, user_id=False):
+        self.user_id = user_id
         self.config = self.get_config()
+        self.colors = self.get_colors()
 
     def get_config(self):
-        """ get config from default file or redis if changed """
+        """get config from default file or redis if changed"""
         config = self.get_config_redis()
         if not config:
-            with open('home/config.json', 'r', encoding="utf-8") as f:
-                config_str = f.read()
-                config = json.loads(config_str)
+            config = self.get_config_file()
 
-        config['application']['REDIS_HOST'] = os.environ.get('REDIS_HOST')
-        config['application']['es_url'] = os.environ.get('ES_URL')
-        config['application']['HOST_UID'] = int(os.environ.get('HOST_UID'))
-        config['application']['HOST_GID'] = int(os.environ.get('HOST_GID'))
+        if self.user_id:
+            key = f"{self.user_id}:page_size"
+            page_size = RedisArchivist().get_message(key)["status"]
+            if page_size:
+                config["archive"]["page_size"] = page_size
+
+        config["application"].update(self.get_config_env())
         return config
 
+    def get_config_file(self):
+        """read the defaults from config.json"""
+        with open("home/config.json", "r", encoding="utf-8") as f:
+            config_str = f.read()
+            config_file = json.loads(config_str)
+
+        config_file["application"].update(self.get_config_env())
+
+        return config_file
+
+    @staticmethod
+    def get_config_env():
+        """read environment application variables"""
+        host_uid_env = os.environ.get("HOST_UID")
+        if host_uid_env:
+            host_uid = int(host_uid_env)
+        else:
+            host_uid = False
+
+        host_gid_env = os.environ.get("HOST_GID")
+        if host_gid_env:
+            host_gid = int(host_gid_env)
+        else:
+            host_gid = False
+
+        es_pass = os.environ.get("ELASTIC_PASSWORD")
+        es_user = os.environ.get("ELASTIC_USER", default="elastic")
+
+        application = {
+            "REDIS_HOST": os.environ.get("REDIS_HOST"),
+            "es_url": os.environ.get("ES_URL"),
+            "es_auth": (es_user, es_pass),
+            "HOST_UID": host_uid,
+            "HOST_GID": host_gid,
+        }
+
+        return application
+
     @staticmethod
     def get_config_redis():
-        """ read config json set from redis to overwrite defaults """
-        config = get_message('config')
+        """read config json set from redis to overwrite defaults"""
+        config = RedisArchivist().get_message("config")
         if not list(config.values())[0]:
             return False
 
         return config
 
     def update_config(self, form_post):
-        """ update config values from settings form """
+        """update config values from settings form"""
         config = self.config
         for key, value in form_post.items():
             to_write = value[0]
             if len(to_write):
-                if to_write == '0':
+                if to_write == "0":
                     to_write = False
+                elif to_write == "1":
+                    to_write = True
                 elif to_write.isdigit():
                     to_write = int(to_write)
 
-                config_dict, config_value = key.split('.')
+                config_dict, config_value = key.split("_", maxsplit=1)
                 config[config_dict][config_value] = to_write
 
-        with open('home/config.json', 'w', encoding="utf-8") as f:
-            f.write(json.dumps(config))
+        RedisArchivist().set_message("config", config, expire=False)
 
-        set_message('config', config, expire=False)
+    @staticmethod
+    def set_user_config(form_post, user_id):
+        """set values in redis for user settings"""
+        for key, value in form_post.items():
+            to_write = value[0]
+            if len(to_write):
+                if to_write.isdigit():
+                    to_write = int(to_write)
+                message = {"status": to_write}
+                redis_key = f"{user_id}:{key}"
+                RedisArchivist().set_message(redis_key, message, expire=False)
+
+    def get_colors(self):
+        """overwrite config if user has set custom values"""
+        colors = False
+        if self.user_id:
+            col_dict = RedisArchivist().get_message(f"{self.user_id}:colors")
+            colors = col_dict["status"]
+
+        if not colors:
+            colors = self.config["application"]["colors"]
+
+        self.config["application"]["colors"] = colors
+        return colors
+
+    def load_new_defaults(self):
+        """check config.json for missing defaults"""
+        default_config = self.get_config_file()
+        redis_config = self.get_config_redis()
+
+        # check for customizations
+        if not redis_config:
+            return
+
+        needs_update = False
+
+        for key, value in default_config.items():
+            # missing whole main key
+            if key not in redis_config:
+                redis_config.update({key: value})
+                needs_update = True
+                continue
+
+            # missing nested values
+            for sub_key, sub_value in value.items():
+                if sub_key not in redis_config[key].keys():
+                    redis_config[key].update({sub_key: sub_value})
+                    needs_update = True
+
+        if needs_update:
+            RedisArchivist().set_message("config", redis_config, expire=False)

tubearchivist/home/src/download.py

@@ -6,30 +6,39 @@ Functionality:
 """
 
 import json
-import shutil
 import os
-
+import shutil
 from datetime import datetime
 from time import sleep
 
 import requests
 import yt_dlp as youtube_dl
-
-from home.src.index import YoutubeChannel, index_new_video
 from home.src.config import AppConfig
-from home.src.helper import clean_string, DurationConverter, set_message
+from home.src.helper import (
+    DurationConverter,
+    RedisArchivist,
+    RedisQueue,
+    clean_string,
+    ignore_filelist,
+)
+from home.src.index import YoutubeChannel, index_new_video
 
 
 class PendingList:
-    """ manage the pending videos list """
+    """manage the pending videos list"""
 
     CONFIG = AppConfig().config
-    ES_URL = CONFIG['application']['es_url']
-    VIDEOS = CONFIG['application']['videos']
+    ES_URL = CONFIG["application"]["es_url"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
+    VIDEOS = CONFIG["application"]["videos"]
+
+    def __init__(self):
+        self.all_channel_ids = False
+        self.all_downloaded = False
 
     @staticmethod
     def parse_url_list(youtube_ids):
-        """ extract youtube ids from list """
+        """extract youtube ids from list"""
         missing_videos = []
         for entry in youtube_ids:
             # notify
@@ -37,313 +46,366 @@ class PendingList:
                 "status": "pending",
                 "level": "info",
                 "title": "Adding to download queue.",
-                "message": 'Extracting lists'
+                "message": "Extracting lists",
             }
-            set_message('progress:download', mess_dict)
+            RedisArchivist().set_message("progress:download", mess_dict)
             # extract
-            url = entry['url']
-            url_type = entry['type']
-            if url_type == 'video':
+            url = entry["url"]
+            url_type = entry["type"]
+            if url_type == "video":
                 missing_videos.append(url)
-            elif url_type == 'channel':
-                youtube_ids = ChannelSubscription().get_last_youtube_videos(
+            elif url_type == "channel":
+                video_results = ChannelSubscription().get_last_youtube_videos(
                     url, limit=False
                 )
+                youtube_ids = [i[0] for i in video_results]
                 missing_videos = missing_videos + youtube_ids
-            elif url_type == 'playlist':
-                youtube_ids = playlist_extractor(url)
+            elif url_type == "playlist":
+                video_results = playlist_extractor(url)
+                youtube_ids = [i[0] for i in video_results]
                 missing_videos = missing_videos + youtube_ids
 
         return missing_videos
 
     def add_to_pending(self, missing_videos):
-        """ build the bulk json data from pending """
+        """build the bulk json data from pending"""
         # check if channel is indexed
         channel_handler = ChannelSubscription()
         all_indexed = channel_handler.get_channels(subscribed_only=False)
-        all_channel_ids = [i['channel_id'] for i in all_indexed]
+        self.all_channel_ids = [i["channel_id"] for i in all_indexed]
         # check if already there
-        all_downloaded = self.get_all_downloaded()
-        # loop
+        self.all_downloaded = self.get_all_downloaded()
+
+        bulk_list, all_videos_added = self.build_bulk(missing_videos)
+        # add last newline
+        bulk_list.append("\n")
+        query_str = "\n".join(bulk_list)
+        headers = {"Content-type": "application/x-ndjson"}
+        url = self.ES_URL + "/_bulk"
+        request = requests.post(
+            url, data=query_str, headers=headers, auth=self.ES_AUTH
+        )
+        if not request.ok:
+            print(request)
+
+        return all_videos_added
+
+    def build_bulk(self, missing_videos):
+        """build the bulk lists"""
         bulk_list = []
-        for video in missing_videos:
-            if isinstance(video, str):
-                youtube_id = video
-            elif isinstance(video, tuple):
-                youtube_id = video[0]
-            if youtube_id in all_downloaded:
-                # skip already downlaoded
+        all_videos_added = []
+        counter = 1
+        for youtube_id in missing_videos:
+            # check if already downloaded
+            if youtube_id in self.all_downloaded:
                 continue
+
             video = self.get_youtube_details(youtube_id)
             # skip on download error
             if not video:
                 continue
 
-            if video['channel_id'] in all_channel_ids:
-                video['channel_indexed'] = True
-            else:
-                video['channel_indexed'] = False
-            video['status'] = "pending"
+            channel_indexed = video["channel_id"] in self.all_channel_ids
+            video["channel_indexed"] = channel_indexed
+            thumb_url = video["vid_thumb_url"]
+            video["status"] = "pending"
             action = {"create": {"_id": youtube_id, "_index": "ta_download"}}
             bulk_list.append(json.dumps(action))
             bulk_list.append(json.dumps(video))
+            all_videos_added.append((youtube_id, thumb_url))
             # notify
+            progress = f"{counter}/{len(missing_videos)}"
             mess_dict = {
                 "status": "pending",
                 "level": "info",
-                "title": "Adding to download queue.",
-                "message": 'Processing IDs...'
+                "title": "Adding new videos to download queue.",
+                "message": "Progress: " + progress,
             }
-            set_message('progress:download', mess_dict)
-        # add last newline
-        bulk_list.append('\n')
-        query_str = '\n'.join(bulk_list)
-        headers = {'Content-type': 'application/x-ndjson'}
-        url = self.ES_URL + '/_bulk'
-        request = requests.post(url, data=query_str, headers=headers)
-        if not request.ok:
-            print(request)
+            RedisArchivist().set_message("progress:download", mess_dict)
+            if counter % 25 == 0:
+                print("adding to queue progress: " + progress)
+            counter = counter + 1
+
+        return bulk_list, all_videos_added
 
     @staticmethod
     def get_youtube_details(youtube_id):
-        """ get details from youtubedl for single pending video """
+        """get details from youtubedl for single pending video"""
         obs = {
-            'default_search': 'ytsearch',
-            'quiet': True,
-            'skip_download': True,
+            "default_search": "ytsearch",
+            "quiet": True,
+            "skip_download": True,
         }
         try:
             vid = youtube_dl.YoutubeDL(obs).extract_info(youtube_id)
         except youtube_dl.utils.DownloadError:
-            print('failed to extract info for: ' + youtube_id)
+            print("failed to extract info for: " + youtube_id)
+            return False
+        # stop if video is streaming live now
+        if vid["is_live"]:
             return False
         # parse response
-        seconds = vid['duration']
+        seconds = vid["duration"]
         duration_str = DurationConverter.get_str(seconds)
-        upload_date = vid['upload_date']
+        if duration_str == "NA":
+            print(f"skip extracting duration for: {youtube_id}")
+        upload_date = vid["upload_date"]
         upload_dt = datetime.strptime(upload_date, "%Y%m%d")
         published = upload_dt.strftime("%Y-%m-%d")
         # build dict
         youtube_details = {
             "youtube_id": youtube_id,
-            "channel_name": vid['channel'],
-            "vid_thumb_url": vid['thumbnail'],
-            "title": vid['title'],
-            "channel_id": vid['channel_id'],
+            "channel_name": vid["channel"],
+            "vid_thumb_url": vid["thumbnail"],
+            "title": vid["title"],
+            "channel_id": vid["channel_id"],
             "duration": duration_str,
             "published": published,
-            "timestamp": int(datetime.now().strftime("%s"))
+            "timestamp": int(datetime.now().strftime("%s")),
         }
         return youtube_details
 
     def get_all_pending(self):
-        """ get a list of all pending videos in ta_download """
-        headers = {'Content-type': 'application/json'}
+        """get a list of all pending videos in ta_download"""
+        headers = {"Content-type": "application/json"}
         # get PIT ID
-        url = self.ES_URL + '/ta_download/_pit?keep_alive=1m'
-        response = requests.post(url)
+        url = self.ES_URL + "/ta_download/_pit?keep_alive=1m"
+        response = requests.post(url, auth=self.ES_AUTH)
         json_data = json.loads(response.text)
-        pit_id = json_data['id']
+        pit_id = json_data["id"]
         # query
         data = {
-            "size": 50, "query": {"match_all": {}},
+            "size": 50,
+            "query": {"match_all": {}},
             "pit": {"id": pit_id, "keep_alive": "1m"},
-            "sort": [{"timestamp": {"order": "desc"}}]
+            "sort": [{"timestamp": {"order": "asc"}}],
         }
         query_str = json.dumps(data)
-        url = self.ES_URL + '/_search'
+        url = self.ES_URL + "/_search"
         all_pending = []
         all_ignore = []
         while True:
-            response = requests.get(url, data=query_str, headers=headers)
+            response = requests.get(
+                url, data=query_str, headers=headers, auth=self.ES_AUTH
+            )
             json_data = json.loads(response.text)
-            all_hits = json_data['hits']['hits']
+            all_hits = json_data["hits"]["hits"]
             if all_hits:
                 for hit in all_hits:
-                    youtube_id = hit['_source']['youtube_id']
-                    status = hit['_source']['status']
-                    if status == 'pending':
-                        all_pending.append(hit['_source'])
-                    elif status == 'ignore':
-                        all_ignore.append(youtube_id)
-                    search_after = hit['sort']
+                    status = hit["_source"]["status"]
+                    if status == "pending":
+                        all_pending.append(hit["_source"])
+                    elif status == "ignore":
+                        all_ignore.append(hit["_source"])
+                    search_after = hit["sort"]
                 # update search_after with last hit data
-                data['search_after'] = search_after
+                data["search_after"] = search_after
                 query_str = json.dumps(data)
             else:
                 break
         # clean up PIT
         query_str = json.dumps({"id": pit_id})
-        requests.delete(self.ES_URL + '/_pit', data=query_str, headers=headers)
+        requests.delete(
+            self.ES_URL + "/_pit",
+            data=query_str,
+            headers=headers,
+            auth=self.ES_AUTH,
+        )
         return all_pending, all_ignore
 
     def get_all_indexed(self):
-        """ get a list of all videos indexed """
-        headers = {'Content-type': 'application/json'}
+        """get a list of all videos indexed"""
+        headers = {"Content-type": "application/json"}
         # get PIT ID
-        url = self.ES_URL + '/ta_video/_pit?keep_alive=1m'
-        response = requests.post(url)
+        url = self.ES_URL + "/ta_video/_pit?keep_alive=1m"
+        response = requests.post(url, auth=self.ES_AUTH)
         json_data = json.loads(response.text)
-        pit_id = json_data['id']
+        pit_id = json_data["id"]
         # query
         data = {
-            "size": 500, "query": {"match_all": {}},
+            "size": 500,
+            "query": {"match_all": {}},
             "pit": {"id": pit_id, "keep_alive": "1m"},
-            "sort": [{"published": {"order": "desc"}}]
+            "sort": [{"published": {"order": "desc"}}],
         }
         query_str = json.dumps(data)
-        url = self.ES_URL + '/_search'
+        url = self.ES_URL + "/_search"
         all_indexed = []
         while True:
-            response = requests.get(url, data=query_str, headers=headers)
+            response = requests.get(
+                url, data=query_str, headers=headers, auth=self.ES_AUTH
+            )
             json_data = json.loads(response.text)
-            all_hits = json_data['hits']['hits']
+            all_hits = json_data["hits"]["hits"]
             if all_hits:
                 for hit in all_hits:
                     all_indexed.append(hit)
-                    search_after = hit['sort']
+                    search_after = hit["sort"]
                 # update search_after with last hit data
-                data['search_after'] = search_after
+                data["search_after"] = search_after
                 query_str = json.dumps(data)
             else:
                 break
         # clean up PIT
         query_str = json.dumps({"id": pit_id})
-        requests.delete(self.ES_URL + '/_pit', data=query_str, headers=headers)
+        requests.delete(
+            self.ES_URL + "/_pit",
+            data=query_str,
+            headers=headers,
+            auth=self.ES_AUTH,
+        )
         return all_indexed
 
     def get_all_downloaded(self):
-        """ get a list of all videos in archive """
-        all_channel_folders = os.listdir(self.VIDEOS)
+        """get a list of all videos in archive"""
+        channel_folders = os.listdir(self.VIDEOS)
+        all_channel_folders = ignore_filelist(channel_folders)
         all_downloaded = []
         for channel_folder in all_channel_folders:
             channel_path = os.path.join(self.VIDEOS, channel_folder)
-            all_videos = os.listdir(channel_path)
+            videos = os.listdir(channel_path)
+            all_videos = ignore_filelist(videos)
             youtube_vids = [i[9:20] for i in all_videos]
             for youtube_id in youtube_vids:
                 all_downloaded.append(youtube_id)
         return all_downloaded
 
     def delete_from_pending(self, youtube_id):
-        """ delete the youtube_id from ta_download """
-        url = f'{self.ES_URL}/ta_download/_doc/{youtube_id}'
-        response = requests.delete(url)
+        """delete the youtube_id from ta_download"""
+        url = f"{self.ES_URL}/ta_download/_doc/{youtube_id}"
+        response = requests.delete(url, auth=self.ES_AUTH)
         if not response.ok:
             print(response.text)
 
     def ignore_from_pending(self, ignore_list):
-        """ build the bulk query string """
+        """build the bulk query string"""
 
         stamp = int(datetime.now().strftime("%s"))
         bulk_list = []
 
         for youtube_id in ignore_list:
             action = {"update": {"_id": youtube_id, "_index": "ta_download"}}
-            source = {"doc": {"status": 'ignore', "timestamp": stamp}}
+            source = {"doc": {"status": "ignore", "timestamp": stamp}}
             bulk_list.append(json.dumps(action))
             bulk_list.append(json.dumps(source))
 
         # add last newline
-        bulk_list.append('\n')
-        query_str = '\n'.join(bulk_list)
+        bulk_list.append("\n")
+        query_str = "\n".join(bulk_list)
 
-        headers = {'Content-type': 'application/x-ndjson'}
-        url = self.ES_URL + '/_bulk'
-        request = requests.post(url, data=query_str, headers=headers)
+        headers = {"Content-type": "application/x-ndjson"}
+        url = self.ES_URL + "/_bulk"
+        request = requests.post(
+            url, data=query_str, headers=headers, auth=self.ES_AUTH
+        )
         mess_dict = {
             "status": "ignore",
             "level": "info",
             "title": "Added to ignore list",
-            "message": ''
+            "message": "",
         }
-        set_message('progress:download', mess_dict)
+        RedisArchivist().set_message("progress:download", mess_dict)
         if not request.ok:
             print(request)
 
 
 class ChannelSubscription:
-    """ manage the list of channels subscribed """
+    """manage the list of channels subscribed"""
 
     def __init__(self):
         config = AppConfig().config
-        self.es_url = config['application']['es_url']
-        self.channel_size = config['subscriptions']['channel_size']
+        self.es_url = config["application"]["es_url"]
+        self.es_auth = config["application"]["es_auth"]
+        self.channel_size = config["subscriptions"]["channel_size"]
 
     def get_channels(self, subscribed_only=True):
-        """ get a list of all channels subscribed to """
-        headers = {'Content-type': 'application/json'}
+        """get a list of all channels subscribed to"""
+        headers = {"Content-type": "application/json"}
         # get PIT ID
-        url = self.es_url + '/ta_channel/_pit?keep_alive=1m'
-        response = requests.post(url)
+        url = self.es_url + "/ta_channel/_pit?keep_alive=1m"
+        response = requests.post(url, auth=self.es_auth)
         json_data = json.loads(response.text)
-        pit_id = json_data['id']
+        pit_id = json_data["id"]
         # query
         if subscribed_only:
             data = {
                 "query": {"term": {"channel_subscribed": {"value": True}}},
-                "size": 50, "pit": {"id": pit_id, "keep_alive": "1m"},
-                "sort": [{"channel_name.keyword": {"order": "asc"}}]
+                "size": 50,
+                "pit": {"id": pit_id, "keep_alive": "1m"},
+                "sort": [{"channel_name.keyword": {"order": "asc"}}],
             }
         else:
             data = {
                 "query": {"match_all": {}},
-                "size": 50, "pit": {"id": pit_id, "keep_alive": "1m"},
-                "sort": [{"channel_name.keyword": {"order": "asc"}}]
+                "size": 50,
+                "pit": {"id": pit_id, "keep_alive": "1m"},
+                "sort": [{"channel_name.keyword": {"order": "asc"}}],
             }
         query_str = json.dumps(data)
-        url = self.es_url + '/_search'
+        url = self.es_url + "/_search"
         all_channels = []
         while True:
-            response = requests.get(url, data=query_str, headers=headers)
+            response = requests.get(
+                url, data=query_str, headers=headers, auth=self.es_auth
+            )
             json_data = json.loads(response.text)
-            all_hits = json_data['hits']['hits']
+            all_hits = json_data["hits"]["hits"]
             if all_hits:
                 for hit in all_hits:
-                    source = hit['_source']
-                    search_after = hit['sort']
+                    source = hit["_source"]
+                    search_after = hit["sort"]
                     all_channels.append(source)
                 # update search_after with last hit data
-                data['search_after'] = search_after
+                data["search_after"] = search_after
                 query_str = json.dumps(data)
             else:
                 break
         # clean up PIT
         query_str = json.dumps({"id": pit_id})
-        requests.delete(self.es_url + '/_pit', data=query_str, headers=headers)
+        requests.delete(
+            self.es_url + "/_pit",
+            data=query_str,
+            headers=headers,
+            auth=self.es_auth,
+        )
         return all_channels
 
     def get_last_youtube_videos(self, channel_id, limit=True):
-        """ get a list of last videos from channel """
-        url = f'https://www.youtube.com/channel/{channel_id}/videos'
+        """get a list of last videos from channel"""
+        url = f"https://www.youtube.com/channel/{channel_id}/videos"
         obs = {
-            'default_search': 'ytsearch', 'quiet': True,
-            'skip_download': True, 'extract_flat': True
+            "default_search": "ytsearch",
+            "quiet": True,
+            "skip_download": True,
+            "extract_flat": True,
         }
         if limit:
-            obs['playlistend'] = self.channel_size
+            obs["playlistend"] = self.channel_size
         chan = youtube_dl.YoutubeDL(obs).extract_info(url, download=False)
-        last_videos = [(i['id'], i['title']) for i in chan['entries']]
+        last_videos = [(i["id"], i["title"]) for i in chan["entries"]]
         return last_videos
 
     def find_missing(self):
-        """ add missing videos from subscribed channels to pending """
+        """add missing videos from subscribed channels to pending"""
         all_channels = self.get_channels()
         pending_handler = PendingList()
         all_pending, all_ignore = pending_handler.get_all_pending()
-        all_pending_ids = [i['youtube_id'] for i in all_pending]
+        all_ids = [i["youtube_id"] for i in all_ignore + all_pending]
         all_downloaded = pending_handler.get_all_downloaded()
-        to_ignore = all_pending_ids + all_ignore + all_downloaded
+        to_ignore = all_ids + all_downloaded
         missing_videos = []
         counter = 1
         for channel in all_channels:
-            channel_id = channel['channel_id']
+            channel_id = channel["channel_id"]
             last_videos = self.get_last_youtube_videos(channel_id)
-            set_message('progress:download', {
-                "status": "rescan",
-                "level": "info",
-                "title": "Rescanning: Looking for new videos.",
-                "message": f'Progress: {counter}/{len(all_channels)}'
-                }
+            RedisArchivist().set_message(
+                "progress:download",
+                {
+                    "status": "rescan",
+                    "level": "info",
+                    "title": "Scanning channels: Looking for new videos.",
+                    "message": f"Progress: {counter}/{len(all_channels)}",
+                },
             )
             for video in last_videos:
                 youtube_id = video[0]
@@ -354,152 +416,235 @@ class ChannelSubscription:
         return missing_videos
 
     def change_subscribe(self, channel_id, channel_subscribed):
-        """ subscribe or unsubscribe from channel and update """
+        """subscribe or unsubscribe from channel and update"""
         if not isinstance(channel_subscribed, bool):
-            print('invalid status, should be bool')
+            print("invalid status, should be bool")
             return
-        headers = {'Content-type': 'application/json'}
+        headers = {"Content-type": "application/json"}
         channel_handler = YoutubeChannel(channel_id)
         channel_dict = channel_handler.channel_dict
-        channel_dict['channel_subscribed'] = channel_subscribed
+        channel_dict["channel_subscribed"] = channel_subscribed
         if channel_subscribed:
             # handle subscribe
-            url = self.es_url + '/ta_channel/_doc/' + channel_id
+            url = self.es_url + "/ta_channel/_doc/" + channel_id
             payload = json.dumps(channel_dict)
             print(channel_dict)
         else:
-            url = self.es_url + '/ta_channel/_update/' + channel_id
-            payload = json.dumps({'doc': channel_dict})
+            url = self.es_url + "/ta_channel/_update/" + channel_id
+            payload = json.dumps({"doc": channel_dict})
         # update channel
-        request = requests.post(url, data=payload, headers=headers)
+        request = requests.post(
+            url, data=payload, headers=headers, auth=self.es_auth
+        )
         if not request.ok:
             print(request.text)
         # sync to videos
         channel_handler.sync_to_videos()
+        if channel_handler.source == "scraped":
+            channel_handler.get_channel_art()
 
 
 def playlist_extractor(playlist_id):
-    """ return youtube_ids from a playlist_id """
-    url = 'https://www.youtube.com/playlist?list=' + playlist_id
+    """return youtube_ids from a playlist_id"""
+    url = "https://www.youtube.com/playlist?list=" + playlist_id
     obs = {
-        'default_search': 'ytsearch', 'quiet': True, 'ignoreerrors': True,
-        'skip_download': True, 'extract_flat': True
+        "default_search": "ytsearch",
+        "quiet": True,
+        "ignoreerrors": True,
+        "skip_download": True,
+        "extract_flat": True,
     }
     playlist = youtube_dl.YoutubeDL(obs).extract_info(url, download=False)
-    playlist_vids = [(i['id'], i['title']) for i in playlist['entries']]
+    playlist_vids = [(i["id"], i["title"]) for i in playlist["entries"]]
     return playlist_vids
 
 
 class VideoDownloader:
-    """ handle the video download functionality """
+    """
+    handle the video download functionality
+    if not initiated with list, take from queue
+    """
 
-    def __init__(self, youtube_id_list):
+    def __init__(self, youtube_id_list=False):
         self.youtube_id_list = youtube_id_list
         self.config = AppConfig().config
 
-    def download_list(self):
-        """ download the list of youtube_ids """
-        limit_count = self.config['downloads']['limit_count']
-        if limit_count:
-            self.youtube_id_list = self.youtube_id_list[:limit_count]
+    def run_queue(self):
+        """setup download queue in redis loop until no more items"""
+        queue = RedisQueue("dl_queue")
+
+        limit_queue = self.config["downloads"]["limit_count"]
+        if limit_queue:
+            queue.trim(limit_queue - 1)
+
+        while True:
+            youtube_id = queue.get_next()
+            if not youtube_id:
+                break
 
-        for youtube_id in self.youtube_id_list:
             try:
                 self.dl_single_vid(youtube_id)
             except youtube_dl.utils.DownloadError:
-                print('failed to download ' + youtube_id)
+                print("failed to download " + youtube_id)
                 continue
             vid_dict = index_new_video(youtube_id)
             self.move_to_archive(vid_dict)
             self.delete_from_pending(youtube_id)
-            if self.config['downloads']['sleep_interval']:
-                sleep(self.config['downloads']['sleep_interval'])
+
+    @staticmethod
+    def add_pending():
+        """add pending videos to download queue"""
+        all_pending, _ = PendingList().get_all_pending()
+        to_add = [i["youtube_id"] for i in all_pending]
+        if not to_add:
+            # there is nothing pending
+            print("download queue is empty")
+            mess_dict = {
+                "status": "downloading",
+                "level": "error",
+                "title": "Download queue is empty",
+                "message": "",
+            }
+            RedisArchivist().set_message("progress:download", mess_dict)
+            return
+
+        queue = RedisQueue("dl_queue")
+        queue.add_list(to_add)
 
     @staticmethod
     def progress_hook(response):
-        """ process the progress_hooks from youtube_dl """
+        """process the progress_hooks from youtube_dl"""
         # title
-        filename = response['filename'][12:].replace('_', ' ')
+        filename = response["filename"][12:].replace("_", " ")
         title = "Downloading: " + os.path.split(filename)[-1]
         # message
         try:
-            percent = response['_percent_str']
-            size = response['_total_bytes_str']
-            speed = response['_speed_str']
-            eta = response['_eta_str']
-            message = f'{percent} of {size} at {speed} - time left: {eta}'
+            percent = response["_percent_str"]
+            size = response["_total_bytes_str"]
+            speed = response["_speed_str"]
+            eta = response["_eta_str"]
+            message = f"{percent} of {size} at {speed} - time left: {eta}"
         except KeyError:
-            message = ''
+            message = ""
         mess_dict = {
             "status": "downloading",
             "level": "info",
             "title": title,
-            "message": message
+            "message": message,
         }
-        set_message('progress:download', mess_dict)
+        RedisArchivist().set_message("progress:download", mess_dict)
 
-    def dl_single_vid(self, youtube_id):
-        """ download single video """
+    def build_obs(self):
+        """build obs dictionary for yt-dlp"""
         obs = {
-            'default_search': 'ytsearch',
-            'merge_output_format': 'mp4', 'restrictfilenames': True,
-            'outtmpl': (self.config['application']['cache_dir'] +
-                        '/download/' +
-                        self.config['application']['file_template']),
-            'progress_hooks': [self.progress_hook],
-            'quiet': True, 'continuedl': True, 'retries': 3
+            "default_search": "ytsearch",
+            "merge_output_format": "mp4",
+            "restrictfilenames": True,
+            "outtmpl": (
+                self.config["application"]["cache_dir"]
+                + "/download/"
+                + self.config["application"]["file_template"]
+            ),
+            "progress_hooks": [self.progress_hook],
+            "noprogress": True,
+            "quiet": True,
+            "continuedl": True,
+            "retries": 3,
+            "writethumbnail": False,
         }
-        if self.config['downloads']['format']:
-            obs['format'] = self.config['downloads']['format']
-        if self.config['downloads']['limit_speed']:
-            obs['ratelimit'] = self.config['downloads']['limit_speed'] * 1024
+        if self.config["downloads"]["format"]:
+            obs["format"] = self.config["downloads"]["format"]
+        if self.config["downloads"]["limit_speed"]:
+            obs["ratelimit"] = self.config["downloads"]["limit_speed"] * 1024
+
+        throttle = self.config["downloads"]["throttledratelimit"]
+        if throttle:
+            obs["throttledratelimit"] = throttle * 1024
+
         external = False
         if external:
-            obs['external_downloader'] = 'aria2c'
+            obs["external_downloader"] = "aria2c"
+
+        postprocessors = []
+
+        if self.config["downloads"]["add_metadata"]:
+            postprocessors.append(
+                {
+                    "key": "FFmpegMetadata",
+                    "add_chapters": True,
+                    "add_metadata": True,
+                }
+            )
+
+        if self.config["downloads"]["add_thumbnail"]:
+            postprocessors.append(
+                {
+                    "key": "EmbedThumbnail",
+                    "already_have_thumbnail": True,
+                }
+            )
+            obs["writethumbnail"] = True
+
+        obs["postprocessors"] = postprocessors
+
+        return obs
+
+    def dl_single_vid(self, youtube_id):
+        """download single video"""
+        dl_cache = self.config["application"]["cache_dir"] + "/download/"
+        obs = self.build_obs()
+
         # check if already in cache to continue from there
-        cache_dir = self.config['application']['cache_dir']
-        all_cached = os.listdir(cache_dir + '/download/')
+        all_cached = ignore_filelist(os.listdir(dl_cache))
         for file_name in all_cached:
             if youtube_id in file_name:
-                obs['outtmpl'] = cache_dir + '/download/' + file_name
+                obs["outtmpl"] = os.path.join(dl_cache, file_name)
         with youtube_dl.YoutubeDL(obs) as ydl:
             try:
                 ydl.download([youtube_id])
             except youtube_dl.utils.DownloadError:
-                print('retry failed download: ' + youtube_id)
+                print("retry failed download: " + youtube_id)
                 sleep(10)
                 ydl.download([youtube_id])
 
+        if obs["writethumbnail"]:
+            # webp files don't get cleaned up automatically
+            all_cached = ignore_filelist(os.listdir(dl_cache))
+            to_clean = [i for i in all_cached if not i.endswith(".mp4")]
+            for file_name in to_clean:
+                file_path = os.path.join(dl_cache, file_name)
+                os.remove(file_path)
+
     def move_to_archive(self, vid_dict):
-        """ move downloaded video from cache to archive """
-        videos = self.config['application']['videos']
-        channel_name = vid_dict['channel']['channel_name']
-        channel_name_clean = clean_string(channel_name)
-        media_url = vid_dict['media_url']
-        youtube_id = vid_dict['youtube_id']
-        # make archive folder
-        videos = self.config['application']['videos']
-        new_folder = os.path.join(videos, channel_name_clean)
-        os.makedirs(new_folder, exist_ok=True)
+        """move downloaded video from cache to archive"""
+        videos = self.config["application"]["videos"]
+        host_uid = self.config["application"]["HOST_UID"]
+        host_gid = self.config["application"]["HOST_GID"]
+        channel_name = clean_string(vid_dict["channel"]["channel_name"])
+        # make archive folder with correct permissions
+        new_folder = os.path.join(videos, channel_name)
+        if not os.path.exists(new_folder):
+            os.makedirs(new_folder)
+            if host_uid and host_gid:
+                os.chown(new_folder, host_uid, host_gid)
         # find real filename
-        cache_dir = self.config['application']['cache_dir']
-        for file_str in os.listdir(cache_dir + '/download'):
-            if youtube_id in file_str:
+        cache_dir = self.config["application"]["cache_dir"]
+        all_cached = ignore_filelist(os.listdir(cache_dir + "/download/"))
+        for file_str in all_cached:
+            if vid_dict["youtube_id"] in file_str:
                 old_file = file_str
-        old_file_path = os.path.join(cache_dir, 'download', old_file)
-        new_file_path = os.path.join(videos, media_url)
-        # move and fix permission
+        old_file_path = os.path.join(cache_dir, "download", old_file)
+        new_file_path = os.path.join(videos, vid_dict["media_url"])
+        # move media file and fix permission
         shutil.move(old_file_path, new_file_path)
-        os.chown(
-            new_file_path,
-            self.config['application']['HOST_UID'],
-            self.config['application']['HOST_GID']
-        )
+        if host_uid and host_gid:
+            os.chown(new_file_path, host_uid, host_gid)
 
     def delete_from_pending(self, youtube_id):
-        """ delete downloaded video from pending index if its there """
-        es_url = self.config['application']['es_url']
-        url = f'{es_url}/ta_download/_doc/{youtube_id}'
-        response = requests.delete(url)
+        """delete downloaded video from pending index if its there"""
+        es_url = self.config["application"]["es_url"]
+        es_auth = self.config["application"]["es_auth"]
+        url = f"{es_url}/ta_download/_doc/{youtube_id}"
+        response = requests.delete(url, auth=es_auth)
         if not response.ok and not response.status_code == 404:
             print(response.text)

tubearchivist/home/src/helper.py

@@ -9,121 +9,281 @@ import re
 import string
 import subprocess
 import unicodedata
+from urllib.parse import parse_qs, urlparse
 
-import requests
 import redis
-
-REDIS_HOST = os.environ.get('REDIS_HOST')
+import requests
+import yt_dlp as youtube_dl
 
 
-def get_total_hits(index, es_url, match_field):
-    """ get total hits from index """
-    headers = {'Content-type': 'application/json'}
+def get_total_hits(index, es_url, es_auth, match_field):
+    """get total hits from index"""
+    headers = {"Content-type": "application/json"}
     data = {"query": {"match": {match_field: True}}}
     payload = json.dumps(data)
-    url = f'{es_url}/{index}/_search?filter_path=hits.total'
-    request = requests.post(url, data=payload, headers=headers)
+    url = f"{es_url}/{index}/_search?filter_path=hits.total"
+    request = requests.post(url, data=payload, headers=headers, auth=es_auth)
     if not request.ok:
         print(request.text)
     total_json = json.loads(request.text)
-    total_hits = total_json['hits']['total']['value']
+    total_hits = total_json["hits"]["total"]["value"]
     return total_hits
 
 
 def clean_string(file_name):
-    """ clean string to only asci characters """
+    """clean string to only asci characters"""
     whitelist = "-_.() " + string.ascii_letters + string.digits
-    normalized = unicodedata.normalize('NFKD', file_name)
-    ascii_only = normalized.encode('ASCII', 'ignore').decode().strip()
-    white_listed = ''.join(c for c in ascii_only if c in whitelist)
-    cleaned = re.sub(r'[ ]{2,}', ' ', white_listed)
+    normalized = unicodedata.normalize("NFKD", file_name)
+    ascii_only = normalized.encode("ASCII", "ignore").decode().strip()
+    white_listed = "".join(c for c in ascii_only if c in whitelist)
+    cleaned = re.sub(r"[ ]{2,}", " ", white_listed)
     return cleaned
 
 
-def process_url_list(url_str):
-    """ parse url_list to find valid youtube video or channel ids """
-    to_replace = ['watch?v=', 'playlist?list=']
-    url_list = re.split('\n+', url_str[0])
-    youtube_ids = []
-    for url in url_list:
-        url_clean = url.strip().strip('/').split('/')[-1]
-        for i in to_replace:
-            url_clean = url_clean.replace(i, '')
-        url_no_param = url_clean.split('&')[0]
-        str_len = len(url_no_param)
+def ignore_filelist(filelist):
+    """ignore temp files for os.listdir sanitizer"""
+    to_ignore = ["Icon\r\r", "Temporary Items", "Network Trash Folder"]
+    cleaned = []
+    for file_name in filelist:
+        if file_name.startswith(".") or file_name in to_ignore:
+            continue
+
+        cleaned.append(file_name)
+
+    return cleaned
+
+
+class UrlListParser:
+    """take a multi line string and detect valid youtube ids"""
+
+    def __init__(self, url_str):
+        self.url_list = [i.strip() for i in url_str.split()]
+
+    def process_list(self):
+        """loop through the list"""
+        youtube_ids = []
+        for url in self.url_list:
+            parsed = urlparse(url)
+            print(f"processing: {url}")
+            print(parsed)
+            if not parsed.netloc:
+                # is not a url
+                id_type = self.find_valid_id(url)
+                youtube_id = url
+            elif "youtube.com" not in url:
+                raise ValueError(f"{url} is not a youtube link")
+            elif parsed.path:
+                # is a url
+                youtube_id, id_type = self.detect_from_url(parsed)
+            else:
+                # not detected
+                raise ValueError(f"failed to detect {url}")
+
+            youtube_ids.append({"url": youtube_id, "type": id_type})
+
+        return youtube_ids
+
+    def detect_from_url(self, parsed):
+        """detect from parsed url"""
+        if parsed.netloc == "youtu.be":
+            # shortened
+            youtube_id = parsed.path.strip("/")
+            _ = self.find_valid_id(youtube_id)
+            return youtube_id, "video"
+
+        if parsed.query:
+            # detect from query string
+            query_parsed = parse_qs(parsed.query)
+            if "v" in query_parsed.keys():
+                youtube_id = query_parsed["v"][0]
+                _ = self.find_valid_id(youtube_id)
+                return youtube_id, "video"
+
+            if "list" in query_parsed.keys():
+                youtube_id = query_parsed["list"][0]
+                return youtube_id, "playlist"
+
+        if parsed.path.startswith("/channel/"):
+            # channel id in url
+            youtube_id = parsed.path.split("/")[2]
+            _ = self.find_valid_id(youtube_id)
+            return youtube_id, "channel"
+
+        # dedect channel with yt_dlp
+        youtube_id = self.extract_channel_name(parsed.geturl())
+        return youtube_id, "channel"
+
+    @staticmethod
+    def find_valid_id(id_str):
+        """dedect valid id from length of string"""
+        str_len = len(id_str)
         if str_len == 11:
-            link_type = 'video'
+            id_type = "video"
         elif str_len == 24:
-            link_type = 'channel'
+            id_type = "channel"
         elif str_len == 34:
-            link_type = 'playlist'
+            id_type = "playlist"
         else:
             # unable to parse
-            raise ValueError('not a valid url: ' + url)
+            raise ValueError("not a valid id_str: " + id_str)
 
-        youtube_ids.append({"url": url_no_param, "type": link_type})
+        return id_type
 
-    return youtube_ids
-
-
-def set_message(key, message, expire=True):
-    """ write new message to redis """
-    redis_connection = redis.Redis(host=REDIS_HOST)
-    redis_connection.execute_command(
-        'JSON.SET', key, '.', json.dumps(message)
-    )
-    if expire:
-        redis_connection.execute_command('EXPIRE', key, 20)
-
-
-def get_message(key):
-    """ get any message from JSON key """
-    redis_connection = redis.Redis(host=REDIS_HOST)
-    reply = redis_connection.execute_command('JSON.GET', key)
-    if reply:
-        json_str = json.loads(reply)
-    else:
-        json_str = {"status": False}
-    return json_str
-
-
-def get_dl_message(cache_dir):
-    """ get latest message if available """
-    redis_connection = redis.Redis(host=REDIS_HOST)
-    reply = redis_connection.execute_command('JSON.GET', 'progress:download')
-    if reply:
-        json_str = json.loads(reply)
-    elif json_str := monitor_cache_dir(cache_dir):
-        json_str = monitor_cache_dir(cache_dir)
-    else:
-        json_str = {"status": False}
-    return json_str
-
-
-def get_lock(lock_key):
-    """ handle lock for task management """
-    redis_lock = redis.Redis(host=REDIS_HOST).lock(lock_key)
-    return redis_lock
-
-
-def monitor_cache_dir(cache_dir):
-    """
-    look at download cache dir directly as alterative progress info
-    """
-    dl_cache = os.path.join(cache_dir, 'download')
-    cache_file = os.listdir(dl_cache)
-    if cache_file:
-        filename = cache_file[0][12:].replace('_', ' ').split('.')[0]
-        mess_dict = {
-            "status": "downloading",
-            "level": "info",
-            "title": "Downloading: " + filename,
-            "message": ""
+    @staticmethod
+    def extract_channel_name(url):
+        """find channel id from channel name with yt-dlp help"""
+        obs = {
+            "default_search": "ytsearch",
+            "quiet": True,
+            "skip_download": True,
+            "extract_flat": True,
+            "playlistend": 0,
         }
-    else:
-        return False
+        url_info = youtube_dl.YoutubeDL(obs).extract_info(url, download=False)
+        try:
+            channel_id = url_info["channel_id"]
+        except KeyError as error:
+            print(f"failed to extract channel id from {url}")
+            raise ValueError from error
 
-    return mess_dict
+        return channel_id
+
+
+class RedisArchivist:
+    """collection of methods to interact with redis"""
+
+    REDIS_HOST = os.environ.get("REDIS_HOST")
+    REDIS_PORT = os.environ.get("REDIS_PORT")
+    NAME_SPACE = "ta:"
+
+    if not REDIS_PORT:
+        REDIS_PORT = 6379
+
+    def __init__(self):
+        self.redis_connection = redis.Redis(
+            host=self.REDIS_HOST, port=self.REDIS_PORT
+        )
+
+    def set_message(self, key, message, expire=True):
+        """write new message to redis"""
+        self.redis_connection.execute_command(
+            "JSON.SET", self.NAME_SPACE + key, ".", json.dumps(message)
+        )
+
+        if expire:
+            self.redis_connection.execute_command(
+                "EXPIRE", self.NAME_SPACE + key, 20
+            )
+
+    def get_message(self, key):
+        """get message dict from redis"""
+        reply = self.redis_connection.execute_command(
+            "JSON.GET", self.NAME_SPACE + key
+        )
+        if reply:
+            json_str = json.loads(reply)
+        else:
+            json_str = {"status": False}
+
+        return json_str
+
+    def del_message(self, key):
+        """delete key from redis"""
+        response = self.redis_connection.execute_command(
+            "DEL", self.NAME_SPACE + key
+        )
+        return response
+
+    def get_lock(self, lock_key):
+        """handle lock for task management"""
+        redis_lock = self.redis_connection.lock(self.NAME_SPACE + lock_key)
+        return redis_lock
+
+    def get_dl_message(self, cache_dir):
+        """get latest download progress message if available"""
+        reply = self.redis_connection.execute_command(
+            "JSON.GET", self.NAME_SPACE + "progress:download"
+        )
+        if reply:
+            json_str = json.loads(reply)
+        elif json_str := self.monitor_cache_dir(cache_dir):
+            json_str = self.monitor_cache_dir(cache_dir)
+        else:
+            json_str = {"status": False}
+
+        return json_str
+
+    @staticmethod
+    def monitor_cache_dir(cache_dir):
+        """
+        look at download cache dir directly as alternative progress info
+        """
+        dl_cache = os.path.join(cache_dir, "download")
+        all_cache_file = os.listdir(dl_cache)
+        cache_file = ignore_filelist(all_cache_file)
+        if cache_file:
+            filename = cache_file[0][12:].replace("_", " ").split(".")[0]
+            mess_dict = {
+                "status": "downloading",
+                "level": "info",
+                "title": "Downloading: " + filename,
+                "message": "",
+            }
+        else:
+            return False
+
+        return mess_dict
+
+
+class RedisQueue:
+    """dynamically interact with the download queue in redis"""
+
+    REDIS_HOST = os.environ.get("REDIS_HOST")
+    REDIS_PORT = os.environ.get("REDIS_PORT")
+    NAME_SPACE = "ta:"
+
+    if not REDIS_PORT:
+        REDIS_PORT = 6379
+
+    def __init__(self, key):
+        self.key = self.NAME_SPACE + key
+        self.conn = redis.Redis(host=self.REDIS_HOST, port=self.REDIS_PORT)
+
+    def get_all(self):
+        """return all elements in list"""
+        result = self.conn.execute_command("LRANGE", self.key, 0, -1)
+        all_elements = [i.decode() for i in result]
+        return all_elements
+
+    def add_list(self, to_add):
+        """add list to queue"""
+        self.conn.execute_command("RPUSH", self.key, *to_add)
+
+    def add_priority(self, to_add):
+        """add single video to front of queue"""
+        self.clear_item(to_add)
+        self.conn.execute_command("LPUSH", self.key, to_add)
+
+    def get_next(self):
+        """return next element in the queue, False if none"""
+        result = self.conn.execute_command("LPOP", self.key)
+        if not result:
+            return False
+
+        next_element = result.decode()
+        return next_element
+
+    def clear(self):
+        """delete list from redis"""
+        self.conn.execute_command("DEL", self.key)
+
+    def clear_item(self, to_clear):
+        """remove single item from list if it's there"""
+        self.conn.execute_command("LREM", self.key, 0, to_clear)
+
+    def trim(self, size):
+        """trim the queue based on settings amount"""
+        self.conn.execute_command("LTRIM", self.key, 0, size)
 
 
 class DurationConverter:
@@ -133,27 +293,41 @@ class DurationConverter:
 
     @staticmethod
     def get_sec(file_path):
-        """ read duration from file """
-        duration = subprocess.run([
-            "ffprobe", "-v", "error", "-show_entries", "format=duration",
-            "-of", "default=noprint_wrappers=1:nokey=1", file_path
-        ], capture_output=True, check=True)
+        """read duration from file"""
+        duration = subprocess.run(
+            [
+                "ffprobe",
+                "-v",
+                "error",
+                "-show_entries",
+                "format=duration",
+                "-of",
+                "default=noprint_wrappers=1:nokey=1",
+                file_path,
+            ],
+            capture_output=True,
+            check=True,
+        )
         duration_sec = int(float(duration.stdout.decode().strip()))
         return duration_sec
 
     @staticmethod
     def get_str(duration_sec):
-        """ takes duration in sec and returns clean string """
+        """takes duration in sec and returns clean string"""
+        if not duration_sec:
+            # failed to extract
+            return "NA"
+
         hours = duration_sec // 3600
         minutes = (duration_sec - (hours * 3600)) // 60
         secs = duration_sec - (hours * 3600) - (minutes * 60)
 
         duration_str = str()
         if hours:
-            duration_str = str(hours).zfill(2) + ':'
+            duration_str = str(hours).zfill(2) + ":"
         if minutes:
-            duration_str = duration_str + str(minutes).zfill(2) + ':'
+            duration_str = duration_str + str(minutes).zfill(2) + ":"
         else:
-            duration_str = duration_str + '00:'
+            duration_str = duration_str + "00:"
         duration_str = duration_str + str(secs).zfill(2)
         return duration_str

tubearchivist/home/src/index.py

@@ -6,27 +6,27 @@ Functionality:
 """
 
 import json
+import os
 import re
-
 from datetime import datetime
 from time import sleep
-import os
 
 import requests
 import yt_dlp as youtube_dl
-
 from bs4 import BeautifulSoup
-
 from home.src.config import AppConfig
-from home.src.helper import clean_string, DurationConverter
+from home.src.helper import DurationConverter, UrlListParser, clean_string
+from home.src.thumbnails import ThumbManager
 
 
 class YoutubeChannel:
-    """ represents a single youtube channel """
+    """represents a single youtube channel"""
 
     CONFIG = AppConfig().config
-    ES_URL = CONFIG['application']['es_url']
-    CACHE_DIR = CONFIG['application']['cache_dir']
+    ES_URL = CONFIG["application"]["es_url"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
+    CACHE_DIR = CONFIG["application"]["cache_dir"]
+    VIDEOS = CONFIG["application"]["videos"]
 
     def __init__(self, channel_id):
         self.channel_id = channel_id
@@ -35,202 +35,235 @@ class YoutubeChannel:
         self.channel_dict = self.build_channel_dict()
 
     def build_channel_dict(self, scrape=False):
-        """ combine the dicts build from extracted json payload """
+        """combine the dicts build from extracted json payload"""
         if scrape:
             channel_dict = False
         else:
             channel_dict = self.get_es_channel()
         if not channel_dict:
-            print('scrape data from youtube')
+            print("scrape data from youtube")
             self.scrape_channel()
             channel_dict = self.parse_channel_main()
             channel_dict.update(self.parse_channel_meta())
-            self.source = 'scraped'
+            self.source = "scraped"
         return channel_dict
 
     def get_es_channel(self):
-        """ get from elastic search first if possible """
+        """get from elastic search first if possible"""
         channel_id = self.channel_id
-        url = f'{self.ES_URL}/ta_channel/_doc/{channel_id}'
-        response = requests.get(url)
+        url = f"{self.ES_URL}/ta_channel/_doc/{channel_id}"
+        response = requests.get(url, auth=self.ES_AUTH)
         if response.ok:
-            channel_source = response.json()['_source']
-            self.source = 'elastic'
+            channel_source = response.json()["_source"]
+            self.source = "elastic"
             return channel_source
         return False
 
     def scrape_channel(self):
-        """ scrape channel page for additional infos """
+        """scrape channel page for additional infos"""
         channel_id = self.channel_id
-        url = f'https://www.youtube.com/channel/{channel_id}/about?hl=en'
-        cookies = {
-            'CONSENT': 'YES+xxxxxxxxxxxxxxxxxxxxxxxxxxx'
-        }
-        response = requests.get(url, cookies=cookies)
+        url = f"https://www.youtube.com/channel/{channel_id}/about?hl=en"
+        cookies = {"CONSENT": "YES+xxxxxxxxxxxxxxxxxxxxxxxxxxx"}
+        response = requests.get(url, cookies=cookies, auth=self.ES_AUTH)
         if response.ok:
             channel_page = response.text
         else:
-            print(f'failed to extract channel info for: {channel_id}')
+            print(f"failed to extract channel info for: {channel_id}")
             raise ConnectionError
-        soup = BeautifulSoup(channel_page, 'html.parser')
+        soup = BeautifulSoup(channel_page, "html.parser")
         # load script into json
-        all_scripts = soup.find('body').find_all('script')
+        all_scripts = soup.find("body").find_all("script")
         for script in all_scripts:
-            if 'var ytInitialData = ' in str(script):
+            if "var ytInitialData = " in str(script):
                 script_content = str(script)
                 break
         # extract payload
-        script_content = script_content.split('var ytInitialData = ')[1]
-        json_raw = script_content.rstrip(';</script>')
+        script_content = script_content.split("var ytInitialData = ")[1]
+        json_raw = script_content.rstrip(";</script>")
         json_data = json.loads(json_raw)
         # add to self
         self.json_data = json_data
 
     def parse_channel_main(self):
-        """ extract maintab values from scraped channel json data """
-        main_tab = self.json_data['header']['c4TabbedHeaderRenderer']
-        channel_name = main_tab['title']
+        """extract maintab values from scraped channel json data"""
+        main_tab = self.json_data["header"]["c4TabbedHeaderRenderer"]
+        channel_name = main_tab["title"]
         last_refresh = int(datetime.now().strftime("%s"))
         # channel_subs
         try:
-            sub_text_simple = main_tab['subscriberCountText']['simpleText']
-            sub_text = sub_text_simple.split(' ')[0]
-            if sub_text[-1] == 'K':
-                channel_subs = int(float(sub_text.replace('K', ''))*1000)
-            elif sub_text[-1] == 'M':
-                channel_subs = int(float(sub_text.replace('M', ''))*1000000)
+            sub_text_simple = main_tab["subscriberCountText"]["simpleText"]
+            sub_text = sub_text_simple.split(" ")[0]
+            if sub_text[-1] == "K":
+                channel_subs = int(float(sub_text.replace("K", "")) * 1000)
+            elif sub_text[-1] == "M":
+                channel_subs = int(float(sub_text.replace("M", "")) * 1000000)
             elif int(sub_text) >= 0:
                 channel_subs = int(sub_text)
             else:
-                message = f'{sub_text} not dealt with'
+                message = f"{sub_text} not dealt with"
                 print(message)
         except KeyError:
             channel_subs = 0
         # banner
         try:
-            all_banners = main_tab['banner']['thumbnails']
-            banner = sorted(all_banners, key=lambda k: k['width'])[-1]['url']
+            all_banners = main_tab["banner"]["thumbnails"]
+            banner = sorted(all_banners, key=lambda k: k["width"])[-1]["url"]
         except KeyError:
             banner = False
         # build and return dict
         main_channel_dict = {
-            'channel_active': True,
-            'channel_last_refresh': last_refresh,
-            'channel_subs': channel_subs,
-            'channel_banner_url': banner,
-            'channel_name': channel_name,
-            'channel_id': self.channel_id
+            "channel_active": True,
+            "channel_last_refresh": last_refresh,
+            "channel_subs": channel_subs,
+            "channel_banner_url": banner,
+            "channel_name": channel_name,
+            "channel_id": self.channel_id,
         }
         return main_channel_dict
 
     def parse_channel_meta(self):
-        """ extract meta tab values from channel payload """
+        """extract meta tab values from channel payload"""
         # meta tab
         json_data = self.json_data
-        meta_tab = json_data['metadata']['channelMetadataRenderer']
-        description = meta_tab['description']
-        all_thumbs = meta_tab['avatar']['thumbnails']
-        thumb_url = sorted(all_thumbs, key=lambda k: k['width'])[-1]['url']
+        meta_tab = json_data["metadata"]["channelMetadataRenderer"]
+        description = meta_tab["description"]
+        all_thumbs = meta_tab["avatar"]["thumbnails"]
+        thumb_url = sorted(all_thumbs, key=lambda k: k["width"])[-1]["url"]
         # stats tab
-        renderer = 'twoColumnBrowseResultsRenderer'
-        all_tabs = json_data['contents'][renderer]['tabs']
+        renderer = "twoColumnBrowseResultsRenderer"
+        all_tabs = json_data["contents"][renderer]["tabs"]
         for tab in all_tabs:
-            if 'tabRenderer' in tab.keys():
-                if tab['tabRenderer']['title'] == 'About':
-                    about_tab = (tab['tabRenderer']['content']
-                                 ['sectionListRenderer']['contents'][0]
-                                 ['itemSectionRenderer']['contents'][0]
-                                 ['channelAboutFullMetadataRenderer'])
+            if "tabRenderer" in tab.keys():
+                if tab["tabRenderer"]["title"] == "About":
+                    about_tab = tab["tabRenderer"]["content"][
+                        "sectionListRenderer"
+                    ]["contents"][0]["itemSectionRenderer"]["contents"][0][
+                        "channelAboutFullMetadataRenderer"
+                    ]
                     break
         try:
-            channel_views_text = about_tab['viewCountText']['simpleText']
+            channel_views_text = about_tab["viewCountText"]["simpleText"]
             channel_views = int(re.sub(r"\D", "", channel_views_text))
         except KeyError:
             channel_views = 0
 
         meta_channel_dict = {
-            'channel_description': description,
-            'channel_thumb_url': thumb_url,
-            'channel_views': channel_views
+            "channel_description": description,
+            "channel_thumb_url": thumb_url,
+            "channel_views": channel_views,
         }
 
         return meta_channel_dict
 
+    def get_channel_art(self):
+        """download channel art for new channels"""
+        channel_id = self.channel_id
+        channel_thumb = self.channel_dict["channel_thumb_url"]
+        channel_banner = self.channel_dict["channel_banner_url"]
+        ThumbManager().download_chan(
+            [(channel_id, channel_thumb, channel_banner)]
+        )
+
     def upload_to_es(self):
-        """ upload channel data to elastic search """
-        url = f'{self.ES_URL}/ta_channel/_doc/{self.channel_id}'
-        response = requests.put(url, json=self.channel_dict)
-        print(f'added {self.channel_id} to es')
+        """upload channel data to elastic search"""
+        url = f"{self.ES_URL}/ta_channel/_doc/{self.channel_id}"
+        response = requests.put(url, json=self.channel_dict, auth=self.ES_AUTH)
+        print(f"added {self.channel_id} to es")
         if not response.ok:
             print(response.text)
 
-    def clear_cache(self):
-        """ delete banner and thumb from cache if available """
-        channel_cache = os.path.join(self.CACHE_DIR, 'channels')
-        thumb = os.path.join(channel_cache, self.channel_id + '_thumb.jpg')
-        banner = os.path.join(channel_cache, self.channel_id + '_banner.jpg')
-        if os.path.exists(thumb):
-            os.remove(thumb)
-        if os.path.exists(banner):
-            os.remove(banner)
-
     def sync_to_videos(self):
-        """ sync new channel_dict to all videos of channel """
-        headers = {'Content-type': 'application/json'}
+        """sync new channel_dict to all videos of channel"""
+        headers = {"Content-type": "application/json"}
         channel_id = self.channel_id
         # add ingest pipeline
         processors = []
         for field, value in self.channel_dict.items():
             line = {"set": {"field": "channel." + field, "value": value}}
             processors.append(line)
-        data = {
-            "description": channel_id,
-            "processors": processors
-        }
+        data = {"description": channel_id, "processors": processors}
         payload = json.dumps(data)
-        url = self.ES_URL + '/_ingest/pipeline/' + channel_id
-        request = requests.put(url, data=payload, headers=headers)
+        url = self.ES_URL + "/_ingest/pipeline/" + channel_id
+        request = requests.put(
+            url, data=payload, headers=headers, auth=self.ES_AUTH
+        )
         if not request.ok:
             print(request.text)
         # apply pipeline
-        data = {
-            "query": {"match": {"channel.channel_id": channel_id}}
-        }
+        data = {"query": {"match": {"channel.channel_id": channel_id}}}
         payload = json.dumps(data)
-        url = self.ES_URL + '/ta_video/_update_by_query?pipeline=' + channel_id
-        request = requests.post(url, data=payload, headers=headers)
+        url = self.ES_URL + "/ta_video/_update_by_query?pipeline=" + channel_id
+        request = requests.post(
+            url, data=payload, headers=headers, auth=self.ES_AUTH
+        )
         if not request.ok:
             print(request.text)
 
-    def get_total_hits(self):
-        """ get total channels indexed """
-        headers = {'Content-type': 'application/json'}
-        data = {"query": {"match_all": {}}}
+    def get_folder_path(self):
+        """get folder where media files get stored"""
+        channel_name = self.channel_dict["channel_name"]
+        folder_name = clean_string(channel_name)
+        folder_path = os.path.join(self.VIDEOS, folder_name)
+        return folder_path
+
+    def delete_es_videos(self):
+        """delete all channel documents from elasticsearch"""
+        headers = {"Content-type": "application/json"}
+        data = {
+            "query": {
+                "term": {"channel.channel_id": {"value": self.channel_id}}
+            }
+        }
         payload = json.dumps(data)
-        url = f'{self.ES_URL}/ta_channel/_search?filter_path=hits.total'
-        request = requests.post(url, data=payload, headers=headers)
-        if not request.ok:
-            print(request.text)
-        total_hits = json.loads(request.text)['hits']['total']['value']
-        return total_hits
+        url = self.ES_URL + "/ta_video/_delete_by_query"
+        response = requests.post(
+            url, data=payload, headers=headers, auth=self.ES_AUTH
+        )
+        if not response.ok:
+            print(response.text)
+
+    def delete_channel(self):
+        """delete channel and all videos"""
+        print(f"deleting {self.channel_id} and all matching media files")
+        folder_path = self.get_folder_path()
+        print("delete all media files")
+        try:
+            all_videos = os.listdir(folder_path)
+            for video in all_videos:
+                video_path = os.path.join(folder_path, video)
+                os.remove(video_path)
+            os.rmdir(folder_path)
+        except FileNotFoundError:
+            print(f"no videos found for {folder_path}")
+
+        ThumbManager().delete_chan_thumb(self.channel_id)
+
+        print("delete indexed videos")
+        self.delete_es_videos()
+        url = self.ES_URL + "/ta_channel/_doc/" + self.channel_id
+        response = requests.delete(url, auth=self.ES_AUTH)
+        if not response.ok:
+            print(response.text)
 
 
 class YoutubeVideo:
-    """ represents a signle youtube video """
+    """represents a single youtube video"""
 
     CONFIG = AppConfig().config
-    ES_URL = CONFIG['application']['es_url']
-    CACHE_DIR = CONFIG['application']['cache_dir']
-    VIDEOS = CONFIG['application']['videos']
+    ES_URL = CONFIG["application"]["es_url"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
+    CACHE_DIR = CONFIG["application"]["cache_dir"]
+    VIDEOS = CONFIG["application"]["videos"]
 
     def __init__(self, youtube_id):
         self.youtube_id = youtube_id
         self.channel_id = None
-        self.vid_dict = self.get_wrapper()
+        self.vid_dict = None
 
-    def get_wrapper(self):
-        """ wrapper to loop around youtube_dl to retry on failure """
-        print(f'get video data for {self.youtube_id}')
+    def get_vid_dict(self):
+        """wrapper to loop around youtube_dl to retry on failure"""
+        print(f"get video data for {self.youtube_id}")
+        vid_dict = False
         for i in range(3):
             try:
                 vid_dict = self.get_youtubedl_vid_data()
@@ -241,66 +274,66 @@ class YoutubeVideo:
             else:
                 break
 
-        return vid_dict
+        self.vid_dict = vid_dict
 
     def get_youtubedl_vid_data(self):
-        """ parse youtubedl extract info """
+        """parse youtubedl extract info"""
         youtube_id = self.youtube_id
         obs = {
-            'quiet': True,
-            'default_search': 'ytsearch',
-            'skip_download': True
+            "quiet": True,
+            "default_search": "ytsearch",
+            "skip_download": True,
         }
         try:
             vid = youtube_dl.YoutubeDL(obs).extract_info(youtube_id)
         except (
-                youtube_dl.utils.ExtractorError,
-                youtube_dl.utils.DownloadError
-                ):
-            print('failed to get info for ' + youtube_id)
+            youtube_dl.utils.ExtractorError,
+            youtube_dl.utils.DownloadError,
+        ):
+            print("failed to get info for " + youtube_id)
             return False
         # extract
-        self.channel_id = vid['channel_id']
-        upload_date = vid['upload_date']
+        self.channel_id = vid["channel_id"]
+        upload_date = vid["upload_date"]
         upload_date_time = datetime.strptime(upload_date, "%Y%m%d")
         published = upload_date_time.strftime("%Y-%m-%d")
         last_refresh = int(datetime.now().strftime("%s"))
         # likes
         try:
-            like_count = vid['like_count']
+            like_count = vid["like_count"]
         except KeyError:
             like_count = 0
         try:
-            dislike_count = vid['dislike_count']
+            dislike_count = vid["dislike_count"]
         except KeyError:
             dislike_count = 0
         # build dicts
         stats = {
-            "view_count": vid['view_count'],
+            "view_count": vid["view_count"],
             "like_count": like_count,
             "dislike_count": dislike_count,
-            "average_rating": vid['average_rating']
+            "average_rating": vid["average_rating"],
         }
         vid_basic = {
-            "title": vid['title'],
-            "description": vid['description'],
-            "category": vid['categories'],
-            "vid_thumb_url": vid['thumbnail'],
-            "tags": vid['tags'],
+            "title": vid["title"],
+            "description": vid["description"],
+            "category": vid["categories"],
+            "vid_thumb_url": vid["thumbnail"],
+            "tags": vid["tags"],
             "published": published,
             "stats": stats,
             "vid_last_refresh": last_refresh,
             "date_downloaded": last_refresh,
             "youtube_id": youtube_id,
             "active": True,
-            "channel": False
+            "channel": False,
         }
 
         return vid_basic
 
     def add_player(self, missing_vid):
-        """ add player information for new videos """
-        cache_path = self.CACHE_DIR + '/download/'
+        """add player information for new videos"""
+        cache_path = self.CACHE_DIR + "/download/"
         videos = self.VIDEOS
 
         if missing_vid:
@@ -321,74 +354,181 @@ class YoutubeVideo:
         player = {
             "watched": False,
             "duration": duration,
-            "duration_str": duration_str
+            "duration_str": duration_str,
         }
-        self.vid_dict['player'] = player
+        self.vid_dict["player"] = player
 
     def build_file_path(self, channel_name):
-        """ build media_url from where file will be located """
+        """build media_url from where file will be located"""
         clean_channel_name = clean_string(channel_name)
-        timestamp = self.vid_dict['published'].replace('-', '')
-        youtube_id = self.vid_dict['youtube_id']
-        title = self.vid_dict['title']
+        timestamp = self.vid_dict["published"].replace("-", "")
+        youtube_id = self.vid_dict["youtube_id"]
+        title = self.vid_dict["title"]
         clean_title = clean_string(title)
-        filename = f'{timestamp}_{youtube_id}_{clean_title}.mp4'
+        filename = f"{timestamp}_{youtube_id}_{clean_title}.mp4"
         media_url = os.path.join(clean_channel_name, filename)
-        self.vid_dict['media_url'] = media_url
+        self.vid_dict["media_url"] = media_url
 
     def get_es_data(self):
-        """ get current data from elastic search """
-        url = self.ES_URL + '/ta_video/_doc/' + self.youtube_id
-        response = requests.get(url)
+        """get current data from elastic search"""
+        url = self.ES_URL + "/ta_video/_doc/" + self.youtube_id
+        response = requests.get(url, auth=self.ES_AUTH)
         if not response.ok:
             print(response.text)
         es_vid_dict = json.loads(response.text)
         return es_vid_dict
 
     def upload_to_es(self):
-        """ upload channel data to elastic search """
-        url = f'{self.ES_URL}/ta_video/_doc/{self.youtube_id}'
-        response = requests.put(url, json=self.vid_dict)
+        """upload channel data to elastic search"""
+        url = f"{self.ES_URL}/ta_video/_doc/{self.youtube_id}"
+        response = requests.put(url, json=self.vid_dict, auth=self.ES_AUTH)
         if not response.ok:
             print(response.text)
 
-    def delete_cache(self):
-        """ delete thumbnail from cache if exist """
-        video_cache = os.path.join(self.CACHE_DIR, 'videos')
-        thumb = os.path.join(video_cache, self.youtube_id + '.jpg')
-        if os.path.exists(thumb):
-            os.remove(thumb)
-
     def deactivate(self):
-        """ deactivate document on extractor error """
+        """deactivate document on extractor error"""
         youtube_id = self.youtube_id
-        headers = {'Content-type': 'application/json'}
-        url = f'{self.ES_URL}/ta_video/_update/{youtube_id}'
+        headers = {"Content-type": "application/json"}
+        url = f"{self.ES_URL}/ta_video/_update/{youtube_id}"
         data = {"script": "ctx._source.active = false"}
         json_str = json.dumps(data)
-        response = requests.post(url, data=json_str, headers=headers)
-        print(f'deactivated {youtube_id}')
+        response = requests.post(
+            url, data=json_str, headers=headers, auth=self.ES_AUTH
+        )
+        print(f"deactivated {youtube_id}")
         if not response.ok:
             print(response.text)
 
+    def delete_media_file(self):
+        """delete video file, meta data, thumbnails"""
+        # delete media file
+        es_vid_dict = self.get_es_data()
+        media_url = es_vid_dict["_source"]["media_url"]
+        print(f"delete {media_url} from file system")
+        to_delete = os.path.join(self.VIDEOS, media_url)
+        os.remove(to_delete)
+        # delete from index
+        url = f"{self.ES_URL}/ta_video/_doc/{self.youtube_id}"
+        response = requests.delete(url, auth=self.ES_AUTH)
+        if not response.ok:
+            print(response.text)
+        # delete thumbs from cache
+        ThumbManager().delete_vid_thumb(self.youtube_id)
+
+
+class WatchState:
+    """handle watched checkbox for videos and channels"""
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG["application"]["es_url"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
+    HEADERS = {"Content-type": "application/json"}
+
+    def __init__(self, youtube_id):
+        self.youtube_id = youtube_id
+        self.stamp = int(datetime.now().strftime("%s"))
+
+    def mark_as_watched(self):
+        """update es with new watched value"""
+        url_type = self.dedect_type()
+        if url_type == "video":
+            self.mark_vid_watched()
+        elif url_type == "channel":
+            self.mark_channel_watched()
+
+        print(f"marked {self.youtube_id} as watched")
+
+    def mark_as_unwatched(self):
+        """revert watched state to false"""
+        url_type = self.dedect_type()
+        if url_type == "video":
+            self.mark_vid_watched(revert=True)
+        elif url_type == "channel":
+            self.mark_channel_watched(revert=True)
+
+        print(f"revert {self.youtube_id} as unwatched")
+
+    def dedect_type(self):
+        """find youtube id type"""
+        url_process = UrlListParser(self.youtube_id).process_list()
+        url_type = url_process[0]["type"]
+        return url_type
+
+    def mark_vid_watched(self, revert=False):
+        """change watched status of single video"""
+        url = self.ES_URL + "/ta_video/_update/" + self.youtube_id
+        data = {
+            "doc": {"player": {"watched": True, "watched_date": self.stamp}}
+        }
+        if revert:
+            data["doc"]["player"]["watched"] = False
+
+        payload = json.dumps(data)
+        request = requests.post(
+            url, data=payload, headers=self.HEADERS, auth=self.ES_AUTH
+        )
+        if not request.ok:
+            print(request.text)
+
+    def mark_channel_watched(self, revert=False):
+        """change watched status of every video in channel"""
+        es_url = self.ES_URL
+        headers = self.HEADERS
+        youtube_id = self.youtube_id
+        # create pipeline
+        data = {
+            "description": youtube_id,
+            "processors": [
+                {"set": {"field": "player.watched", "value": True}},
+                {"set": {"field": "player.watched_date", "value": self.stamp}},
+            ],
+        }
+        if revert:
+            data["processors"][0]["set"]["value"] = False
+
+        payload = json.dumps(data)
+        url = f"{es_url}/_ingest/pipeline/{youtube_id}"
+        request = requests.put(
+            url, data=payload, headers=headers, auth=self.ES_AUTH
+        )
+        if not request.ok:
+            print(request.text)
+            raise ValueError("failed to post ingest pipeline")
+
+        # apply pipeline
+        must_list = [
+            {"term": {"channel.channel_id": {"value": youtube_id}}},
+            {"term": {"player.watched": {"value": False}}},
+        ]
+        data = {"query": {"bool": {"must": must_list}}}
+        payload = json.dumps(data)
+        url = f"{es_url}/ta_video/_update_by_query?pipeline={youtube_id}"
+        request = requests.post(
+            url, data=payload, headers=headers, auth=self.ES_AUTH
+        )
+        if not request.ok:
+            print(request.text)
+
 
 def index_new_video(youtube_id, missing_vid=False):
-    """ combine video and channel classes for new video index """
+    """combine video and channel classes for new video index"""
     vid_handler = YoutubeVideo(youtube_id)
+    vid_handler.get_vid_dict()
     if not vid_handler.vid_dict:
-        raise ValueError('failed to get metadata for ' + youtube_id)
+        raise ValueError("failed to get metadata for " + youtube_id)
 
     channel_handler = YoutubeChannel(vid_handler.channel_id)
     # add filepath to vid_dict
-    channel_name = channel_handler.channel_dict['channel_name']
+    channel_name = channel_handler.channel_dict["channel_name"]
     vid_handler.build_file_path(channel_name)
     # add channel and player to video
     vid_handler.add_player(missing_vid)
-    vid_handler.vid_dict['channel'] = channel_handler.channel_dict
+    vid_handler.vid_dict["channel"] = channel_handler.channel_dict
     # add new channel to es
-    if channel_handler.source == 'scraped':
-        channel_handler.channel_dict['channel_subscribed'] = False
+    if channel_handler.source == "scraped":
+        channel_handler.channel_dict["channel_subscribed"] = False
         channel_handler.upload_to_es()
+        channel_handler.get_channel_art()
     # upload video to es
     vid_handler.upload_to_es()
     # return vid_dict for further processing

tubearchivist/home/src/index_management.py

@@ -9,19 +9,17 @@ Functionality:
 import json
 import os
 import zipfile
-
 from datetime import datetime
 
 import requests
-
 from home.src.config import AppConfig
-
+from home.src.helper import ignore_filelist
 
 # expected mapping and settings
 INDEX_CONFIG = [
     {
-        'index_name': 'channel',
-        'expected_map': {
+        "index_name": "channel",
+        "expected_map": {
             "channel_id": {
                 "type": "keyword",
             },
@@ -31,53 +29,34 @@ INDEX_CONFIG = [
                     "keyword": {
                         "type": "keyword",
                         "ignore_above": 256,
-                        "normalizer": "to_lower"
+                        "normalizer": "to_lower",
                     },
                     "search_as_you_type": {
                         "type": "search_as_you_type",
                         "doc_values": False,
-                        "max_shingle_size": 3
-                    }
-                }
+                        "max_shingle_size": 3,
+                    },
+                },
             },
-            "channel_banner_url": {
-                "type": "keyword",
-                "index": False
-            },
-            "channel_thumb_url": {
-                "type": "keyword",
-                "index": False
-            },
-            "channel_description": {
-                "type": "text"
-            },
-            "channel_last_refresh": {
-                "type": "date",
-                "format": "epoch_second"
-            }
+            "channel_banner_url": {"type": "keyword", "index": False},
+            "channel_thumb_url": {"type": "keyword", "index": False},
+            "channel_description": {"type": "text"},
+            "channel_last_refresh": {"type": "date", "format": "epoch_second"},
         },
-        'expected_set': {
+        "expected_set": {
             "analysis": {
                 "normalizer": {
-                    "to_lower": {
-                        "type": "custom",
-                        "filter": ["lowercase"]
-                    }
+                    "to_lower": {"type": "custom", "filter": ["lowercase"]}
                 }
             },
-            "number_of_replicas": "0"
-        }
+            "number_of_replicas": "0",
+        },
     },
     {
-        'index_name': 'video',
-        'expected_map': {
-            "vid_thumb_url": {
-                "type": "text",
-                "index": False
-            },
-            "date_downloaded": {
-                "type": "date"
-            },
+        "index_name": "video",
+        "expected_map": {
+            "vid_thumb_url": {"type": "text", "index": False},
+            "date_downloaded": {"type": "date"},
             "channel": {
                 "properties": {
                     "channel_id": {
@@ -89,127 +68,92 @@ INDEX_CONFIG = [
                             "keyword": {
                                 "type": "keyword",
                                 "ignore_above": 256,
-                                "normalizer": "to_lower"
+                                "normalizer": "to_lower",
                             },
                             "search_as_you_type": {
                                 "type": "search_as_you_type",
                                 "doc_values": False,
-                                "max_shingle_size": 3
-                            }
-                        }
-                    },
-                    "channel_banner_url": {
-                        "type": "keyword",
-                        "index": False
-                    },
-                    "channel_thumb_url": {
-                        "type": "keyword",
-                        "index": False
-                    },
-                    "channel_description": {
-                        "type": "text"
+                                "max_shingle_size": 3,
+                            },
+                        },
                     },
+                    "channel_banner_url": {"type": "keyword", "index": False},
+                    "channel_thumb_url": {"type": "keyword", "index": False},
+                    "channel_description": {"type": "text"},
                     "channel_last_refresh": {
                         "type": "date",
-                        "format": "epoch_second"
-                    }
+                        "format": "epoch_second",
+                    },
                 }
             },
-            "description": {
-                "type": "text"
-            },
-            "media_url": {
-                "type": "keyword",
-                "index": False
-            },
+            "description": {"type": "text"},
+            "media_url": {"type": "keyword", "index": False},
             "title": {
                 "type": "text",
                 "fields": {
                     "keyword": {
                         "type": "keyword",
                         "ignore_above": 256,
-                        "normalizer": "to_lower"
+                        "normalizer": "to_lower",
                     },
                     "search_as_you_type": {
                         "type": "search_as_you_type",
                         "doc_values": False,
-                        "max_shingle_size": 3
-                    }
-                }
-            },
-            "vid_last_refresh": {
-                "type": "date"
-            },
-            "youtube_id": {
-                "type": "keyword"
-            },
-            "published": {
-                "type": "date"
+                        "max_shingle_size": 3,
+                    },
+                },
             },
+            "vid_last_refresh": {"type": "date"},
+            "youtube_id": {"type": "keyword"},
+            "published": {"type": "date"},
         },
-        'expected_set': {
+        "expected_set": {
             "analysis": {
                 "normalizer": {
-                    "to_lower": {
-                        "type": "custom",
-                        "filter": ["lowercase"]
-                    }
+                    "to_lower": {"type": "custom", "filter": ["lowercase"]}
                 }
             },
-            "number_of_replicas": "0"
-        }
+            "number_of_replicas": "0",
+        },
     },
     {
-        'index_name': 'download',
-        'expected_map': {
-            "timestamp": {
-                "type": "date"
-            },
-            "channel_id": {
-                "type": "keyword"
-            },
+        "index_name": "download",
+        "expected_map": {
+            "timestamp": {"type": "date"},
+            "channel_id": {"type": "keyword"},
             "channel_name": {
                 "type": "text",
                 "fields": {
                     "keyword": {
                         "type": "keyword",
                         "ignore_above": 256,
-                        "normalizer": "to_lower"
+                        "normalizer": "to_lower",
                     }
-                }
-            },
-            "status": {
-                "type": "keyword"
+                },
             },
+            "status": {"type": "keyword"},
             "title": {
                 "type": "text",
                 "fields": {
                     "keyword": {
                         "type": "keyword",
                         "ignore_above": 256,
-                        "normalizer": "to_lower"
+                        "normalizer": "to_lower",
                     }
-                }
+                },
             },
-            "vid_thumb_url": {
-                "type": "keyword"
-            },
-            "youtube_id": {
-                "type": "keyword"
-            }
+            "vid_thumb_url": {"type": "keyword"},
+            "youtube_id": {"type": "keyword"},
         },
-        'expected_set': {
+        "expected_set": {
             "analysis": {
                 "normalizer": {
-                    "to_lower": {
-                        "type": "custom",
-                        "filter": ["lowercase"]
-                    }
+                    "to_lower": {"type": "custom", "filter": ["lowercase"]}
                 }
             },
-            "number_of_replicas": "0"
-        }
-    }
+            "number_of_replicas": "0",
+        },
+    },
 ]
 
 
@@ -219,8 +163,9 @@ class ElasticIndex:
     """
 
     CONFIG = AppConfig().config
-    ES_URL = CONFIG['application']['es_url']
-    HEADERS = {'Content-type': 'application/json'}
+    ES_URL = CONFIG["application"]["es_url"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
+    HEADERS = {"Content-type": "application/json"}
 
     def __init__(self, index_name, expected_map, expected_set):
         self.index_name = index_name
@@ -229,14 +174,14 @@ class ElasticIndex:
         self.exists, self.details = self.index_exists()
 
     def index_exists(self):
-        """ check if index already exists and return mapping if it does """
+        """check if index already exists and return mapping if it does"""
         index_name = self.index_name
-        url = f'{self.ES_URL}/ta_{index_name}'
-        response = requests.get(url)
+        url = f"{self.ES_URL}/ta_{index_name}"
+        response = requests.get(url, auth=self.ES_AUTH)
         exists = response.ok
 
         if exists:
-            details = response.json()[f'ta_{index_name}']
+            details = response.json()[f"ta_{index_name}"]
         else:
             details = False
 
@@ -261,19 +206,19 @@ class ElasticIndex:
         return False
 
     def validate_mappings(self):
-        """ check if all mappings are as expected """
+        """check if all mappings are as expected"""
 
         expected_map = self.expected_map
-        now_map = self.details['mappings']['properties']
+        now_map = self.details["mappings"]["properties"]
 
         for key, value in expected_map.items():
             # nested
-            if list(value.keys()) == ['properties']:
-                for key_n, value_n in value['properties'].items():
-                    if key_n not in now_map[key]['properties'].keys():
+            if list(value.keys()) == ["properties"]:
+                for key_n, value_n in value["properties"].items():
+                    if key_n not in now_map[key]["properties"].keys():
                         print(key_n, value_n)
                         return True
-                    if not value_n == now_map[key]['properties'][key_n]:
+                    if not value_n == now_map[key]["properties"][key_n]:
                         print(key_n, value_n)
                         return True
 
@@ -290,9 +235,9 @@ class ElasticIndex:
         return False
 
     def validate_settings(self):
-        """ check if all settings are as expected """
+        """check if all settings are as expected"""
 
-        now_set = self.details['settings']['index']
+        now_set = self.details["settings"]["index"]
 
         for key, value in self.expected_set.items():
             if key not in now_set.keys():
@@ -306,53 +251,48 @@ class ElasticIndex:
         return False
 
     def rebuild_index(self):
-        """ rebuild with new mapping """
+        """rebuild with new mapping"""
         # backup
-        self.reindex('backup')
+        self.reindex("backup")
         # delete original
         self.delete_index(backup=False)
         # create new
         self.create_blank()
-        self.reindex('restore')
+        self.reindex("restore")
         # delete backup
         self.delete_index()
 
     def reindex(self, method):
-        """ create on elastic search """
+        """create on elastic search"""
         index_name = self.index_name
-        if method == 'backup':
-            source = f'ta_{index_name}'
-            destination = f'ta_{index_name}_backup'
-        elif method == 'restore':
-            source = f'ta_{index_name}_backup'
-            destination = f'ta_{index_name}'
+        if method == "backup":
+            source = f"ta_{index_name}"
+            destination = f"ta_{index_name}_backup"
+        elif method == "restore":
+            source = f"ta_{index_name}_backup"
+            destination = f"ta_{index_name}"
 
-        query = {
-            "source": {
-                "index": source
-            },
-            "dest": {
-                "index": destination
-            }
-        }
+        query = {"source": {"index": source}, "dest": {"index": destination}}
         data = json.dumps(query)
-        url = self.ES_URL + '/_reindex?refresh=true'
-        response = requests.post(url=url, data=data, headers=self.HEADERS)
+        url = self.ES_URL + "/_reindex?refresh=true"
+        response = requests.post(
+            url=url, data=data, headers=self.HEADERS, auth=self.ES_AUTH
+        )
         if not response.ok:
             print(response.text)
 
     def delete_index(self, backup=True):
-        """ delete index passed as argument """
+        """delete index passed as argument"""
         if backup:
-            url = f'{self.ES_URL}/ta_{self.index_name}_backup'
+            url = f"{self.ES_URL}/ta_{self.index_name}_backup"
         else:
-            url = f'{self.ES_URL}/ta_{self.index_name}'
-        response = requests.delete(url)
+            url = f"{self.ES_URL}/ta_{self.index_name}"
+        response = requests.delete(url, auth=self.ES_AUTH)
         if not response.ok:
             print(response.text)
 
     def create_blank(self):
-        """ apply new mapping and settings for blank new index """
+        """apply new mapping and settings for blank new index"""
         expected_map = self.expected_map
         expected_set = self.expected_set
         # stich payload
@@ -362,149 +302,193 @@ class ElasticIndex:
         if expected_map:
             payload.update({"mappings": {"properties": expected_map}})
         # create
-        url = f'{self.ES_URL}/ta_{self.index_name}'
+        url = f"{self.ES_URL}/ta_{self.index_name}"
         data = json.dumps(payload)
-        response = requests.put(url=url, data=data, headers=self.HEADERS)
+        response = requests.put(
+            url=url, data=data, headers=self.HEADERS, auth=self.ES_AUTH
+        )
         if not response.ok:
             print(response.text)
 
 
 class ElasticBackup:
-    """ dump index to nd-json files for later bulk import """
+    """dump index to nd-json files for later bulk import"""
 
     def __init__(self, index_config):
         self.config = AppConfig().config
         self.index_config = index_config
-        self.timestamp = datetime.now().strftime('%Y%m%d')
+        self.timestamp = datetime.now().strftime("%Y%m%d")
         self.backup_files = []
 
     def get_all_documents(self, index_name):
-        """ export all documents of a single index """
-        headers = {'Content-type': 'application/json'}
-        es_url = self.config['application']['es_url']
+        """export all documents of a single index"""
+        headers = {"Content-type": "application/json"}
+        es_url = self.config["application"]["es_url"]
+        es_auth = self.config["application"]["es_auth"]
         # get PIT ID
-        url = f'{es_url}/ta_{index_name}/_pit?keep_alive=1m'
-        response = requests.post(url)
+        url = f"{es_url}/ta_{index_name}/_pit?keep_alive=1m"
+        response = requests.post(url, auth=es_auth)
         json_data = json.loads(response.text)
-        pit_id = json_data['id']
+        pit_id = json_data["id"]
         # build query
         data = {
             "query": {"match_all": {}},
-            "size": 100, "pit": {"id": pit_id, "keep_alive": "1m"},
-            "sort": [{"_id": {"order": "asc"}}]
+            "size": 100,
+            "pit": {"id": pit_id, "keep_alive": "1m"},
+            "sort": [{"_id": {"order": "asc"}}],
         }
         query_str = json.dumps(data)
-        url = es_url + '/_search'
+        url = es_url + "/_search"
         # loop until nothing left
         all_results = []
         while True:
-            response = requests.get(url, data=query_str, headers=headers)
+            response = requests.get(
+                url, data=query_str, headers=headers, auth=es_auth
+            )
             json_data = json.loads(response.text)
-            all_hits = json_data['hits']['hits']
+            all_hits = json_data["hits"]["hits"]
             if all_hits:
                 for hit in all_hits:
-                    search_after = hit['sort']
+                    search_after = hit["sort"]
                     all_results.append(hit)
                 # update search_after with last hit data
-                data['search_after'] = search_after
+                data["search_after"] = search_after
                 query_str = json.dumps(data)
             else:
                 break
         # clean up PIT
         query_str = json.dumps({"id": pit_id})
-        requests.delete(es_url + '/_pit', data=query_str, headers=headers)
+        requests.delete(
+            es_url + "/_pit", data=query_str, headers=headers, auth=es_auth
+        )
 
         return all_results
 
     @staticmethod
     def build_bulk(all_results):
-        """ build bulk query data from all_results """
+        """build bulk query data from all_results"""
         bulk_list = []
 
         for document in all_results:
-            document_id = document['_id']
-            es_index = document['_index']
+            document_id = document["_id"]
+            es_index = document["_index"]
             action = {"index": {"_index": es_index, "_id": document_id}}
-            source = document['_source']
+            source = document["_source"]
             bulk_list.append(json.dumps(action))
             bulk_list.append(json.dumps(source))
 
         # add last newline
-        bulk_list.append('\n')
-        file_content = '\n'.join(bulk_list)
+        bulk_list.append("\n")
+        file_content = "\n".join(bulk_list)
 
         return file_content
 
     def write_es_json(self, file_content, index_name):
-        """ write nd json file for es _bulk API to disk """
-        cache_dir = self.config['application']['cache_dir']
-        file_name = f'es_{index_name}-{self.timestamp}.json'
-        file_path = os.path.join(cache_dir, 'backup', file_name)
-        with open(file_path, 'w', encoding='utf-8') as f:
+        """write nd-json file for es _bulk API to disk"""
+        cache_dir = self.config["application"]["cache_dir"]
+        file_name = f"es_{index_name}-{self.timestamp}.json"
+        file_path = os.path.join(cache_dir, "backup", file_name)
+        with open(file_path, "w", encoding="utf-8") as f:
             f.write(file_content)
 
         self.backup_files.append(file_path)
 
     def write_ta_json(self, all_results, index_name):
-        """ write generic json file to disk """
-        cache_dir = self.config['application']['cache_dir']
-        file_name = f'ta_{index_name}-{self.timestamp}.json'
-        file_path = os.path.join(cache_dir, 'backup', file_name)
-        to_write = [i['_source'] for i in all_results]
+        """write generic json file to disk"""
+        cache_dir = self.config["application"]["cache_dir"]
+        file_name = f"ta_{index_name}-{self.timestamp}.json"
+        file_path = os.path.join(cache_dir, "backup", file_name)
+        to_write = [i["_source"] for i in all_results]
         file_content = json.dumps(to_write)
-        with open(file_path, 'w', encoding='utf-8') as f:
+        with open(file_path, "w", encoding="utf-8") as f:
             f.write(file_content)
 
         self.backup_files.append(file_path)
 
     def zip_it(self):
-        """ pack it up into single zip file """
-        cache_dir = self.config['application']['cache_dir']
-        file_name = f'ta_backup-{self.timestamp}.zip'
-        backup_file = os.path.join(cache_dir, 'backup', file_name)
+        """pack it up into single zip file"""
+        cache_dir = self.config["application"]["cache_dir"]
+        file_name = f"ta_backup-{self.timestamp}.zip"
+        backup_folder = os.path.join(cache_dir, "backup")
+        backup_file = os.path.join(backup_folder, file_name)
 
         with zipfile.ZipFile(
-                    backup_file, 'w', compression=zipfile.ZIP_DEFLATED
-                ) as zip_f:
+            backup_file, "w", compression=zipfile.ZIP_DEFLATED
+        ) as zip_f:
             for backup_file in self.backup_files:
-                zip_f.write(backup_file)
+                zip_f.write(backup_file, os.path.basename(backup_file))
 
         # cleanup
         for backup_file in self.backup_files:
             os.remove(backup_file)
 
     def post_bulk_restore(self, file_name):
-        """ send bulk to es """
-        cache_dir = self.config['application']['cache_dir']
-        es_url = self.config['application']['es_url']
-        headers = {'Content-type': 'application/x-ndjson'}
+        """send bulk to es"""
+        cache_dir = self.config["application"]["cache_dir"]
+        es_url = self.config["application"]["es_url"]
+        es_auth = self.config["application"]["es_auth"]
+        headers = {"Content-type": "application/x-ndjson"}
         file_path = os.path.join(cache_dir, file_name)
 
-        with open(file_path, 'r', encoding='utf-8') as f:
+        with open(file_path, "r", encoding="utf-8") as f:
             query_str = f.read()
 
-        url = es_url + '/_bulk'
-        request = requests.post(url, data=query_str, headers=headers)
+        if not query_str.strip():
+            return
+
+        url = es_url + "/_bulk"
+        request = requests.post(
+            url, data=query_str, headers=headers, auth=es_auth
+        )
         if not request.ok:
             print(request.text)
 
-    def restore_from_file(self):
-        """ restore all available backup files """
-        cache_dir = self.config['application']['cache_dir']
+    def unpack_zip_backup(self):
+        """extract backup zip and return filelist"""
+        cache_dir = self.config["application"]["cache_dir"]
+        backup_dir = os.path.join(cache_dir, "backup")
+        backup_files = os.listdir(backup_dir)
+        all_backup_files = ignore_filelist(backup_files)
         all_available_backups = [
-            i for i in os.listdir(cache_dir) if
-            i.startswith('ta_') and i.endswith('.json')
+            i
+            for i in all_backup_files
+            if i.startswith("ta_") and i.endswith(".zip")
         ]
-        for file_name in all_available_backups:
+        all_available_backups.sort()
+        newest_backup = all_available_backups[-1]
+        file_path = os.path.join(backup_dir, newest_backup)
+
+        with zipfile.ZipFile(file_path, "r") as z:
+            zip_content = z.namelist()
+            z.extractall(backup_dir)
+
+        return zip_content
+
+    def restore_json_files(self, zip_content):
+        """go through the unpacked files and restore"""
+
+        cache_dir = self.config["application"]["cache_dir"]
+        backup_dir = os.path.join(cache_dir, "backup")
+
+        for json_f in zip_content:
+
+            file_name = os.path.join(backup_dir, json_f)
+
+            if not json_f.startswith("es_") or not json_f.endswith(".json"):
+                os.remove(file_name)
+                continue
+
+            print("restoring: " + json_f)
             self.post_bulk_restore(file_name)
+            os.remove(file_name)
 
 
 def backup_all_indexes():
-    """ backup all es indexes to disk """
+    """backup all es indexes to disk"""
     backup_handler = ElasticBackup(INDEX_CONFIG)
 
     for index in backup_handler.index_config:
-        index_name = index['index_name']
+        index_name = index["index_name"]
         all_results = backup_handler.get_all_documents(index_name)
         file_content = backup_handler.build_bulk(all_results)
         backup_handler.write_es_json(file_content, index_name)
@@ -514,23 +498,24 @@ def backup_all_indexes():
 
 
 def restore_from_backup():
-    """ restore indexes from backup file """
+    """restore indexes from backup file"""
     # delete
     index_check(force_restore=True)
     # recreate
     backup_handler = ElasticBackup(INDEX_CONFIG)
-    backup_handler.restore_from_file()
+    zip_content = backup_handler.unpack_zip_backup()
+    backup_handler.restore_json_files(zip_content)
 
 
 def index_check(force_restore=False):
-    """ check if all indexes are created and have correct mapping """
+    """check if all indexes are created and have correct mapping"""
 
     backed_up = False
 
     for index in INDEX_CONFIG:
-        index_name = index['index_name']
-        expected_map = index['expected_map']
-        expected_set = index['expected_set']
+        index_name = index["index_name"]
+        expected_map = index["expected_map"]
+        expected_set = index["expected_set"]
         handler = ElasticIndex(index_name, expected_map, expected_set)
         # force restore
         if force_restore:
@@ -540,7 +525,7 @@ def index_check(force_restore=False):
 
         # create new
         if not handler.exists:
-            print(f'create new blank index with name ta_{index_name}...')
+            print(f"create new blank index with name ta_{index_name}...")
             handler.create_blank()
             continue
 
@@ -549,13 +534,13 @@ def index_check(force_restore=False):
         if rebuild:
             # make backup before rebuild
             if not backed_up:
-                print('running backup first')
+                print("running backup first")
                 backup_all_indexes()
                 backed_up = True
 
-            print(f'applying new mappings to index ta_{index_name}...')
+            print(f"applying new mappings to index ta_{index_name}...")
             handler.rebuild_index()
             continue
 
         # else all good
-        print(f'ta_{index_name} index is created and up to date...')
+        print(f"ta_{index_name} index is created and up to date...")

tubearchivist/home/src/reindex.py

@@ -8,38 +8,34 @@ Functionality:
 import json
 import os
 import re
-import subprocess
 import shutil
-
+import subprocess
 from datetime import datetime
-from time import sleep
 from math import ceil
+from time import sleep
 
 import requests
-
-from home.src.download import ChannelSubscription, PendingList, VideoDownloader
 from home.src.config import AppConfig
-from home.src.index import (
-    YoutubeChannel,
-    YoutubeVideo,
-    index_new_video
-)
+from home.src.download import ChannelSubscription, PendingList, VideoDownloader
 from home.src.helper import (
-    get_total_hits,
+    RedisArchivist,
     clean_string,
-    set_message,
-    get_message
+    get_total_hits,
+    ignore_filelist,
 )
+from home.src.index import YoutubeChannel, YoutubeVideo, index_new_video
+from home.src.thumbnails import ThumbManager
 
 
 class Reindex:
-    """ check for outdated documents and refresh data from youtube """
+    """check for outdated documents and refresh data from youtube"""
 
     def __init__(self):
         # config
         config = AppConfig().config
-        self.sleep_interval = config['downloads']['sleep_interval']
-        self.es_url = config['application']['es_url']
+        self.sleep_interval = config["downloads"]["sleep_interval"]
+        self.es_url = config["application"]["es_url"]
+        self.es_auth = config["application"]["es_auth"]
         self.refresh_interval = 90
         # scan
         self.video_daily, self.channel_daily = self.get_daily()
@@ -47,20 +43,20 @@ class Reindex:
         self.all_channel_ids = False
 
     def get_daily(self):
-        """ get daily refresh values """
+        """get daily refresh values"""
         total_videos = get_total_hits(
-            'ta_video', self.es_url, 'active'
+            "ta_video", self.es_url, self.es_auth, "active"
         )
         video_daily = ceil(total_videos / self.refresh_interval * 1.2)
         total_channels = get_total_hits(
-            'ta_channel', self.es_url, 'channel_active'
+            "ta_channel", self.es_url, self.es_auth, "channel_active"
         )
         channel_daily = ceil(total_channels / self.refresh_interval * 1.2)
         return (video_daily, channel_daily)
 
     def get_outdated_vids(self):
-        """ get daily videos to refresh """
-        headers = {'Content-type': 'application/json'}
+        """get daily videos to refresh"""
+        headers = {"Content-type": "application/json"}
         now = int(datetime.now().strftime("%s"))
         now_3m = now - 3 * 30 * 24 * 60 * 60
         size = self.video_daily
@@ -70,24 +66,27 @@ class Reindex:
                 "bool": {
                     "must": [
                         {"match": {"active": True}},
-                        {"range": {"vid_last_refresh": {"lte": now_3m}}}
+                        {"range": {"vid_last_refresh": {"lte": now_3m}}},
                     ]
                 }
             },
-            "sort": [{"vid_last_refresh": {"order": "asc"}}], "_source": False
+            "sort": [{"vid_last_refresh": {"order": "asc"}}],
+            "_source": False,
         }
         query_str = json.dumps(data)
-        url = self.es_url + '/ta_video/_search'
-        response = requests.get(url, data=query_str, headers=headers)
+        url = self.es_url + "/ta_video/_search"
+        response = requests.get(
+            url, data=query_str, headers=headers, auth=self.es_auth
+        )
         if not response.ok:
             print(response.text)
         response_dict = json.loads(response.text)
-        all_youtube_ids = [i['_id'] for i in response_dict['hits']['hits']]
+        all_youtube_ids = [i["_id"] for i in response_dict["hits"]["hits"]]
         return all_youtube_ids
 
     def get_outdated_channels(self):
-        """ get daily channels to refresh """
-        headers = {'Content-type': 'application/json'}
+        """get daily channels to refresh"""
+        headers = {"Content-type": "application/json"}
         now = int(datetime.now().strftime("%s"))
         now_3m = now - 3 * 30 * 24 * 60 * 60
         size = self.channel_daily
@@ -97,52 +96,52 @@ class Reindex:
                 "bool": {
                     "must": [
                         {"match": {"channel_active": True}},
-                        {"range": {"channel_last_refresh": {"lte": now_3m}}}
+                        {"range": {"channel_last_refresh": {"lte": now_3m}}},
                     ]
                 }
             },
             "sort": [{"channel_last_refresh": {"order": "asc"}}],
-            "_source": False
+            "_source": False,
         }
         query_str = json.dumps(data)
-        url = self.es_url + '/ta_channel/_search'
-        response = requests.get(url, data=query_str, headers=headers)
+        url = self.es_url + "/ta_channel/_search"
+        response = requests.get(
+            url, data=query_str, headers=headers, auth=self.es_auth
+        )
         if not response.ok:
             print(response.text)
         response_dict = json.loads(response.text)
-        all_channel_ids = [i['_id'] for i in response_dict['hits']['hits']]
+        all_channel_ids = [i["_id"] for i in response_dict["hits"]["hits"]]
         return all_channel_ids
 
     def check_outdated(self):
-        """ add missing vids and channels """
+        """add missing vids and channels"""
         self.all_youtube_ids = self.get_outdated_vids()
         self.all_channel_ids = self.get_outdated_channels()
 
     def rescrape_all_channels(self):
-        """ sync new data from channel to all matching videos """
+        """sync new data from channel to all matching videos"""
         sleep_interval = self.sleep_interval
         channel_sub_handler = ChannelSubscription()
-        all_channels = channel_sub_handler.get_channels(
-            subscribed_only=False
-        )
-        all_channel_ids = [i['channel_id'] for i in all_channels]
+        all_channels = channel_sub_handler.get_channels(subscribed_only=False)
+        all_channel_ids = [i["channel_id"] for i in all_channels]
 
         counter = 1
         for channel_id in all_channel_ids:
-            message = f'Progress: {counter}/{len(all_channels)}'
+            message = f"Progress: {counter}/{len(all_channels)}"
             mess_dict = {
                 "status": "scraping",
                 "level": "info",
                 "title": "Scraping all youtube channels",
-                "message": message
+                "message": message,
             }
-            set_message('progress:download', mess_dict)
+            RedisArchivist().set_message("progress:download", mess_dict)
             channel_index = YoutubeChannel(channel_id)
-            subscribed = channel_index.channel_dict['channel_subscribed']
+            subscribed = channel_index.channel_dict["channel_subscribed"]
             channel_index.channel_dict = channel_index.build_channel_dict(
                 scrape=True
             )
-            channel_index.channel_dict['channel_subscribed'] = subscribed
+            channel_index.channel_dict["channel_subscribed"] = subscribed
             channel_index.upload_to_es()
             channel_index.sync_to_videos()
             counter = counter + 1
@@ -151,50 +150,60 @@ class Reindex:
 
     @staticmethod
     def reindex_single_video(youtube_id):
-        """ refresh data for single video """
+        """refresh data for single video"""
         vid_handler = YoutubeVideo(youtube_id)
+        vid_handler.get_vid_dict()
         if not vid_handler.vid_dict:
             # stop if deactivated
             vid_handler.deactivate()
             return
 
         es_vid_dict = vid_handler.get_es_data()
-        player = es_vid_dict['_source']['player']
-        date_downloaded = es_vid_dict['_source']['date_downloaded']
-        channel_dict = es_vid_dict['_source']['channel']
-        channel_name = channel_dict['channel_name']
+        player = es_vid_dict["_source"]["player"]
+        date_downloaded = es_vid_dict["_source"]["date_downloaded"]
+        channel_dict = es_vid_dict["_source"]["channel"]
+        channel_name = channel_dict["channel_name"]
         vid_handler.build_file_path(channel_name)
         # add to vid_dict
-        vid_handler.vid_dict['player'] = player
-        vid_handler.vid_dict['date_downloaded'] = date_downloaded
-        vid_handler.vid_dict['channel'] = channel_dict
+        vid_handler.vid_dict["player"] = player
+        vid_handler.vid_dict["date_downloaded"] = date_downloaded
+        vid_handler.vid_dict["channel"] = channel_dict
         # update
         vid_handler.upload_to_es()
-        vid_handler.delete_cache()
+        thumb_handler = ThumbManager()
+        thumb_handler.delete_vid_thumb(youtube_id)
+        to_download = (youtube_id, vid_handler.vid_dict["vid_thumb_url"])
+        thumb_handler.download_vid([to_download], notify=False)
 
     @staticmethod
     def reindex_single_channel(channel_id):
-        """ refresh channel data and sync to videos """
+        """refresh channel data and sync to videos"""
         channel_handler = YoutubeChannel(channel_id)
-        subscribed = channel_handler.channel_dict['channel_subscribed']
+        subscribed = channel_handler.channel_dict["channel_subscribed"]
         channel_handler.channel_dict = channel_handler.build_channel_dict(
             scrape=True
         )
-        channel_handler.channel_dict['channel_subscribed'] = subscribed
+        channel_handler.channel_dict["channel_subscribed"] = subscribed
+        # update
         channel_handler.upload_to_es()
         channel_handler.sync_to_videos()
-        channel_handler.clear_cache()
+        thumb_handler = ThumbManager()
+        thumb_handler.delete_chan_thumb(channel_id)
+        channel_thumb = channel_handler.channel_dict["channel_thumb_url"]
+        channel_banner = channel_handler.channel_dict["channel_banner_url"]
+        to_download = (channel_id, channel_thumb, channel_banner)
+        thumb_handler.download_chan([to_download])
 
     def reindex(self):
-        """ reindex what's needed """
+        """reindex what's needed"""
         # videos
-        print(f'reindexing {len(self.all_youtube_ids)} videos')
+        print(f"reindexing {len(self.all_youtube_ids)} videos")
         for youtube_id in self.all_youtube_ids:
             self.reindex_single_video(youtube_id)
             if self.sleep_interval:
                 sleep(self.sleep_interval)
         # channels
-        print(f'reindexing {len(self.all_channel_ids)} channels')
+        print(f"reindexing {len(self.all_channel_ids)} channels")
         for channel_id in self.all_channel_ids:
             self.reindex_single_channel(channel_id)
             if self.sleep_interval:
@@ -202,28 +211,32 @@ class Reindex:
 
 
 class FilesystemScanner:
-    """ handle scanning and fixing from filesystem """
+    """handle scanning and fixing from filesystem"""
 
     CONFIG = AppConfig().config
-    ES_URL = CONFIG['application']['es_url']
-    VIDEOS = CONFIG['application']['videos']
+    ES_URL = CONFIG["application"]["es_url"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
+    VIDEOS = CONFIG["application"]["videos"]
 
     def __init__(self):
         self.all_downloaded = self.get_all_downloaded()
         self.all_indexed = self.get_all_indexed()
-        self.missmatch = None
+        self.mismatch = None
         self.to_rename = None
         self.to_index = None
         self.to_delete = None
 
     def get_all_downloaded(self):
-        """ get a list of all video files downloaded """
-        all_channels = os.listdir(self.VIDEOS)
+        """get a list of all video files downloaded"""
+        channels = os.listdir(self.VIDEOS)
+        all_channels = ignore_filelist(channels)
         all_channels.sort()
         all_downloaded = []
         for channel_name in all_channels:
             channel_path = os.path.join(self.VIDEOS, channel_name)
-            for video in os.listdir(channel_path):
+            videos = os.listdir(channel_path)
+            all_videos = ignore_filelist(videos)
+            for video in all_videos:
                 youtube_id = video[9:20]
                 all_downloaded.append((channel_name, video, youtube_id))
 
@@ -231,26 +244,26 @@ class FilesystemScanner:
 
     @staticmethod
     def get_all_indexed():
-        """ get a list of all indexed videos """
+        """get a list of all indexed videos"""
         index_handler = PendingList()
         all_indexed_raw = index_handler.get_all_indexed()
         all_indexed = []
         for video in all_indexed_raw:
-            youtube_id = video['_id']
-            media_url = video['_source']['media_url']
-            published = video['_source']['published']
-            title = video['_source']['title']
+            youtube_id = video["_id"]
+            media_url = video["_source"]["media_url"]
+            published = video["_source"]["published"]
+            title = video["_source"]["title"]
             all_indexed.append((youtube_id, media_url, published, title))
         return all_indexed
 
     def list_comarison(self):
-        """ compare the lists to figure out what to do """
+        """compare the lists to figure out what to do"""
         self.find_unindexed()
         self.find_missing()
         self.find_bad_media_url()
 
     def find_unindexed(self):
-        """ find video files without a matching document indexed """
+        """find video files without a matching document indexed"""
         all_indexed_ids = [i[0] for i in self.all_indexed]
         to_index = []
         for downloaded in self.all_downloaded:
@@ -260,7 +273,7 @@ class FilesystemScanner:
         self.to_index = to_index
 
     def find_missing(self):
-        """ find indexed videos without matching media file """
+        """find indexed videos without matching media file"""
         all_downloaded_ids = [i[2] for i in self.all_downloaded]
         to_delete = []
         for video in self.all_indexed:
@@ -271,7 +284,7 @@ class FilesystemScanner:
         self.to_delete = to_delete
 
     def find_bad_media_url(self):
-        """ rename media files not matching the indexed title """
+        """rename media files not matching the indexed title"""
         to_fix = []
         to_rename = []
         for downloaded in self.all_downloaded:
@@ -282,8 +295,8 @@ class FilesystemScanner:
                 if indexed_id == downloaded_id:
                     # found it
                     title_c = clean_string(title)
-                    pub = published.replace('-', '')
-                    expected_filename = f'{pub}_{indexed_id}_{title_c}.mp4'
+                    pub = published.replace("-", "")
+                    expected_filename = f"{pub}_{indexed_id}_{title_c}.mp4"
                     new_url = os.path.join(channel, expected_filename)
                     if expected_filename != filename:
                         # file to rename
@@ -296,83 +309,89 @@ class FilesystemScanner:
 
                     break
 
-        self.missmatch = to_fix
+        self.mismatch = to_fix
         self.to_rename = to_rename
 
     def rename_files(self):
-        """ rename media files as identified by find_bad_media_url """
+        """rename media files as identified by find_bad_media_url"""
         for bad_filename in self.to_rename:
             channel, filename, expected_filename = bad_filename
+            print(f"renaming [{filename}] to [{expected_filename}]")
             old_path = os.path.join(self.VIDEOS, channel, filename)
             new_path = os.path.join(self.VIDEOS, channel, expected_filename)
             os.rename(old_path, new_path)
 
-    def send_missmatch_bulk(self):
-        """ build bulk update """
+    def send_mismatch_bulk(self):
+        """build bulk update"""
         bulk_list = []
-        for video_missmatch in self.missmatch:
-            youtube_id, media_url = video_missmatch
-            action = {"update": {"_id": youtube_id, "_index": 'ta_video'}}
+        for video_mismatch in self.mismatch:
+            youtube_id, media_url = video_mismatch
+            print(f"{youtube_id}: fixing media url {media_url}")
+            action = {"update": {"_id": youtube_id, "_index": "ta_video"}}
             source = {"doc": {"media_url": media_url}}
             bulk_list.append(json.dumps(action))
             bulk_list.append(json.dumps(source))
         # add last newline
-        bulk_list.append('\n')
-        query_str = '\n'.join(bulk_list)
+        bulk_list.append("\n")
+        query_str = "\n".join(bulk_list)
         # make the call
-        headers = {'Content-type': 'application/x-ndjson'}
-        url = self.ES_URL + '/_bulk'
-        request = requests.post(url, data=query_str, headers=headers)
+        headers = {"Content-type": "application/x-ndjson"}
+        url = self.ES_URL + "/_bulk"
+        request = requests.post(
+            url, data=query_str, headers=headers, auth=self.ES_AUTH
+        )
         if not request.ok:
             print(request.text)
 
     def delete_from_index(self):
-        """ find indexed but deleted mediafile """
+        """find indexed but deleted mediafile"""
         for indexed in self.to_delete:
-            youtube_id, _ = indexed
-            url = self.ES_URL + '/ta_video/_doc/' + youtube_id
-            request = requests.delete(url)
+            youtube_id = indexed[0]
+            print(f"deleting {youtube_id} from index")
+            url = self.ES_URL + "/ta_video/_doc/" + youtube_id
+            request = requests.delete(url, auth=self.ES_AUTH)
             if not request.ok:
                 print(request.text)
 
 
 class ManualImport:
-    """ import and indexing existing video files """
+    """import and indexing existing video files"""
 
     CONFIG = AppConfig().config
-    CACHE_DIR = CONFIG['application']['cache_dir']
-    IMPORT_DIR = os.path.join(CACHE_DIR, 'import')
+    CACHE_DIR = CONFIG["application"]["cache_dir"]
+    IMPORT_DIR = os.path.join(CACHE_DIR, "import")
 
     def __init__(self):
         self.identified = self.import_folder_parser()
 
     def import_folder_parser(self):
-        """ detect files in import folder """
-
-        to_import = os.listdir(self.IMPORT_DIR)
+        """detect files in import folder"""
+        import_files = os.listdir(self.IMPORT_DIR)
+        to_import = ignore_filelist(import_files)
         to_import.sort()
-        video_files = [i for i in to_import if not i.endswith('.json')]
+        video_files = [i for i in to_import if not i.endswith(".json")]
 
         identified = []
 
         for file_path in video_files:
 
-            file_dict = {'video_file': file_path}
+            file_dict = {"video_file": file_path}
             file_name, _ = os.path.splitext(file_path)
 
             matching_json = [
-                i for i in to_import if i.startswith(file_name)
-                and i.endswith('.json')
+                i
+                for i in to_import
+                if i.startswith(file_name) and i.endswith(".json")
             ]
             if matching_json:
                 json_file = matching_json[0]
                 youtube_id = self.extract_id_from_json(json_file)
-                file_dict.update({'json_file': json_file})
+                file_dict.update({"json_file": json_file})
             else:
                 youtube_id = self.extract_id_from_filename(file_name)
-                file_dict.update({'json_file': False})
+                file_dict.update({"json_file": False})
 
-            file_dict.update({'youtube_id': youtube_id})
+            file_dict.update({"youtube_id": youtube_id})
             identified.append(file_dict)
 
         return identified
@@ -383,92 +402,111 @@ class ManualImport:
         look at the file name for the youtube id
         expects filename ending in [<youtube_id>].<ext>
         """
-        id_search = re.search(r'\[([a-zA-Z0-9_-]{11})\]$', file_name)
+        id_search = re.search(r"\[([a-zA-Z0-9_-]{11})\]$", file_name)
         if id_search:
             youtube_id = id_search.group(1)
             return youtube_id
 
-        print('failed to extract youtube id for: ' + file_name)
+        print("failed to extract youtube id for: " + file_name)
         raise Exception
 
     def extract_id_from_json(self, json_file):
-        """ open json file and extract id """
-        json_path = os.path.join(self.CACHE_DIR, 'import', json_file)
-        with open(json_path, 'r', encoding='utf-8') as f:
+        """open json file and extract id"""
+        json_path = os.path.join(self.CACHE_DIR, "import", json_file)
+        with open(json_path, "r", encoding="utf-8") as f:
             json_content = f.read()
 
-        youtube_id = json.loads(json_content)['id']
+        youtube_id = json.loads(json_content)["id"]
 
         return youtube_id
 
     def process_import(self):
-        """ go through identified media files """
+        """go through identified media files"""
+
+        all_videos_added = []
 
         for media_file in self.identified:
-            json_file = media_file['json_file']
-            video_file = media_file['video_file']
-            youtube_id = media_file['youtube_id']
+            json_file = media_file["json_file"]
+            video_file = media_file["video_file"]
+            youtube_id = media_file["youtube_id"]
 
-            video_path = os.path.join(self.CACHE_DIR, 'import', video_file)
+            video_path = os.path.join(self.CACHE_DIR, "import", video_file)
 
             self.move_to_cache(video_path, youtube_id)
 
             # identify and archive
             vid_dict = index_new_video(youtube_id)
             VideoDownloader([youtube_id]).move_to_archive(vid_dict)
+            youtube_id = vid_dict["youtube_id"]
+            thumb_url = vid_dict["vid_thumb_url"]
+            all_videos_added.append((youtube_id, thumb_url))
 
             # cleanup
             if os.path.exists(video_path):
                 os.remove(video_path)
             if json_file:
-                json_path = os.path.join(self.CACHE_DIR, 'import', json_file)
+                json_path = os.path.join(self.CACHE_DIR, "import", json_file)
                 os.remove(json_path)
 
+        return all_videos_added
+
     def move_to_cache(self, video_path, youtube_id):
-        """ move identified video file to cache, convert to mp4 """
+        """move identified video file to cache, convert to mp4"""
         file_name = os.path.split(video_path)[-1]
         video_file, ext = os.path.splitext(file_name)
 
         # make sure youtube_id is in filename
-        if not youtube_id in video_file:
-            video_file = f'{video_file}_{youtube_id}'
+        if youtube_id not in video_file:
+            video_file = f"{video_file}_{youtube_id}"
 
         # move, convert if needed
-        if ext == '.mp4':
+        if ext == ".mp4":
             new_file = video_file + ext
-            dest_path = os.path.join(self.CACHE_DIR, 'download', new_file)
+            dest_path = os.path.join(self.CACHE_DIR, "download", new_file)
             shutil.move(video_path, dest_path)
         else:
-            print(f'processing with ffmpeg: {video_file}')
-            new_file = video_file + '.mp4'
-            dest_path = os.path.join(self.CACHE_DIR, 'download', new_file)
+            print(f"processing with ffmpeg: {video_file}")
+            new_file = video_file + ".mp4"
+            dest_path = os.path.join(self.CACHE_DIR, "download", new_file)
             subprocess.run(
-                ["ffmpeg", "-i", video_path, dest_path,
-                "-loglevel", "warning", "-stats"], check=True
+                [
+                    "ffmpeg",
+                    "-i",
+                    video_path,
+                    dest_path,
+                    "-loglevel",
+                    "warning",
+                    "-stats",
+                ],
+                check=True,
             )
 
 
 def scan_filesystem():
-    """ grouped function to delete and update index """
+    """grouped function to delete and update index"""
     filesystem_handler = FilesystemScanner()
     filesystem_handler.list_comarison()
     if filesystem_handler.to_rename:
+        print("renaming files")
         filesystem_handler.rename_files()
-    if filesystem_handler.missmatch:
-        filesystem_handler.send_missmatch_bulk()
+    if filesystem_handler.mismatch:
+        print("fixing media urls in index")
+        filesystem_handler.send_mismatch_bulk()
     if filesystem_handler.to_delete:
+        print("delete metadata from index")
         filesystem_handler.delete_from_index()
     if filesystem_handler.to_index:
+        print("index new videos")
         for missing_vid in filesystem_handler.to_index:
             youtube_id = missing_vid[2]
             index_new_video(youtube_id, missing_vid=missing_vid)
 
 
 def reindex_old_documents():
-    """ daily refresh of old documents """
+    """daily refresh of old documents"""
     # check needed last run
     now = int(datetime.now().strftime("%s"))
-    last_reindex = get_message('last_reindex')
+    last_reindex = RedisArchivist().get_message("last_reindex")
     if isinstance(last_reindex, int) and now - last_reindex < 60 * 60 * 24:
         return
     # continue if needed
@@ -476,4 +514,4 @@ def reindex_old_documents():
     reindex_handler.check_outdated()
     reindex_handler.reindex()
     # set timestamp
-    set_message('last_reindex', now, expire=False)
+    RedisArchivist().set_message("last_reindex", now, expire=False)

tubearchivist/home/src/searching.py

@@ -7,40 +7,39 @@ Functionality:
 """
 
 import math
-import os
 import urllib.parse
-
 from datetime import datetime
 
 import requests
-
-from PIL import Image
-
 from home.src.config import AppConfig
+from home.src.helper import RedisArchivist
+from home.src.thumbnails import ThumbManager
 
 
 class SearchHandler:
-    """ search elastic search """
+    """search elastic search"""
 
     CONFIG = AppConfig().config
-    CACHE_DIR = CONFIG['application']['cache_dir']
+    CACHE_DIR = CONFIG["application"]["cache_dir"]
+    ES_AUTH = CONFIG["application"]["es_auth"]
 
-    def __init__(self, url, data, cache=True):
+    def __init__(self, url, data):
         self.max_hits = None
         self.url = url
         self.data = data
-        self.cache = cache
 
     def get_data(self):
-        """ get the data """
+        """get the data"""
         if self.data:
-            response = requests.get(self.url, json=self.data).json()
+            response = requests.get(
+                self.url, json=self.data, auth=self.ES_AUTH
+            ).json()
         else:
-            response = requests.get(self.url).json()
+            response = requests.get(self.url, auth=self.ES_AUTH).json()
 
-        if 'hits' in response.keys():
-            self.max_hits = response['hits']['total']['value']
-            return_value = response['hits']['hits']
+        if "hits" in response.keys():
+            self.max_hits = response["hits"]["total"]["value"]
+            return_value = response["hits"]["hits"]
         else:
             # simulate list for single result to reuse rest of class
             return_value = [response]
@@ -53,155 +52,155 @@ class SearchHandler:
         all_channels = []
         for idx, hit in enumerate(return_value):
             return_value[idx] = self.hit_cleanup(hit)
-            if hit['_index'] == 'ta_video':
+            if hit["_index"] == "ta_video":
                 video_dict, channel_dict = self.vid_cache_link(hit)
                 if video_dict not in all_videos:
                     all_videos.append(video_dict)
                 if channel_dict not in all_channels:
                     all_channels.append(channel_dict)
-            elif hit['_index'] == 'ta_channel':
+            elif hit["_index"] == "ta_channel":
                 channel_dict = self.channel_cache_link(hit)
                 if channel_dict not in all_channels:
                     all_channels.append(channel_dict)
-        if self.cache:
-            # validate cache
-            self.cache_dl_vids(all_videos)
-            self.cache_dl_chan(all_channels)
 
         return return_value
 
     @staticmethod
     def vid_cache_link(hit):
-        """ download thumbnails into chache """
-        vid_thumb = hit['source']['vid_thumb_url']
-        youtube_id = hit['source']['youtube_id']
-        channel_id_hit = hit['source']['channel']['channel_id']
-        chan_thumb = hit['source']['channel']['channel_thumb_url']
+        """download thumbnails into cache"""
+        vid_thumb = hit["source"]["vid_thumb_url"]
+        youtube_id = hit["source"]["youtube_id"]
+        channel_id_hit = hit["source"]["channel"]["channel_id"]
+        chan_thumb = hit["source"]["channel"]["channel_thumb_url"]
         try:
-            chan_banner = hit['source']['channel']['channel_banner_url']
+            chan_banner = hit["source"]["channel"]["channel_banner_url"]
         except KeyError:
             chan_banner = False
-        video_dict = {
-            'youtube_id': youtube_id,
-            'vid_thumb': vid_thumb
-        }
+        video_dict = {"youtube_id": youtube_id, "vid_thumb": vid_thumb}
         channel_dict = {
-            'channel_id': channel_id_hit,
-            'chan_thumb': chan_thumb,
-            'chan_banner': chan_banner
+            "channel_id": channel_id_hit,
+            "chan_thumb": chan_thumb,
+            "chan_banner": chan_banner,
         }
         return video_dict, channel_dict
 
     @staticmethod
     def channel_cache_link(hit):
-        """ build channel thumb links """
-        channel_id_hit = hit['source']['channel_id']
-        chan_thumb = hit['source']['channel_thumb_url']
+        """build channel thumb links"""
+        channel_id_hit = hit["source"]["channel_id"]
+        chan_thumb = hit["source"]["channel_thumb_url"]
         try:
-            chan_banner = hit['source']['channel_banner_url']
+            chan_banner = hit["source"]["channel_banner_url"]
         except KeyError:
             chan_banner = False
         channel_dict = {
-            'channel_id': channel_id_hit,
-            'chan_thumb': chan_thumb,
-            'chan_banner': chan_banner
+            "channel_id": channel_id_hit,
+            "chan_thumb": chan_thumb,
+            "chan_banner": chan_banner,
         }
         return channel_dict
 
-    def cache_dl_vids(self, all_videos):
-        """ video thumbs links for cache """
-        vid_cache = os.path.join(self.CACHE_DIR, 'videos')
-        all_vid_cached = os.listdir(vid_cache)
-        # videos
-        for video_dict in all_videos:
-            youtube_id = video_dict['youtube_id']
-            if not youtube_id + '.jpg' in all_vid_cached:
-                cache_path = os.path.join(vid_cache, youtube_id + '.jpg')
-                thumb_url = video_dict['vid_thumb']
-                img_raw = requests.get(thumb_url, stream=True).raw
-                img = Image.open(img_raw)
-                width, height = img.size
-                if not width / height == 16 / 9:
-                    new_height = width / 16 * 9
-                    offset = (height - new_height) / 2
-                    img = img.crop((0, offset, width, height - offset))
-                img.convert("RGB").save(cache_path)
-
-    def cache_dl_chan(self, all_channels):
-        """ download channel thumbs """
-        chan_cache = os.path.join(self.CACHE_DIR, 'channels')
-        all_chan_cached = os.listdir(chan_cache)
-        for channel_dict in all_channels:
-            channel_id_cache = channel_dict['channel_id']
-            channel_banner_url = channel_dict['chan_banner']
-            channel_banner = channel_id_cache + '_banner.jpg'
-            channel_thumb_url = channel_dict['chan_thumb']
-            channel_thumb = channel_id_cache + '_thumb.jpg'
-            # thumb
-            if channel_thumb_url and channel_thumb not in all_chan_cached:
-                cache_path = os.path.join(chan_cache, channel_thumb)
-                img_raw = requests.get(channel_thumb_url, stream=True).content
-                with open(cache_path, 'wb') as f:
-                    f.write(img_raw)
-            # banner
-            if channel_banner_url and channel_banner not in all_chan_cached:
-                cache_path = os.path.join(chan_cache, channel_banner)
-                img_raw = requests.get(channel_banner_url, stream=True).content
-                with open(cache_path, 'wb') as f:
-                    f.write(img_raw)
-
     @staticmethod
     def hit_cleanup(hit):
-        """ clean up and parse data from a single hit """
-        hit['source'] = hit.pop('_source')
-        hit_keys = hit['source'].keys()
-        if 'media_url' in hit_keys:
-            parsed_url = urllib.parse.quote(hit['source']['media_url'])
-            hit['source']['media_url'] = parsed_url
+        """clean up and parse data from a single hit"""
+        hit["source"] = hit.pop("_source")
+        hit_keys = hit["source"].keys()
+        if "media_url" in hit_keys:
+            parsed_url = urllib.parse.quote(hit["source"]["media_url"])
+            hit["source"]["media_url"] = parsed_url
 
-        if 'published' in hit_keys:
-            published = hit['source']['published']
+        if "published" in hit_keys:
+            published = hit["source"]["published"]
             date_pub = datetime.strptime(published, "%Y-%m-%d")
             date_str = datetime.strftime(date_pub, "%d %b, %Y")
-            hit['source']['published'] = date_str
+            hit["source"]["published"] = date_str
 
-        if 'vid_last_refresh' in hit_keys:
-            vid_last_refresh = hit['source']['vid_last_refresh']
+        if "vid_last_refresh" in hit_keys:
+            vid_last_refresh = hit["source"]["vid_last_refresh"]
             date_refresh = datetime.fromtimestamp(vid_last_refresh)
             date_str = datetime.strftime(date_refresh, "%d %b, %Y")
-            hit['source']['vid_last_refresh'] = date_str
+            hit["source"]["vid_last_refresh"] = date_str
 
-        if 'channel_last_refresh' in hit_keys:
-            refreshed = hit['source']['channel_last_refresh']
+        if "vid_thumb_url" in hit_keys:
+            youtube_id = hit["source"]["youtube_id"]
+            thumb_path = ThumbManager().vid_thumb_path(youtube_id)
+            hit["source"]["vid_thumb_url"] = thumb_path
+
+        if "channel_last_refresh" in hit_keys:
+            refreshed = hit["source"]["channel_last_refresh"]
             date_refresh = datetime.fromtimestamp(refreshed)
             date_str = datetime.strftime(date_refresh, "%d %b, %Y")
-            hit['source']['channel_last_refresh'] = date_str
+            hit["source"]["channel_last_refresh"] = date_str
 
-        if 'channel' in hit_keys:
-            channel_keys = hit['source']['channel'].keys()
-            if 'channel_last_refresh' in channel_keys:
-                refreshed = hit['source']['channel']['channel_last_refresh']
+        if "channel" in hit_keys:
+            channel_keys = hit["source"]["channel"].keys()
+            if "channel_last_refresh" in channel_keys:
+                refreshed = hit["source"]["channel"]["channel_last_refresh"]
                 date_refresh = datetime.fromtimestamp(refreshed)
                 date_str = datetime.strftime(date_refresh, "%d %b, %Y")
-                hit['source']['channel']['channel_last_refresh'] = date_str
+                hit["source"]["channel"]["channel_last_refresh"] = date_str
 
         return hit
 
 
+class SearchForm:
+    """build query from search form data"""
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG["application"]["es_url"]
+
+    def search_channels(self, search_query):
+        """fancy searching channels as you type"""
+        url = self.ES_URL + "/ta_channel/_search"
+        data = {
+            "size": 10,
+            "query": {
+                "multi_match": {
+                    "query": search_query,
+                    "type": "bool_prefix",
+                    "fields": [
+                        "channel_name.search_as_you_type",
+                        "channel_name._2gram",
+                        "channel_name._3gram",
+                    ],
+                }
+            },
+        }
+        look_up = SearchHandler(url, data)
+        search_results = look_up.get_data()
+        return {"results": search_results}
+
+    @staticmethod
+    def search_videos():
+        """searching for videos"""
+        # TBD palceholder for now
+        return False
+
+
 class Pagination:
     """
     figure out the pagination based on page size and total_hits
     """
 
-    def __init__(self, page_get, search_get=False):
-        config = AppConfig().config
-        self.page_size = config['archive']['page_size']
+    def __init__(self, page_get, user_id, search_get=False):
+        self.user_id = user_id
+        self.page_size = self.get_page_size()
         self.page_get = page_get
         self.search_get = search_get
         self.pagination = self.first_guess()
 
+    def get_page_size(self):
+        """get default or user modified page_size"""
+        key = f"{self.user_id}:page_size"
+        page_size = RedisArchivist().get_message(key)["status"]
+        if not page_size:
+            config = AppConfig().config
+            page_size = config["archive"]["page_size"]
+
+        return page_size
+
     def first_guess(self):
-        """ build first guess before api call """
+        """build first guess before api call"""
         page_get = self.page_get
         if page_get in [0, 1]:
             page_from = 0
@@ -216,22 +215,22 @@ class Pagination:
             "page_size": self.page_size,
             "page_from": page_from,
             "prev_pages": prev_pages,
-            "current_page": page_get
+            "current_page": page_get,
         }
         if self.search_get:
             pagination.update({"search_get": self.search_get})
         return pagination
 
     def validate(self, total_hits):
-        """ validate pagination with total_hits after making api call """
+        """validate pagination with total_hits after making api call"""
         page_get = self.page_get
         max_pages = math.ceil(total_hits / self.page_size)
         if page_get < max_pages and max_pages > 1:
-            self.pagination['last_page'] = max_pages
+            self.pagination["last_page"] = max_pages
         else:
-            self.pagination['last_page'] = False
+            self.pagination["last_page"] = False
         next_pages = [
             i for i in range(page_get + 1, page_get + 6) if 1 < i < max_pages
         ]
 
-        self.pagination['next_pages'] = next_pages
+        self.pagination["next_pages"] = next_pages

tubearchivist/home/src/thumbnails.py

@@ -0,0 +1,288 @@
+"""
+functionality:
+- handle download and caching for thumbnails
+"""
+
+import os
+from collections import Counter
+from time import sleep
+
+import home.src.download as download
+import requests
+from home.src.config import AppConfig
+from home.src.helper import RedisArchivist, ignore_filelist
+from mutagen.mp4 import MP4, MP4Cover
+from PIL import Image
+
+
+class ThumbManager:
+    """handle thumbnails related functions"""
+
+    CONFIG = AppConfig().config
+    MEDIA_DIR = CONFIG["application"]["videos"]
+    CACHE_DIR = CONFIG["application"]["cache_dir"]
+    VIDEO_DIR = os.path.join(CACHE_DIR, "videos")
+    CHANNEL_DIR = os.path.join(CACHE_DIR, "channels")
+
+    def get_all_thumbs(self):
+        """get all video artwork already downloaded"""
+        all_thumb_folders = ignore_filelist(os.listdir(self.VIDEO_DIR))
+        all_thumbs = []
+        for folder in all_thumb_folders:
+            folder_path = os.path.join(self.VIDEO_DIR, folder)
+            if os.path.isfile(folder_path):
+                self.update_path(folder)
+                all_thumbs.append(folder_path)
+                continue
+                # raise exemption here in a future version
+                # raise FileExistsError("video cache dir has files inside")
+
+            all_folder_thumbs = ignore_filelist(os.listdir(folder_path))
+            all_thumbs.extend(all_folder_thumbs)
+
+        return all_thumbs
+
+    def update_path(self, file_name):
+        """reorganize thumbnails into folders as update path from v0.0.5"""
+        folder_name = file_name[0].lower()
+        folder_path = os.path.join(self.VIDEO_DIR, folder_name)
+        old_file = os.path.join(self.VIDEO_DIR, file_name)
+        new_file = os.path.join(folder_path, file_name)
+        os.makedirs(folder_path, exist_ok=True)
+        os.rename(old_file, new_file)
+
+    def get_needed_thumbs(self, missing_only=False):
+        """get a list of all missing thumbnails"""
+        all_thumbs = self.get_all_thumbs()
+        all_indexed = download.PendingList().get_all_indexed()
+        all_in_queue, all_ignored = download.PendingList().get_all_pending()
+
+        needed_thumbs = []
+        for video in all_indexed:
+            youtube_id = video["_source"]["youtube_id"]
+            thumb_url = video["_source"]["vid_thumb_url"]
+            if missing_only:
+                if youtube_id + ".jpg" not in all_thumbs:
+                    needed_thumbs.append((youtube_id, thumb_url))
+            else:
+                needed_thumbs.append((youtube_id, thumb_url))
+
+        for video in all_in_queue + all_ignored:
+            youtube_id = video["youtube_id"]
+            thumb_url = video["vid_thumb_url"]
+            if missing_only:
+                if youtube_id + ".jpg" not in all_thumbs:
+                    needed_thumbs.append((youtube_id, thumb_url))
+            else:
+                needed_thumbs.append((youtube_id, thumb_url))
+
+        return needed_thumbs
+
+    def get_missing_channels(self):
+        """get all channel artwork"""
+        all_channel_art = os.listdir(self.CHANNEL_DIR)
+        files = [i[0:24] for i in all_channel_art]
+        cached_channel_ids = [k for (k, v) in Counter(files).items() if v > 1]
+        channels = download.ChannelSubscription().get_channels(
+            subscribed_only=False
+        )
+
+        missing_channels = []
+        for channel in channels:
+            channel_id = channel["channel_id"]
+            if channel_id not in cached_channel_ids:
+                channel_banner = channel["channel_banner_url"]
+                channel_thumb = channel["channel_thumb_url"]
+                missing_channels.append(
+                    (channel_id, channel_thumb, channel_banner)
+                )
+
+        return missing_channels
+
+    def get_raw_img(self, img_url, thumb_type):
+        """get raw image from youtube and handle 404"""
+        try:
+            app_root = self.CONFIG["application"]["app_root"]
+        except KeyError:
+            # lazy keyerror fix to not have to deal with a strange startup
+            # racing contition between the threads in HomeConfig.ready()
+            app_root = "/app"
+        default_map = {
+            "video": os.path.join(
+                app_root, "static/img/default-video-thumb.jpg"
+            ),
+            "icon": os.path.join(
+                app_root, "static/img/default-channel-icon.jpg"
+            ),
+            "banner": os.path.join(
+                app_root, "static/img/default-channel-banner.jpg"
+            ),
+        }
+        if img_url:
+            try:
+                response = requests.get(img_url, stream=True)
+            except ConnectionError:
+                sleep(5)
+                response = requests.get(img_url, stream=True)
+            if not response.ok and not response.status_code == 404:
+                print("retry thumbnail download for " + img_url)
+                sleep(5)
+                response = requests.get(img_url, stream=True)
+        else:
+            response = False
+        if not response or response.status_code == 404:
+            # use default
+            img_raw = Image.open(default_map[thumb_type])
+        else:
+            # use response
+            img_obj = response.raw
+            img_raw = Image.open(img_obj)
+
+        return img_raw
+
+    def download_vid(self, missing_thumbs, notify=True):
+        """download all missing thumbnails from list"""
+        print(f"downloading {len(missing_thumbs)} thumbnails")
+        counter = 1
+        for youtube_id, thumb_url in missing_thumbs:
+            folder_path = os.path.join(self.VIDEO_DIR, youtube_id[0].lower())
+            thumb_path = os.path.join(
+                self.CACHE_DIR, self.vid_thumb_path(youtube_id)
+            )
+
+            os.makedirs(folder_path, exist_ok=True)
+            img_raw = self.get_raw_img(thumb_url, "video")
+
+            width, height = img_raw.size
+            if not width / height == 16 / 9:
+                new_height = width / 16 * 9
+                offset = (height - new_height) / 2
+                img_raw = img_raw.crop((0, offset, width, height - offset))
+
+            img_raw.convert("RGB").save(thumb_path)
+
+            progress = f"{counter}/{len(missing_thumbs)}"
+            if notify:
+                mess_dict = {
+                    "status": "pending",
+                    "level": "info",
+                    "title": "Downloading Thumbnails",
+                    "message": "Progress: " + progress,
+                }
+                RedisArchivist().set_message("progress:download", mess_dict)
+
+            if counter % 25 == 0:
+                print("thumbnail progress: " + progress)
+            counter = counter + 1
+
+    def download_chan(self, missing_channels):
+        """download needed artwork for channels"""
+        print(f"downloading {len(missing_channels)} channel artwork")
+        for channel in missing_channels:
+            channel_id, channel_thumb, channel_banner = channel
+
+            thumb_path = os.path.join(
+                self.CHANNEL_DIR, channel_id + "_thumb.jpg"
+            )
+            img_raw = self.get_raw_img(channel_thumb, "icon")
+            img_raw.convert("RGB").save(thumb_path)
+
+            banner_path = os.path.join(
+                self.CHANNEL_DIR, channel_id + "_banner.jpg"
+            )
+            img_raw = self.get_raw_img(channel_banner, "banner")
+            img_raw.convert("RGB").save(banner_path)
+
+            mess_dict = {
+                "status": "pending",
+                "level": "info",
+                "title": "Adding to download queue.",
+                "message": "Downloading Channel Art...",
+            }
+            RedisArchivist().set_message("progress:download", mess_dict)
+
+    @staticmethod
+    def vid_thumb_path(youtube_id):
+        """build expected path for video thumbnail from youtube_id"""
+        folder_name = youtube_id[0].lower()
+        folder_path = os.path.join("videos", folder_name)
+        thumb_path = os.path.join(folder_path, youtube_id + ".jpg")
+        return thumb_path
+
+    def delete_vid_thumb(self, youtube_id):
+        """delete video thumbnail if exists"""
+        thumb_path = self.vid_thumb_path(youtube_id)
+        to_delete = os.path.join(self.CACHE_DIR, thumb_path)
+        if os.path.exists(to_delete):
+            os.remove(to_delete)
+
+    def delete_chan_thumb(self, channel_id):
+        """delete all artwork of channel"""
+        thumb = os.path.join(self.CHANNEL_DIR, channel_id + "_thumb.jpg")
+        banner = os.path.join(self.CHANNEL_DIR, channel_id + "_banner.jpg")
+        if os.path.exists(thumb):
+            os.remove(thumb)
+        if os.path.exists(banner):
+            os.remove(banner)
+
+    def cleanup_downloaded(self):
+        """find downloaded thumbnails without video indexed"""
+        all_thumbs = self.get_all_thumbs()
+        all_indexed = self.get_needed_thumbs()
+        all_needed_thumbs = [i[0] + ".jpg" for i in all_indexed]
+        for thumb in all_thumbs:
+            if thumb not in all_needed_thumbs:
+                # cleanup
+                youtube_id = thumb.rstrip(".jpg")
+                self.delete_vid_thumb(youtube_id)
+
+    def get_thumb_list(self):
+        """get list of mediafiles and matching thumbnails"""
+        all_indexed = download.PendingList().get_all_indexed()
+        video_list = []
+        for video in all_indexed:
+            youtube_id = video["_source"]["youtube_id"]
+            media_url = os.path.join(
+                self.MEDIA_DIR, video["_source"]["media_url"]
+            )
+            thumb_path = os.path.join(
+                self.CACHE_DIR, self.vid_thumb_path(youtube_id)
+            )
+            video_list.append(
+                {
+                    "media_url": media_url,
+                    "thumb_path": thumb_path,
+                }
+            )
+
+        return video_list
+
+    @staticmethod
+    def write_all_thumbs(video_list):
+        """rewrite the thumbnail into media file"""
+
+        counter = 1
+        for video in video_list:
+            # loop through all videos
+            media_url = video["media_url"]
+            thumb_path = video["thumb_path"]
+
+            mutagen_vid = MP4(media_url)
+            with open(thumb_path, "rb") as f:
+                mutagen_vid["covr"] = [
+                    MP4Cover(f.read(), imageformat=MP4Cover.FORMAT_JPEG)
+                ]
+            mutagen_vid.save()
+            if counter % 50 == 0:
+                print(f"thumbnail write progress {counter}/{len(video_list)}")
+            counter = counter + 1
+
+
+def validate_thumbnails():
+    """check if all thumbnails are there and organized correctly"""
+    handler = ThumbManager()
+    thumbs_to_download = handler.get_needed_thumbs(missing_only=True)
+    handler.download_vid(thumbs_to_download)
+    missing_channels = handler.get_missing_channels()
+    handler.download_chan(missing_channels)
+    handler.cleanup_downloaded()

tubearchivist/home/tasks.py

@@ -7,86 +7,115 @@ Functionality:
 import os
 
 from celery import Celery, shared_task
-
-from home.src.download import (
-    PendingList,
-    ChannelSubscription,
-    VideoDownloader
-)
 from home.src.config import AppConfig
-from home.src.reindex import reindex_old_documents, ManualImport
-from home.src.index_management import backup_all_indexes
-from home.src.helper import get_lock
-
+from home.src.download import ChannelSubscription, PendingList, VideoDownloader
+from home.src.helper import RedisArchivist, RedisQueue, UrlListParser
+from home.src.index_management import backup_all_indexes, restore_from_backup
+from home.src.reindex import (
+    ManualImport,
+    reindex_old_documents,
+    scan_filesystem,
+)
+from home.src.thumbnails import ThumbManager
 
 CONFIG = AppConfig().config
-REDIS_HOST = CONFIG['application']['REDIS_HOST']
+REDIS_HOST = os.environ.get("REDIS_HOST")
+REDIS_PORT = os.environ.get("REDIS_PORT")
 
-os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'home.settings')
-app = Celery('tasks', broker='redis://' + REDIS_HOST)
-app.config_from_object('django.conf:settings', namespace='CELERY')
+if not REDIS_PORT:
+    REDIS_PORT = 6379
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "home.settings")
+app = Celery("tasks", broker=f"redis://{REDIS_HOST}:{REDIS_PORT}")
+app.config_from_object("django.conf:settings", namespace="ta:")
 app.autodiscover_tasks()
 
 
 @shared_task
 def update_subscribed():
-    """ look for missing videos and add to pending """
+    """look for missing videos and add to pending"""
     channel_handler = ChannelSubscription()
     missing_videos = channel_handler.find_missing()
     if missing_videos:
         pending_handler = PendingList()
-        pending_handler.add_to_pending(missing_videos)
+        all_videos_added = pending_handler.add_to_pending(missing_videos)
+        ThumbManager().download_vid(all_videos_added)
     # check if reindex is needed
     check_reindex.delay()
 
 
 @shared_task
 def download_pending():
-    """ download latest pending videos """
-    pending_handler = PendingList()
-    pending_vids = pending_handler.get_all_pending()[0]
-    to_download = [i['youtube_id'] for i in pending_vids]
-    to_download.reverse()
-    if to_download:
-        download_handler = VideoDownloader(to_download)
-        download_handler.download_list()
+    """download latest pending videos"""
+    have_lock = False
+    my_lock = RedisArchivist().get_lock("downloading")
+
+    try:
+        have_lock = my_lock.acquire(blocking=False)
+        if have_lock:
+            downloader = VideoDownloader()
+            downloader.add_pending()
+            downloader.run_queue()
+        else:
+            print("Did not acquire download lock.")
+
+    finally:
+        if have_lock:
+            my_lock.release()
 
 
 @shared_task
 def download_single(youtube_id):
-    """ start download single video now """
-    download_handler = VideoDownloader([youtube_id])
-    download_handler.download_list()
+    """start download single video now"""
+    queue = RedisQueue("dl_queue")
+    queue.add_priority(youtube_id)
+    print("Added to queue with priority: " + youtube_id)
+    # start queue if needed
+    have_lock = False
+    my_lock = RedisArchivist().get_lock("downloading")
+
+    try:
+        have_lock = my_lock.acquire(blocking=False)
+        if have_lock:
+            VideoDownloader().run_queue()
+        else:
+            print("Download queue already running.")
+
+    finally:
+        # release if only single run
+        if have_lock and not queue.get_next():
+            my_lock.release()
 
 
 @shared_task
 def extrac_dl(youtube_ids):
-    """ parse list passed and add to pending """
+    """parse list passed and add to pending"""
     pending_handler = PendingList()
     missing_videos = pending_handler.parse_url_list(youtube_ids)
-    pending_handler.add_to_pending(missing_videos)
+    all_videos_added = pending_handler.add_to_pending(missing_videos)
+    ThumbManager().download_vid(all_videos_added)
 
 
 @shared_task
 def check_reindex():
-    """ run the reindex main command """
+    """run the reindex main command"""
     reindex_old_documents()
 
 
 @shared_task
 def run_manual_import():
-    """ called from settings page, to go through import folder """
-
-    print('starting media file import')
+    """called from settings page, to go through import folder"""
+    print("starting media file import")
     have_lock = False
-    my_lock = get_lock('manual_import')
+    my_lock = RedisArchivist().get_lock("manual_import")
 
     try:
         have_lock = my_lock.acquire(blocking=False)
         if have_lock:
             import_handler = ManualImport()
             if import_handler.identified:
-                import_handler.process_import()
+                all_videos_added = import_handler.process_import()
+                ThumbManager().download_vid(all_videos_added)
         else:
             print("Did not acquire lock form import.")
 
@@ -94,8 +123,78 @@ def run_manual_import():
         if have_lock:
             my_lock.release()
 
+
 @shared_task
 def run_backup():
-    """ called from settings page, dump backup to zip file """
+    """called from settings page, dump backup to zip file"""
     backup_all_indexes()
-    print('backup finished')
+    print("backup finished")
+
+
+@shared_task
+def run_restore_backup():
+    """called from settings page, dump backup to zip file"""
+    restore_from_backup()
+    print("index restore finished")
+
+
+def kill_dl(task_id):
+    """kill download worker task by ID"""
+    if task_id:
+        app.control.revoke(task_id, terminate=True)
+
+    _ = RedisArchivist().del_message("dl_queue_id")
+    RedisQueue("dl_queue").clear()
+
+    # clear cache
+    cache_dir = os.path.join(CONFIG["application"]["cache_dir"], "download")
+    for cached in os.listdir(cache_dir):
+        to_delete = os.path.join(cache_dir, cached)
+        os.remove(to_delete)
+
+    # notify
+    mess_dict = {
+        "status": "downloading",
+        "level": "error",
+        "title": "Brutally killing download queue",
+        "message": "",
+    }
+    RedisArchivist().set_message("progress:download", mess_dict)
+
+
+@shared_task
+def rescan_filesystem():
+    """check the media folder for mismatches"""
+    scan_filesystem()
+
+
+@shared_task
+def re_sync_thumbs():
+    """sync thumbnails to mediafiles"""
+    handler = ThumbManager()
+    video_list = handler.get_thumb_list()
+    handler.write_all_thumbs(video_list)
+
+
+@shared_task
+def subscribe_to(url_str):
+    """take a list of urls to subscribe to"""
+    youtube_ids = UrlListParser(url_str).process_list()
+    for youtube_id in youtube_ids:
+        if youtube_id["type"] == "video":
+            to_sub = youtube_id["url"]
+            vid_details = PendingList().get_youtube_details(to_sub)
+            channel_id_sub = vid_details["channel_id"]
+        elif youtube_id["type"] == "channel":
+            channel_id_sub = youtube_id["url"]
+        else:
+            raise ValueError("failed to subscribe to: " + youtube_id)
+
+        ChannelSubscription().change_subscribe(
+            channel_id_sub, channel_subscribed=True
+        )
+        print("subscribed to: " + channel_id_sub)
+        # notify
+        RedisArchivist().set_message(
+            "progress:subscribe", {"status": "subscribing"}
+        )

tubearchivist/home/templates/home/about.html

@@ -5,35 +5,13 @@
     <h1>About The Tube Archivist</h1>
 </div>
 <div class="about-section">
-    <h2>Getting started</h2>
-    <ol>
-        <li>Before adding some videos to the download queue, take a look at the download format settings on your <a href="{% url 'settings' %}#format">settings</a> page and set your desired download quality.</li>
-        <li>While at the settings page also set the value for the Subscriptions <a href="{% url 'settings' %}#subscriptions">page size</a>. This will define the max amount of videos that will get added once you run <i>Rescan Subscriptions</i>. yt-dlp by default uses 50 video page size. Any value higher than that will significantly slow down the scanning process.</li>
-        <li>Subscribe to some of your favourite youtube channels in the <a href="{% url 'channel' %}">channel</a> page. To subscribe to a channel you have a few options:
-            <ul>
-                <li>Enter the Youtube channel ID, a 25 character alphanumeric string. For example <span class="settings-current">UCBa659QWEk1AI4Tg--mrJ2A</span></li>
-                <li>Enter the url to the channel page on youtube. For example <span class="settings-current">https://www.youtube.com/channel/UCBa659QWEk1AI4Tg--mrJ2A</span></li>
-                <li>Enter the video url for any video and let <i>Tube Archivist</i> extract the channel ID for you. For example <span class="settings-current">https://www.youtube.com/watch?v=2tdiKTSdE9Y</span></li>
-            </ul>
-        </li>
-        <li>After that head over to the <a href="{% url 'downloads' %}">Downloads</a> Page. Once you click on the <i>Rescan Subscriptions</i> button, <b>Tube Archivist</b> will go through all your subscribed channels and look for new videos. Initially these are the latest videos depending on the page size as described above.</li>
-        <li>Click on <span class="settings-current">ignore</span> for any video you don't want to download or on <span class="settings-current">Download now</span> for any video you want to start downloading now independently from the queue.</li>
-        <li>Click on the <span class="settings-current">Download queue</span> button to start downloading. </b>Tube Archivist</b> will then start the queue from the bottom and download as many videos as defined in <a href="{% url 'settings' %}#downloads">download limit</a>. There is currently no good way to cancel the download process.</li>
-    </ol>
+    <h2>Useful Links</h2>
+    <p>This project is in active and constant development, take a look at the <a href="https://github.com/bbilly1/tubearchivist#roadmap" target="_blank">roadmap</a> for a overview.</p>
+    <p>For any questions on what a button or a function does, You can find the up-to-date user documentation on <a href="https://github.com/bbilly1/tubearchivist/wiki" target="_blank">Github</a>.</p>
+    <p>All contributions are welcome: Open an <a href="https://github.com/bbilly1/tubearchivist/issues" target="_blank">issue</a> for any bugs and errors, start a <a href="https://github.com/bbilly1/tubearchivist/discussions" target="_blank">discussion</a> for anything that will require a more indepth look. The <a href="https://github.com/bbilly1/tubearchivist/blob/master/CONTRIBUTING.md" target="_blank">contributing</a> page is a good place to get started.</p>
 </div>
 <div class="about-section">
-    <h2>Additional</h2>
-    <ul>
-        <li>You can manually add videos to the queue on the <a href="{% url 'downloads' %}">download page</a> by clicking on <i>Add to download queue</i> and then entering a list of videos. Add one link per line. You have a few options:
-            <ul>
-                <li>Add a link to a Youtube video. For example <span class="settings-current">https://www.youtube.com/watch?v=2tdiKTSdE9Y</span>.</li>
-                <li>Add a Youtube video ID. For example <span class="settings-current">2tdiKTSdE9Y</span>.</li>
-                <li>Add a link to a Youtube video by providing the shortened url, for example <span class="settings-current">https://youtu.be/2tdiKTSdE9Y</span>.</li>
-                <li>Add a Channel ID or Channel Url to add every available video to the download queue. This will ignore the page size as described above. You can still ignore selected videos before starting the download.</li>
-                <li>Add a playlist ID or url to add every available video in the list to the download queue, for example <span class="settings-current">https://www.youtube.com/playlist?list=PL96C35uN7xGLLeET0dOWaKHkAlPsrkcha</span> or <span class="settings-current">PL96C35uN7xGLLeET0dOWaKHkAlPsrkcha</span>. Note that when you add a link to a video in a playlist, <b>Tube Archivist</b> assumes you want to download only the specific video and not the whole playlist, vor example <span class="settings-current">https://www.youtube.com/watch?v=CINVwWHlzTY&list=PL96C35uN7xGLLeET0dOWaKHkAlPsrkcha</span> will only add one video <span class="settings-current">CINVwWHlzTY</span> to the queue.</li>
-            </ul>
-        </li>
-        <li>As you watch videos, mark them as watched by clicking on the unseen icon <span class="about-icon"><img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" class="unseen-icon"></span>. Once marked as watched, the icon will change to <span class="about-icon"><img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" class="seen-icon"></span>.</li>
-    </ul>
+    <h2>Donate</h2>
+    <p>Here are <a href="https://github.com/bbilly1/tubearchivist#donate" target="_blank">some links</a>, if you want to buy the developer a coffee. Thank you for your support!</p>
 </div>
-{% endblock content %}
+{% endblock content %}

tubearchivist/home/templates/home/base.html

@@ -45,10 +45,13 @@
             </div>
             <div class="nav-icons">
                 <a href="{% url 'about' %}">
-                    <img src="{% static 'img/icon-help.svg' %}" alt="help-icon">
+                    <img src="{% static 'img/icon-help.svg' %}" alt="help-icon" title="About">
                 </a>
                 <a href="{% url 'settings' %}">
-                    <img src="{% static 'img/icon-gear.svg' %}" alt="gear-icon">
+                    <img src="{% static 'img/icon-gear.svg' %}" alt="gear-icon" title="Settings">
+                </a>
+                <a href="{% url 'logout' %}">
+                    <img src="{% static 'img/icon-exit.svg' %}" alt="exit-icon" title="Logout">
                 </a>
             </div>
         </div>
@@ -96,7 +99,7 @@
     </div>
     <div class="footer">
         <div class="boxed-content">
-            <span>© 2021 The Tube Archivist | <a href="https://github.com/bbilly1/tubearchivist" target="_blank">Github</a> | <a href="https://hub.docker.com/r/bbilly1/tubearchivist" target="_blank">Docker Hub</a></span>
+            <span>© 2021 The Tube Archivist v0.0.7 | <a href="https://github.com/bbilly1/tubearchivist" target="_blank">Github</a> | <a href="https://hub.docker.com/r/bbilly1/tubearchivist" target="_blank">Docker Hub</a></span>
         </div>
     </div>
 </body>

tubearchivist/home/templates/home/channel.html

@@ -7,50 +7,63 @@
 </div>
 <div class="info-box info-box-2">
     <div class="icon-text">
-        <img id="add-icon" onclick="showForm()" src="{% static 'img/icon-add.svg' %}" alt="add-icon">
-        <p>Subscribe to Channels</p>
-        <div class="show-form">
-            <form id="hidden-form" action="/channel/" method="post">
-                {% csrf_token %}
-                <textarea rows="3" placeholder="Input channel ID, channel URL or Video of a channel" id="subscribe" name="subscribe"></textarea>
-                <button type="submit">Subscribe</button>
-            </form>
-        </div>
+        {% if running == "subscribing" %}
+            <p>Subscribing in progress, refresh.</p>
+        {% else %}
+            <img id="add-icon" onclick="showForm()" src="{% static 'img/icon-add.svg' %}" alt="add-icon">
+            <p>Subscribe to Channels</p>
+            <div class="show-form">
+                <form id="hidden-form" action="/channel/" method="post">
+                    {% csrf_token %}
+                    {{ subscribe_form }}
+                    <button type="submit">Subscribe</button>
+                </form>
+            </div>
+        {% endif %}
     </div>
     <div class="search-form icon-text">
         <div class="search-icon">
             <img src="{% static 'img/icon-search.svg' %}" alt="search-icon" onclick="showSearch()">
-            <p>Search Channels</p>
+            <p>Search your Channels</p>
         </div>
         <form onSubmit="return channelRedirect();" id="search-box">
             {% csrf_token %}
-            <input name="videoSearch" list="resultBox" type="text" id="searchInput" autocomplete="off" oninput="searchChannels(this.value)">
+            {{ search_form }}
             <datalist id="resultBox">
             </datalist>
         </form>
     </div>
 </div>
-<div class="padding-box">
-    <h2>Total matching channels: {{ max_hits }}</h2>
-    <span>Change show / hide subscribed only </span><span class="settings-current">{{ show_subed_only }}</span>
-    <select name="watched" id="watched" onchange="showSubscribedOnly(this.value)">
-        <option value="" disabled selected> -- change -- </option>
-        <option value="0">show all channels</option>
-        <option value="1">show subscribed channels only</option>
-    </select>
+<div class="view-controls">
+    <div class="toggle">
+        <span>Show only subscribed channels:</span>
+        <div class="toggleBox">
+            <input 
+                id="show_subed_only" onclick="toggleCheckbox(this)" type="checkbox"
+                {% if show_subed_only %}
+                    checked
+                {% endif %}
+                >
+            <label for="" class="onbtn">On</label>
+            <label for="" class="ofbtn">Off</label>
+        </div>
+    </div>
+    <div class="view-icons">
+        <img src="{% static 'img/icon-gridview.svg' %}" onclick="changeView(this)" data-origin="channel" data-value="grid" alt="grid view">
+        <img src="{% static 'img/icon-listview.svg' %}" onclick="changeView(this)" data-origin="channel" data-value="list" alt="list view">
+    </div>
 </div>
-<div>
+<h2>Total matching channels: {{ max_hits }}</h2>
+<div class="channel-list {{ view_style }}">
     {% if channels %}
         {% for channel in channels %}
-        <div class="channel-item">
-            {% if channel.source.channel_banner_url %}
-                <div class="channel-banner">
-                    <a href="{% url 'channel_id' channel.source.channel_id %}">
-                        <img src="/cache/channels/{{ channel.source.channel_id }}_banner.jpg" alt="{{ channel.source.channel_id }}-banner">
-                    </a>
-                </div>
-            {% endif %}
-            <div class="info-box info-box-2">
+        <div class="channel-item {{ view_style }}">
+            <div class="channel-banner {{ view_style }}">
+                <a href="{% url 'channel_id' channel.source.channel_id %}">
+                    <img src="/cache/channels/{{ channel.source.channel_id }}_banner.jpg" alt="{{ channel.source.channel_id }}-banner">
+                </a>
+            </div>
+            <div class="info-box info-box-2 {{ view_style }}">
                 <div class="info-box-item">
                     <div class="round-img">
                         <a href="{% url 'channel_id' channel.source.channel_id %}">

tubearchivist/home/templates/home/channel_id.html

@@ -6,11 +6,9 @@
     <h1>Channel: {{ channel_info.channel_name }}</h1>
 </div>
 <div class="channel-banner">
-    {% if channel_info.channel_banner_url %}
-        <a href="/channel/{{ channel_info.channel_id }}/"><img src="/cache/channels/{{ channel_info.channel_id }}_banner.jpg" alt="channel_banner"></a>
-    {% endif %}
+    <a href="/channel/{{ channel_info.channel_id }}/"><img src="/cache/channels/{{ channel_info.channel_id }}_banner.jpg" alt="channel_banner"></a>
 </div>
-<div class="info-box info-box-3 padding-box">
+<div class="info-box info-box-3">
     <div class="info-box-item">
         <div class="round-img">
             <a href="{% url 'channel_id' channel_info.channel_id %}">
@@ -36,22 +34,26 @@
                 false
             {% endif %}
             </p>
+            <p>Channel id: {{ channel_info.channel_id }}</p>
+            <button onclick="deleteConfirm()" id="delete-item">Delete Channel</button>
+            <div class="delete-confirm" id="delete-button">
+                <span>Delete {{ channel_info.channel_name }} including all videos? </span><button class="danger-button" onclick="deleteChannel(this)" data-id="{{ channel_info.channel_id }}">Delete</button> <button onclick="cancelDelete()">Cancel</button>
+            </div>
         </div>
     </div>
-    {% if videos %}
     <div class="info-box-item">
         <div>
             {% if channel_info.channel_views >= 1000000 %}
                 <p>Channel views: {{ channel_info.channel_views|intword }}</p>
-            {% else %}
+            {% elif channel_info.channel_views > 0 %}
                 <p>Channel views: {{ channel_info.channel_views|intcomma }}</p>
             {% endif %}
-            <p>Total Videos archived: {{ max_hits }}</p>
-            <p>Watched: <button title="Mark all videos from {{ channel_info.channel_name }} as watched" type="button" id="{{ channel_info.channel_id }}" onclick="isWatched(this.id)">Mark as watched</button></p>
-            <p>Channel id: {{ channel_info.channel_id }}</p>
+            {% if max_hits %}
+                <p>Total Videos archived: {{ max_hits }}</p>
+                <p>Watched: <button title="Mark all videos from {{ channel_info.channel_name }} as watched" type="button" id="{{ channel_info.channel_id }}" onclick="isWatched(this.id)">Mark as watched</button></p>
+            {% endif %}
         </div>
     </div>
-    {% endif %}
 </div>
 {% if channel_info.channel_description %}
     <div class="info-box-item description-box">
@@ -62,25 +64,66 @@
     </div>
 {% endif %}
 <div id="player" class="video-player"></div>
-<h2>Videos</h2>
-<div class="video-list">
+<div class="sort">
+    <p>Sort by <span class="settings-current">{{ sort_by }}</span>
+        <select name="sort" id="sort" onchange="sortChange(this.value)">
+            <option value="" disabled selected> -- change sort by -- </option>
+            <option value="published">date published</option>
+            <option value="downloaded">date downloaded</option>
+            <option value="views">views</option>
+            <option value="likes">likes</option>
+        </select>
+        <select name="sord-order" id="sort-order" onchange="sortChange(this.value)">
+            {% if sort_order == "asc" %}
+                <option value="asc" selected>asc</option>
+            {% else %}
+                <option value="asc">asc</option>
+            {% endif %}
+            {% if sort_order == "desc" %}
+                <option value="desc" selected>desc</option>
+            {% else %}
+                <option value="desc">desc</option>
+            {% endif %}
+        </select>
+    </p>
+</div>
+<div class="view-controls">
+    <div class="toggle">
+        <span>Hide watched videos:</span>
+        <div class="toggleBox">
+            <input 
+                id="hide_watched" onclick="toggleCheckbox(this)" type="checkbox"
+                {% if hide_watched %}
+                    checked
+                {% endif %}
+                >
+            <label for="" class="onbtn">On</label>
+            <label for="" class="ofbtn">Off</label>
+        </div>
+    </div>
+    <div class="view-icons">
+        <img src="{% static 'img/icon-gridview.svg' %}" onclick="changeView(this)" data-origin="home" data-value="grid" alt="grid view">
+        <img src="{% static 'img/icon-listview.svg' %}" onclick="changeView(this)" data-origin="home" data-value="list" alt="list view">
+    </div>
+</div>
+<div class="video-list {{ view_style }}">
     {% if videos %}
         {% for video in videos %}
-            <div class="video-item">
-                <a href="#player" data-src="/media/{{ video.source.media_url }}" data-thumb="/cache/videos/{{ video.source.youtube_id }}.jpg" data-title="{{ video.source.title }}" data-channel="{{ video.source.channel.channel_name }}" data-id="{{ video.source.youtube_id }}" onclick="createPlayer(this)">
-                    <div class="video-thumb-wrap">
+            <div class="video-item {{ view_style }}">
+                <a href="#player" data-src="/media/{{ video.source.media_url }}" data-thumb="/cache/{{ video.source.vid_thumb_url }}" data-title="{{ video.source.title }}" data-channel="{{ video.source.channel.channel_name }}" data-id="{{ video.source.youtube_id }}" onclick="createPlayer(this)">
+                    <div class="video-thumb-wrap {{ view_style }}">
                         <div class="video-thumb">
-                            <img src="/cache/videos/{{ video.source.youtube_id }}.jpg" alt="video-thumb">
+                            <img src="/cache/{{ video.source.vid_thumb_url }}" alt="video-thumb">
                         </div>
                         <div class="video-play">
                             <img src="{% static 'img/icon-play.svg' %}" alt="play-icon">
                         </div>
                     </div>
                 </a>
-                <div class="video-desc">
+                <div class="video-desc {{ view_style }}">
                     <div class="video-desc-player" id="video-info-{{ video.source.youtube_id }}">
                         {% if video.source.player.watched %}
-                            <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.source.youtube_id }}" class="seen-icon">
+                            <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.source.youtube_id }}" onclick="isUnwatched(this.id)" class="seen-icon" title="Mark as unwatched">
                         {% else %}
                             <img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" id="{{ video.source.youtube_id }}" onclick="isWatched(this.id)" class="unseen-icon" title="Mark as watched.">
                         {% endif %}

tubearchivist/home/templates/home/downloads.html

@@ -5,14 +5,15 @@
     <h1>Downloads</h1>
 </div>
 <div id="downloadMessage"></div>
-<div class="info-box info-box-3 padding-box">
+<div id="downloadControl"></div>
+<div class="info-box info-box-3">
     <div class="icon-text">
         <img id="rescan-icon" onclick="rescanPending()" src="{% static 'img/icon-rescan.svg' %}" alt="rescan-icon">
         <p>Rescan subscriptions</p>
     </div>
     <div class="icon-text">
         <img id="download-icon" onclick="dlPending()" src="{% static 'img/icon-download.svg' %}" alt="download-icon">
-        <p>Download queue</p>
+        <p>Start download</p>
     </div>
     <div class="icon-text">
         <img id="add-icon" onclick="showForm()" src="{% static 'img/icon-add.svg' %}" alt="add-icon">
@@ -20,22 +21,51 @@
         <div class="show-form">
             <form id='hidden-form' action="/downloads/" method="post">
                 {% csrf_token %}
-                <textarea rows="4" placeholder="Enter Video Urls or IDs here..." id="vid-url" name="vid-url"></textarea>
+                <!-- <textarea rows="4" placeholder="Enter Video Urls or IDs here..." id="vid-url" name="vid-url"></textarea> -->
+                {{ add_form }}
                 <button type="submit">Add to download queue</button>
             </form>
         </div>
     </div>
 </div>
-<h2>Download queue</h2>
-<div>
-    {% if pending %}
-        <h3>Total pending downloads: {{ max_hits }}</h3>
-        {% for video in pending %}
-            <div class="dl-item" id="dl-{{ video.youtube_id }}">
-                <div class="dl-thumb">
-                    <img src="{{ video.vid_thumb_url }}" alt="video_thumb">
+<div class="view-controls">
+    <div class="toggle">
+        <span>Show only ignored videos:</span>
+        <div class="toggleBox">
+            <input 
+                id="show_ignored_only" onclick="toggleCheckbox(this)" type="checkbox"
+                {% if show_ignored_only %}
+                    checked
+                {% endif %}
+                >
+            <label for="" class="onbtn">On</label>
+            <label for="" class="ofbtn">Off</label>
+        </div>
+    </div>
+    <div class="view-icons">
+        <img src="{% static 'img/icon-gridview.svg' %}" onclick="changeView(this)" data-origin="downloads" data-value="grid" alt="grid view">
+        <img src="{% static 'img/icon-listview.svg' %}" onclick="changeView(this)" data-origin="downloads" data-value="list" alt="list view">
+    </div>
+</div>
+{% if show_ignored_only %}
+    <h2>Ignored from download</h2>
+{% else %}
+    <h2>Download queue</h2>
+{% endif %}
+<h3>Total videos: {{ max_hits }}</h3>
+<div class="dl-list {{ view_style }}">
+    {% if all_video_hits %}
+        {% for video in all_video_hits %}
+            <div class="dl-item {{ view_style }}" id="dl-{{ video.youtube_id }}">
+                <div class="dl-thumb {{ view_style }}">
+                    <img src="/cache/{{ video.vid_thumb_url }}" alt="video_thumb">
+                    {% if show_ignored_only %}
+                        <span>ignored</span>
+                    {% else %}
+                        <span>queued</span>
+                    {% endif %}
                 </div>
-                <div class="dl-desc">
+                <div class="dl-desc {{ view_style }}">
                     <h3>{{ video.title }}</h3>
                     {% if video.channel_indexed %}
                         <a href="{% url 'channel_id' video.channel_id %}">{{ video.channel_name }}</a>
@@ -43,13 +73,16 @@
                         <span>{{ video.channel_name }}</span>
                     {% endif %}
                     <p>Published: {{ video.published }} | Duration: {{ video.duration }} | {{ video.youtube_id }}</p>
-                    <button data-id="{{ video.youtube_id }}" onclick="toIgnore(this)">Ignore</button>
-                    <button id="{{ video.youtube_id }}" data-id="{{ video.youtube_id }}" onclick="downloadNow(this)">Download now</button>
+                    {% if show_ignored_only %}
+                        <button data-id="{{ video.youtube_id }}" onclick="forgetIgnore(this)">Forget</button>
+                        <button data-id="{{ video.youtube_id }}" onclick="addSingle(this)">Add to queue</button>
+                    {% else %}
+                        <button data-id="{{ video.youtube_id }}" onclick="toIgnore(this)">Ignore</button>
+                        <button id="{{ video.youtube_id }}" data-id="{{ video.youtube_id }}" onclick="downloadNow(this)">Download now</button>
+                    {% endif %}
                 </div>
             </div>
         {% endfor %}
-    {% else %}
-        <h3>No pending downloads</h3>
     {% endif %}
 </div>
 <script type="text/javascript" src="{% static 'progress.js' %}"></script>

tubearchivist/home/templates/home/home.html

@@ -6,18 +6,25 @@
 </div>
 <div class="info-box info-box-2">
     <div class="sort">
-        <p>Sort order from <span class="settings-current">{{ sortorder }}</span>
+        <p>Sort by <span class="settings-current">{{ sort_by }}</span>
             <select name="sort" id="sort" onchange="sortChange(this.value)">
-                <option value="" disabled selected> -- change sort order -- </option>
+                <option value="" disabled selected> -- change sort by -- </option>
                 <option value="published">date published</option>
                 <option value="downloaded">date downloaded</option>
+                <option value="views">views</option>
+                <option value="likes">likes</option>
             </select>
-        </p>
-        <p>Hide watched videos <span class="settings-current">{{ hide_watched }}</span>
-            <select name="watched" id="watched" onchange="hideWatched(this.value)">
-                <option value="" disabled selected> -- change hide watched -- </option>
-                <option value="0">show watched videos</option>
-                <option value="1">hide watched videos</option>
+            <select name="sord-order" id="sort-order" onchange="sortChange(this.value)">
+                {% if sort_order == "asc" %}
+                    <option value="asc" selected>asc</option>
+                {% else %}
+                    <option value="asc">asc</option>
+                {% endif %}
+                {% if sort_order == "desc" %}
+                    <option value="desc" selected>desc</option>
+                {% else %}
+                    <option value="desc">desc</option>
+                {% endif %}
             </select>
         </p>
     </div>
@@ -27,29 +34,48 @@
         </div>
         <form action="/" method="POST" id="search-box">
             {% csrf_token %}
-            <input name="videoSearch" list="resultBox" type="text" id="searchInput" autocomplete="off">
+            {{ search_form }}
         </form>
     </div>
 </div>
+<div class="view-controls">
+    <div class="toggle">
+        <span>Hide watched videos:</span>
+        <div class="toggleBox">
+            <input 
+                id="hide_watched" onclick="toggleCheckbox(this)" type="checkbox"
+                {% if hide_watched %}
+                    checked
+                {% endif %}
+                >
+            <label for="" class="onbtn">On</label>
+            <label for="" class="ofbtn">Off</label>
+        </div>
+    </div>
+    <div class="view-icons">
+        <img src="{% static 'img/icon-gridview.svg' %}" onclick="changeView(this)" data-origin="home" data-value="grid" alt="grid view">
+        <img src="{% static 'img/icon-listview.svg' %}" onclick="changeView(this)" data-origin="home" data-value="list" alt="list view">
+    </div>
+</div>
 <div id="player" class="video-player"></div>
-<div class="video-list">
+<div class="video-list {{ view_style }}">
     {% if videos %}
         {% for video in videos %}
-            <div class="video-item">
-                <a href="#player" data-src="/media/{{ video.source.media_url }}" data-thumb="/cache/videos/{{ video.source.youtube_id }}.jpg" data-title="{{ video.source.title }}" data-channel="{{ video.source.channel.channel_name }}" data-id="{{ video.source.youtube_id }}" onclick="createPlayer(this)">
-                    <div class="video-thumb-wrap">
+            <div class="video-item {{ view_style }}">
+                <a href="#player" data-src="/media/{{ video.source.media_url }}" data-thumb="/cache/{{ video.source.vid_thumb_url }}" data-title="{{ video.source.title }}" data-channel="{{ video.source.channel.channel_name }}" data-id="{{ video.source.youtube_id }}" onclick="createPlayer(this)">
+                    <div class="video-thumb-wrap {{ view_style }}">
                         <div class="video-thumb">
-                            <img src="/cache/videos/{{ video.source.youtube_id }}.jpg" alt="video-thumb">
+                            <img src="/cache/{{ video.source.vid_thumb_url }}" alt="video-thumb">
                         </div>
                         <div class="video-play">
                             <img src="{% static 'img/icon-play.svg' %}" alt="play-icon">
                         </div>
                     </div>
                 </a>
-                <div class="video-desc">
+                <div class="video-desc {{ view_style }}">
                     <div class="video-desc-player" id="video-info-{{ video.source.youtube_id }}">
                         {% if video.source.player.watched %}
-                            <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.source.youtube_id }}" class="seen-icon">
+                            <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.source.youtube_id }}" onclick="isUnwatched(this.id)" class="seen-icon" title="Mark as unwatched">
                         {% else %}
                             <img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" id="{{ video.source.youtube_id }}" onclick="isWatched(this.id)" class="unseen-icon" title="Mark as watched.">
                         {% endif %}

tubearchivist/home/templates/home/login.html

@@ -0,0 +1,46 @@
+{% load static %}
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>TA | Welcome</title>
+    <link rel="stylesheet" type="text/css" href="{% static 'css/style.css' %}">
+    <link rel="shortcut icon" type="image/png" href="{% static 'favicon.ico' %}"/>
+    {% if colors == "dark" %}
+        <link rel="stylesheet" href="{% static 'css/dark.css' %}">
+    {% else %}
+        <link rel="stylesheet" href="{% static 'css/light.css' %}">
+    {% endif %}
+</head>
+<body>
+    <div class="boxed-content login-page">
+        {% if colors == 'dark' %}
+            <img src="{% static 'img/logo-tube-archivist-dark.png' %}" alt="tube-archivist-logo">
+        {% endif %}
+        {% if colors == 'light' %}
+            <img src="{% static 'img/logo-tube-archivist-light.png' %}" alt="tube-archivist-banner">
+        {% endif %}
+        <h1>Tube Archivist</h1>
+        <h2>Your Self Hosted YouTube Media Server</h2>
+        {% if form_error %}
+            <p class="danger-zone">Failed to login.</p>
+        {% endif %}
+        <form action="/login/" method="POST" name="login">
+            {% csrf_token %}
+            {% for field in form %}
+                {{ field }}<br>
+            {% endfor %}
+            <input type="hidden" name="next" value="{{ request.GET.next }}" />
+            <button type="submit">Login</button>
+        </form>
+        <p class="login-links"><span><a href="https://github.com/bbilly1/tubearchivist" target="_blank">Github</a></span> <span><a href="https://github.com/bbilly1/tubearchivist#donate" target="_blank">Donate</a></span></p>
+    </div>
+    <div class="footer-colors">
+        <div class="col-1"></div>
+        <div class="col-2"></div>
+        <div class="col-3"></div>
+    </div>
+</body>
+</html>

tubearchivist/home/templates/home/settings.html

@@ -1,63 +1,39 @@
 {% extends "home/base.html" %}
 {% block content %}
 <div class="title-bar">
-    <h1>Settings</h1>
+    <h1>User Configurations</h1>
 </div>
-<form action="/settings/" method="POST" name="settings-update">
+<form action="/settings/" method="POST" name="user-update">
     {% csrf_token %}
     <div class="settings-group">
         <h2>Color scheme</h2>
         <div class="settings-item">
             <p>Current color scheme: <span class="settings-current">{{ config.application.colors }}</span></p>
-            <i>Select yout prefered color scheme between dark and light mode.</i><br>
-            <select name="application.colors" id="application.colors">
-                <option value="" disabled selected> -- change color scheme -- </option>
-                <option value="dark">dark mode</option>
-                <option value="light">light mode</option>
-            </select>
+            <i>Select your preferred color scheme between dark and light mode.</i><br>
+            {{ user_form.colors }}
         </div>
     </div>
     <div class="settings-group">
         <h2>Archive View</h2>
-        <div class="settings-item">
-            <p>Current default Sort: <span class="settings-current">{{ config.archive.sort }}</span></p>
-            <i>Change how the home view and channels view sorts by defaults.</i><br>
-            <select name="archive.sort" id="archive.sort"">
-                <option value="" disabled selected> -- change sort order -- </option>
-                <option value="published">date published</option>
-                <option value="downloaded">date downloaded</option>
-            </select>
-        </div>
-        <div class="settings-item">
-            <p>Current default hide watched: <span class="settings-current">{{ config.archive.hide_watched }}</span></p>
-            <i>Show or hide watched videos by default.</i><br>
-            <select name="archive.hide_watched" id="archive.hide_watched"">
-                <option value="" disabled selected> -- change visibility -- </option>
-                <option value="0">show watched</option>
-                <option value="1">hide watched</option>
-            </select>
-        </div>
-        <div class="settings-item">
-            <p>Current default show subscribed channels only: <span class="settings-current">{{ config.archive.show_subed_only }}</span></p>
-            <i>Show subscribed channels only by default.</i><br>
-            <select name="archive.show_subed_only" id="archive.show_subed_only"">
-                <option value="" disabled selected> -- change visibility -- </option>
-                <option value="0">show subscribed only</option>
-                <option value="1">hide not subscribed</option>
-            </select>
-        </div>
         <div class="settings-item">
             <p>Current page size: <span class="settings-current">{{ config.archive.page_size }}</span></p>
             <i>Result of videos showing in archive page</i><br>
-            <input type="number" name="archive.page_size" id="archive.page_size">
+            {{ user_form.page_size }}
         </div>
     </div>
+    <button type="submit" name="user-settings">Update User Configurations</button>
+</form>
+<div class="title-bar">
+    <h1>Application Configurations</h1>
+</div>
+<form action="/settings/" method="POST" name="application-update">
+    {% csrf_token %}
     <div class="settings-group">
         <h2 id="subscriptions">Subscriptions</h2>
         <div class="settings-item">
-            <p>Currend channel page size: <span class="settings-current">{{ config.subscriptions.channel_size }}</span></p>
+            <p>Current channel page size: <span class="settings-current">{{ config.subscriptions.channel_size }}</span></p>
             <i>Recent videos to check on check pending, max recommended 50.</i><br>
-            <input type="number" name="subscriptions.channel_size" id="subscriptions.channel_size">
+            {{ app_form.subscriptions_channel_size }}
         </div>
         <div class="settings-item">
             <p>Auto scan subscribed channels:</p>
@@ -72,18 +48,23 @@
         <h2 id="downloads">Downloads</h2>
         <div class="settings-item">
             <p>Current download limit: <span class="settings-current">{{ config.downloads.limit_count }}</span></p>
-            <i>Limit the count of videos getting downloaded on every run. 0 (zero) to deactivate.</i><br>
-            <input type="number" name="downloads.limit_count" id="downloads.limit_count">
+            <i>Limit the number of videos getting downloaded on every run. 0 (zero) to deactivate.</i><br>
+            {{ app_form.downloads_limit_count }}
         </div>
         <div class="settings-item">
-            <p>Currend Download speed limit: <span class="settings-current">{{ config.downloads.limit_speed }}</span></p>
+            <p>Current download speed limit: <span class="settings-current">{{ config.downloads.limit_speed }}</span></p>
             <i>Limit download speed. 0 (zero) to deactivate.</i><br>
-            <input type="number" name="downloads.limit_speed" id="downloads.limit_speed"><span>KB/sec</span>
+            {{ app_form.downloads_limit_speed }}
+        </div>
+        <div class="settings-item">
+            <p>Current throttled rate limit: <span class="settings-current">{{ config.downloads.throttledratelimit }}</span></p>
+            <i>Assume the download is being throttled below this speed and restart. 0 (zero) to deactivate, e.g. 100KB/sec</i><br>
+            {{ app_form.downloads_throttledratelimit }}
         </div>
         <div class="settings-item">
             <p>Current scraping sleep interval: <span class="settings-current">{{ config.downloads.sleep_interval }}</p>
-            <i>Seconds to sleep between calls to youtube. Might be necessary to avoid throttling. Recommended 3.</i><br>
-            <input type="number" name="downloads.sleep_interval" id="downloads.sleep_interval">
+            <i>Seconds to sleep between calls to YouTube. Might be necessary to avoid throttling. Recommended 3.</i><br>
+            {{ app_form.downloads_sleep_interval }}
         </div>
         <div class="settings-item">
             <p>External downloader:</p>
@@ -100,25 +81,43 @@
             <ul>
                 <li><span class="settings-current">bestvideo[height<=720]+bestaudio/best[height<=720]</span>: best audio and max video height of 720p.</li>
                 <li><span class="settings-current">bestvideo[height<=1080]+bestaudio/best[height<=1080]</span>: best audio and max video height of 1080p.</li>
+                <li><span class="settings-current">bestvideo[height<=1080][VCODEC=avc1]+bestaudio[ACODEC=mp4a]/mp4</span>: Max 1080p video height with iOS compatible video and audio codecs.</li>
                 <li><span class="settings-current">0</span>: deactivate and download the best quality possible as decided by yt-dlp.</li>
             </ul>
             <i>Make sure your custom format gets merged into a single file. Check out the <a href="https://github.com/yt-dlp/yt-dlp#format-selection" target="_blank">documentation</a> for valid configurations.</i><br>
-            <input type="text" name="downloads.format" id="downloads.format">
+            {{ app_form.downloads_format }}
             <br>
         </div>
+        <div class="settings-item">
+            <p>Current metadata embed setting: <span class="settings-current">{{ config.downloads.add_metadata }}</span></p>
+            <i>Metadata is not embedded into the downloaded files by default.</i><br>
+            {{ app_form.downloads_add_metadata }}
+        </div>
+        <div class="settings-item">
+            <p>Current thumbnail embed setting: <span class="settings-current">{{ config.downloads.add_thumbnail }}</span></p>
+            <i>Embed thumbnail into the mediafile.</i><br>
+            {{ app_form.downloads_add_thumbnail }}
+        </div>
     </div>
-    <button type="submit">Update Settings</button>
+    <button type="submit" name="application-settings">Update Application Configurations</button>
 </form>
 <div class="title-bar">
     <h1>Actions</h1>
 </div>
 <div class="settings-group">
     <h2>Manual media files import.</h2>
-    <p>Add files to the <span class="settings-current">cache/import</span> folder. Make sure to follow the instructions on <a href="https://github.com/bbilly1/tubearchivist#import-your-existing-library" target="_blank">Github</a>.</p>
+    <p>Add files to the <span class="settings-current">cache/import</span> folder. Make sure to follow the instructions in the Github <a href="https://github.com/bbilly1/tubearchivist/wiki/Settings" target="_blank">Wiki</a>.</p>
     <div id="manual-import">
         <button onclick="manualImport()">Start import</button>
     </div>
 </div>
+<div class="settings-group">
+    <h2>Embed thumbnails into media file.</h2>
+    <p>Set extracted youtube thumbnail as cover art of the media file.</p>
+    <div id="re-embed">
+        <button onclick="reEmbed()">Start process</button>
+    </div>
+</div>
 <div class="settings-group">
     <h2>Backup database</h2>
     <p>Export your database to a zip file stored at <span class="settings-current">cache/backup</span>.</p>
@@ -127,11 +126,29 @@
     </div>
 </div>
 <div class="settings-group">
-    <p>Restore from backup.</p>
-    <i>Coming soon</i>
+    <h2>Restore from backup</h2>
+    <p><span class="danger-zone">Danger Zone</span>: This will replace your existing index with the backup.</p>
+    <p>Add the backup zip file to the <span class="settings-current">cache/backup</span> folder.</p>
+    <div id="db-restore">
+        <button onclick="dbRestore()">Restore backup</button>
+    </div>
 </div>
 <div class="settings-group">
-    <p>Rescan filesystem.</p>
-    <i>Coming soon</i>
+    <h2>Rescan filesystem</h2>
+    <p><span class="danger-zone">Danger Zone</span>: This will delete the metadata of deleted videos from the filesystem.</p>
+    <p>Rescan your media folder looking for missing videos and clean up index. More infos on the Github <a href="https://github.com/bbilly1/tubearchivist/wiki/Settings" target="_blank">Wiki</a>.</p>
+    <div id="fs-rescan">
+        <button onclick="fsRescan()">Rescan filesystem</button>
+    </div>
 </div>
-{% endblock content %}
+{% if request.user.is_superuser %}
+    <div class="title-bar">
+        <h1>Users</h1>
+    </div>
+    <div class="settings-group">
+        <h2>User Management</h2>
+        <p>Access the admin interface for basic user management functionality like adding and deleting users, changing passwords and more.</p>
+        <a href="/admin/"><button>Admin Interface</button></a>
+    </div>
+{% endif %}
+{% endblock content %}

tubearchivist/home/templates/home/video.html

@@ -8,8 +8,8 @@
 <div class="video-main">
     <video 
         src="/media/{{ video.media_url }}" 
-        poster="/cache/videos/{{ video.youtube_id }}.jpg" controls preload="false" 
-        type='video/mp4' width="100%">
+        poster="/cache/{{ video.vid_thumb_url }}" controls preload="false" 
+        type='video/mp4' width="100%" playsinline>
     </video>
 </div>
 <div class="info-box info-box-3 padding-box">
@@ -34,7 +34,7 @@
             <p>Last refreshed: {{ video.vid_last_refresh }}</p>
             <p class="video-info-watched">Watched:
                 {% if video.player.watched %}
-                    <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" class="seen-icon" id="{{ video.youtube_id }}">
+                    <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.youtube_id }}" onclick="isUnwatched(this.id)" class="seen-icon" title="Mark as unwatched">
                 {% else %}
                     <img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" id="{{ video.youtube_id }}" onclick="isWatched(this.id)" class="unseen-icon" title="Mark as watched.">
                 {% endif %}
@@ -45,6 +45,10 @@
                 <p>Youtube: Deactivated</p>
             {% endif %}
             <p>Video ID: {{ video.youtube_id }}</p>
+            <button onclick="deleteConfirm()" id="delete-item">Delete Video</button>
+            <div class="delete-confirm" id="delete-button">
+                <span>Are you sure? </span><button class="danger-button" onclick="deleteVideo(this)" data-id="{{ video.youtube_id }}" data-redirect = "{{ video.channel.channel_id }}">Delete</button> <button onclick="cancelDelete()">Cancel</button>
+            </div>
         </div>
     </div>
     <div class="info-box-item">
@@ -52,7 +56,13 @@
             <p>Views: {{ video.stats.view_count|intcomma }}</p>
             <p class="thumb-icon like"><img src="{% static 'img/icon-thumb.svg' %}" alt="thumbs-up">: {{ video.stats.like_count|intcomma }}</p>
             <p class="thumb-icon dislike"><img src="{% static 'img/icon-thumb.svg' %}" alt="thumbs-down">: {{ video.stats.dislike_count|intcomma }}</p>
-            <p>Rating: {{ video.stats.average_rating }}</p>
+            {% if video.stats.average_rating %}
+                <p class="rating-stars">Rating: 
+                    {% for star in video.stats.average_rating %}
+                        <img src="/static/img/icon-star-{{ star }}.svg" alt="{{ star }}">
+                    {% endfor %}
+                </p>
+            {% endif %}
         </div>
     </div>
 </div>

tubearchivist/home/tests.py

@@ -1,3 +0,0 @@
-from django.test import TestCase
-
-# Create your tests here.

tubearchivist/home/tests/test_views.py

@@ -0,0 +1,42 @@
+"""All test classes"""
+
+from django.test import TestCase
+
+
+class URLTests(TestCase):
+    """test if all expected URL are there"""
+
+    def test_home_view(self):
+        """check homepage"""
+        response = self.client.get("/")
+        self.assertEqual(response.status_code, 200)
+
+    def test_about_view(self):
+        """check about page"""
+        response = self.client.get("/about/")
+        self.assertEqual(response.status_code, 200)
+
+    def test_downloads_view(self):
+        """check downloads page"""
+        response = self.client.get("/downloads/")
+        self.assertEqual(response.status_code, 200)
+
+    def test_channel_view(self):
+        """check channel page"""
+        response = self.client.get("/channel/")
+        self.assertEqual(response.status_code, 200)
+
+    def test_settings_view(self):
+        """check settings page"""
+        response = self.client.get("/settings/")
+        self.assertEqual(response.status_code, 200)
+
+    def test_progress_view(self):
+        """check ajax progress endpoint"""
+        response = self.client.get("/downloads/progress/")
+        self.assertEqual(response.status_code, 200)
+
+    def test_process_view(self):
+        """check process ajax endpoint"""
+        response = self.client.get("/process/")
+        self.assertEqual(response.status_code, 200)

tubearchivist/home/urls.py

@@ -1,27 +1,47 @@
 """ all home app urls """
 
+from django.conf import settings
+from django.contrib.auth.decorators import login_required
+from django.contrib.auth.views import LogoutView
 from django.urls import path
-
 from home.views import (
-    HomeView,
-    DownloadView,
-    ChannelView,
+    AboutView,
     ChannelIdView,
-    VideoView,
+    ChannelView,
+    DownloadView,
+    HomeView,
+    LoginView,
     SettingsView,
-    AboutView
+    VideoView,
+    process,
+    progress,
 )
 
-from . import views
-
 urlpatterns = [
-    path('', HomeView.as_view(), name='home'),
-    path('about/', AboutView.as_view(), name='about'),
-    path('downloads/', DownloadView.as_view(), name='downloads'),
-    path('settings/', SettingsView.as_view(), name='settings'),
-    path('process/', views.process, name='process'),
-    path('downloads/progress', views.progress, name='progress'),
-    path('channel/', ChannelView.as_view(), name='channel'),
-    path('channel/<slug:channel_id_detail>/', ChannelIdView.as_view(), name='channel_id'),
-    path('video/<slug:video_id>/', VideoView.as_view(), name='video')
+    path("", login_required(HomeView.as_view()), name="home"),
+    path("login/", LoginView.as_view(), name="login"),
+    path(
+        "logout/",
+        LogoutView.as_view(),
+        {"next_page": settings.LOGOUT_REDIRECT_URL},
+        name="logout",
+    ),
+    path("about/", AboutView.as_view(), name="about"),
+    path(
+        "downloads/", login_required(DownloadView.as_view()), name="downloads"
+    ),
+    path("settings/", login_required(SettingsView.as_view()), name="settings"),
+    path("process/", login_required(process), name="process"),
+    path("downloads/progress/", login_required(progress), name="progress"),
+    path("channel/", login_required(ChannelView.as_view()), name="channel"),
+    path(
+        "channel/<slug:channel_id_detail>/",
+        login_required(ChannelIdView.as_view()),
+        name="channel_id",
+    ),
+    path(
+        "video/<slug:video_id>/",
+        login_required(VideoView.as_view()),
+        name="video",
+    ),
 ]

tubearchivist/manage.py

@@ -5,8 +5,9 @@ import sys
 
 
 def main():
+    # pylint: disable=import-outside-toplevel
     """Run administrative tasks."""
-    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')
+    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "config.settings")
     try:
         from django.core.management import execute_from_command_line
     except ImportError as exc:
@@ -18,5 +19,5 @@ def main():
     execute_from_command_line(sys.argv)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

tubearchivist/requirements.txt

@@ -1,9 +1,9 @@
 beautifulsoup4==4.10.0
 celery==5.1.2
-Django==3.2.7
-Pillow==8.3.2
+Django==3.2.8
+Pillow==8.4.0
 redis==3.5.3
 requests==2.26.0
-uWSGI==2.0.19.1
+uWSGI==2.0.20
 whitenoise==5.3.0
-yt_dlp==2021.9.2
+yt_dlp==2021.10.22

tubearchivist/static/css/dark.css

@@ -2,9 +2,11 @@
     --main-bg: #00202f;
     --highlight-bg: #00293b;
     --highlight-error: #990202;
+    --highlight-error-light: #c44343;
     --highlight-bg-transparent: #00293baf;
     --main-font: #eeeeee;
     --accent-font-dark: #259485;
     --accent-font-light: #97d4c8;
     --img-filter: invert(50%) sepia(9%) saturate(2940%) hue-rotate(122deg) brightness(94%) contrast(90%);
+    --img-filter-error: invert(16%) sepia(60%) saturate(3717%) hue-rotate(349deg) brightness(86%) contrast(120%);
 }

tubearchivist/static/css/light.css

@@ -1,10 +1,12 @@
 :root {
     --main-bg: #eeeeee;
     --highlight-bg: #d9e0d9;
-    --highlight-error: #f79c9c;
+    --highlight-error: #990202;
+    --highlight-error-light: #c44343;
     --highlight-bg-transparent: #00293baf;
     --main-font: #00202f;
     --accent-font-dark: #259485;
     --accent-font-light: #35b399;
     --img-filter: invert(50%) sepia(9%) saturate(2940%) hue-rotate(122deg) brightness(94%) contrast(90%);
+    --img-filter-error: invert(16%) sepia(60%) saturate(3717%) hue-rotate(349deg) brightness(86%) contrast(120%);
 }

tubearchivist/static/css/style.css

@@ -1,12 +1,12 @@
 @font-face {
 font-family: 'Sen-Bold';
-    src:  url('../font/Sen-Bold.ttf.woff');
+    src:  url('../font/Sen-Bold.woff');
     font-family: 'Sen-Bold';
 }
 
 @font-face {
 font-family: 'Sen-Regular';
-    src:  url('../font/Sen-Regular.ttf.woff');
+    src:  url('../font/Sen-Regular.woff');
     font-family: 'Sen-Regular';
 }
 
@@ -62,7 +62,7 @@ ul {
     margin-left: 20px;
 }
 
-td, span {
+td, span, label {
     font-family: Sen-Regular, sans-serif;
     color: var(--main-font);
 }
@@ -138,6 +138,86 @@ button:hover {
     text-decoration: underline;
 }
 
+/* toggle on-off */
+.toggle {
+    display: flex;
+    align-items: center;
+}
+
+.toggleBox > input[type="checkbox"] {
+    position: relative;
+    width: 70px;
+    height: 30px;
+    background-color: var(--accent-font-dark);
+    border-color: var(--accent-font-dark);
+    appearance: none;
+    border-radius: 15px;
+    transition: 0.4s;
+    box-shadow: inset 0 0 5px rgba(0, 0, 0, 0.2);
+    cursor: pointer;
+}
+
+.toggleBox > input:checked[type="checkbox"] {
+    background-color: var(--accent-font-light);
+    border-color: var(--accent-font-light);
+}
+
+.toggleBox > input[type="checkbox"]::before {
+    z-index: 2;
+    position: absolute;
+    content: "";
+    left: 0;
+    top: 0;
+    width: 30px;
+    height: 30px;
+    background-color: white;
+    border-radius: 50%;
+    transform: scale(1.1);
+    transition: 0.4s;
+}
+
+.toggleBox > input:checked[type="checkbox"]::before {
+    left: 40px;
+}
+
+.toggleBox {
+    margin-left: 10px;
+    position: relative;
+    display: inline;
+}
+
+.toggleBox > label {
+    position: absolute;
+    color: var(--main-font);
+    pointer-events: none;
+}
+
+.toggleBox > .onbtn {
+    bottom: 15px;
+    left: 15px;
+    font-family: Sen-Regular, sans-serif;
+}
+
+.toggleBox > .ofbtn {
+    bottom: 15px;
+    right: 15px;
+    font-family: Sen-Regular, sans-serif;
+    color: var(--main-font);
+}
+
+/* delete button */
+.delete-confirm {
+    display: none;
+}
+
+.danger-button {
+    background-color: var(--highlight-error);
+}
+
+.danger-button:hover {
+    background-color: var(--highlight-error-light);
+}
+
 /* navigation */
 .top-nav {
     display: block;
@@ -170,13 +250,13 @@ button:hover {
 
 .nav-icons img {
     width: 40px;
-    padding: 0 10px;
+    padding: 0 5px;
     filter: var(--img-filter);
 }
 
 /* top of page */
 .title-bar {
-    padding: 25px 0;
+    padding: 20px 0;
 }
 
 .sort {
@@ -211,6 +291,26 @@ button:hover {
     filter: var(--img-filter);
 }
 
+.view-controls {
+    display: grid;
+    grid-template-columns: 1fr 1fr;
+    border-bottom: 2px solid;
+    border-color: var(--accent-font-dark);
+    margin: 15px 0;
+}
+
+.view-icons {
+    display: flex;
+    justify-content: end;
+}
+
+.view-icons img {
+    width: 30px;
+    margin: 5px 10px;
+    cursor: pointer;
+    filter: var(--img-filter);
+}
+
 #search-box {
     display: none;
     flex: auto;
@@ -261,16 +361,27 @@ button:hover {
 
 
 /* video list */
-.video-list {
+.video-list.grid {
     display: grid;
     grid-template-columns: 1fr 1fr 1fr;
     grid-gap: 1rem;
 }
 
+.video-list.list {
+    display: grid;
+    grid-template-columns: unset;
+    grid-gap: 1rem;
+}
+
 .video-item {
     overflow: hidden;
 }
 
+.video-item.list {
+    display: grid;
+    grid-template-columns: 25% auto;
+}
+
 .video-thumb img {
     width: 100%;
 }
@@ -301,12 +412,25 @@ button:hover {
     padding: 8px;
 }
 
-.video-desc {
+.video-desc.grid {
     padding: 10px;
     height: 100%;
     background-color: var(--highlight-bg);
 }
 
+.video-desc.list {
+    padding: 10px;
+    height: unset;
+    background-color: var(--highlight-bg);
+    display: flex;
+    flex-wrap: wrap-reverse;
+    align-content: center;
+}
+
+.video-desc > div {
+    width: 100%;
+}
+
 .video-desc img {
     width: 20px;
     margin-right: 10px;
@@ -329,15 +453,12 @@ button:hover {
 }
 
 .unseen-icon,
+.seen-icon,
 .close-button {
     cursor: pointer;
     filter: var(--img-filter);
 }
 
-.seen-icon {
-    filter: var(--img-filter);
-}
-
 .video-more {
     text-decoration: underline;
     text-align: right;
@@ -362,6 +483,7 @@ button:hover {
 .info-box {
     display: grid;
     grid-gap: 1rem;
+    margin: 1rem 0;
 }
 
 .info-box-3 {
@@ -392,6 +514,69 @@ button:hover {
     margin-bottom: 10px;
 }
 
+/* login */
+.login-page {
+    display: flex;
+    flex-wrap: wrap;
+    justify-content: center;
+    text-align: center;
+    align-content: center;
+}
+
+.login-page > * {
+    width: 100%;
+}
+
+.login-page img {
+    width: 100%;
+    max-width: 200px;
+    max-height: 200px;
+    margin-bottom: 40px;
+}
+
+.login-page form {
+    margin: 30px 0;
+}
+
+.login-page input {
+    min-width: 200px;
+}
+
+.login-page button,
+.login-page .danger-zone {
+    width: 210px;
+    margin-top: 5px;
+}
+
+.login-links a {
+    text-decoration: underline;
+    margin: 30px 0;
+    padding: 20px;
+}
+
+.footer-colors {
+    grid-row-start: 2;
+    grid-row-end: 3;
+    display: flex;
+}
+
+.footer-colors div {
+    padding: 20px 0;
+    width: 33.33%;
+}
+
+.col-1 {
+    background-color: var(--highlight-bg);
+}
+
+.col-2 {
+    background-color: var(--accent-font-dark);
+}
+
+.col-3 {
+    background-color: var(--accent-font-light);
+}
+
 /* video page */
 .video-main video {
     max-height: 70vh;
@@ -406,7 +591,8 @@ button:hover {
     margin-left: 5px;
 }
 
-.thumb-icon img {
+.thumb-icon img,
+.rating-stars img {
     width: 20px;
     margin: 0;
     filter: var(--img-filter);
@@ -417,14 +603,41 @@ button:hover {
 }
 
 /* channel overview page */
-.channel-item {
+.channel-list.list {
+    display: block;
+}
+
+.channel-list.grid {
+    display: grid;
+    grid-template-columns: 1fr 1fr 1fr;
+    gap: 1rem;
+}
+
+.channel-item.list {
     padding: 20px 0;
 }
 
+.channel-item.grid > .info-box {
+    display: block;
+}
+
 .channel-banner img {
     width: 100%;
 }
 
+.channel-banner.grid {
+    overflow: hidden;
+}
+
+.channel-banner.list img {
+    width: 100%;
+}
+
+.channel-banner.grid img {
+    width: 250%;
+    transform: translateX(-30%);
+}
+
 
 /* download page */
 .icon-text {
@@ -438,30 +651,92 @@ button:hover {
     cursor: pointer;
 }
 
-.dl-item {
+.dl-list.list {
+    display: block;
+}
+
+.dl-list.grid {
+    display: grid;
+    grid-template-columns: 1fr 1fr 1fr;
+    grid-gap: 1rem;
+}
+
+.dl-item.list {
     display: flex;
     margin: 15px 0;
     align-items: center;
     background-color: var(--highlight-bg);
 }
 
+.dl-item.grid {
+    display: flex;
+    flex-wrap: wrap;
+    background-color: var(--highlight-bg);
+}
+
 .dl-check {
     width: 30px;
 }
 
+.dl-item:hover > .dl-thumb span {
+    opacity: 1;
+}
+
 .dl-thumb {
+    position: relative;
+}
+
+.dl-thumb span {
+    position: absolute;
+    top: 5px;
+    left: 5px;
+    background-color: var(--accent-font-light);
+    padding: 5px;
+    opacity: 0;
+    transition: 300ms ease-in-out;
+}
+
+.dl-thumb.list {
     width: 25%;
 }
 
+.dl-thumb.grid {
+    width: 100%;
+}
+
 .dl-item img {
     width: 100%;
 }
 
-.dl-desc {
-    padding-left: 15px;
+.dl-desc.list {
+    padding: 0 15px;
     width: 75%;
 }
 
+.dl-desc.grid {
+    padding: 15px;
+    width: 100%;
+}
+
+.dl-control-icons {
+    display: flex;
+    justify-content: center;
+    padding: 10px 0;
+}
+
+.dl-control-icons img {
+    width: 30px;
+    cursor: pointer;
+    margin: 5px;
+}
+
+#stop-icon {
+    filter: var(--img-filter);
+}
+
+#kill-icon {
+    filter: var(--img-filter-error);
+}
 
 /* status message */
 .download-progress {
@@ -478,6 +753,10 @@ button:hover {
     background-color: var(--highlight-error);
 }
 
+.download-progress.error h3 {
+    color: #fff;
+}
+
 /* settings */
 .settings-group {
     background-color: var(--highlight-bg);
@@ -493,6 +772,12 @@ button:hover {
     min-width: 300px;
 }
 
+.danger-zone {
+    background-color: var(--highlight-error);
+    color: #fff;
+    padding: 3px;
+}
+
 /* about */
 .about-section {
     padding: 20px 0;
@@ -562,9 +847,18 @@ button:hover {
     .boxed-content {
         width: 90%;
     }
-    .video-list {
+    .video-list.grid,
+    .dl-list.grid,
+    .channel-list.grid {
         grid-template-columns: 1fr 1fr;
     }
+    .dl-thumb.list {
+        width: 35%;
+    }
+    .video-item.list {
+        display: grid;
+        grid-template-columns: 35% auto;
+    }
     .two-col {
         display: block;
     }
@@ -578,15 +872,26 @@ button:hover {
     * {
         word-wrap: anywhere;
     }
-    .video-list {
+    .video-list.grid,
+    .dl-list.grid,
+    .channel-list.grid,
+    .video-item.list {
         grid-template-columns: 1fr;
     }
+    .video-desc.grid {
+        height: unset;
+        display: flex;
+        flex-wrap: wrap-reverse;
+    }
     .boxed-content {
         width: 95%;
     }
     .footer {
         text-align: center;
     }
+    .toggle {
+        flex-wrap: wrap;
+    }
     .top-nav {
         flex-wrap: wrap-reverse;
         display: flex;

tubearchivist/static/font/OFL_License.txt

@@ -0,0 +1,94 @@
+Copyright (c) 2015, Kosal Sen, Philatype (<http://philatype.com>),
+with Reserved Font Name Sen.
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

tubearchivist/static/img/icon-exit.svg

@@ -0,0 +1,67 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_exit.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.66442107"
+     inkscape:cx="161.45413"
+     inkscape:cy="207.61753"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1169"
+     inkscape:window-height="893"
+     inkscape:window-x="729"
+     inkscape:window-y="13"
+     inkscape:window-maximized="0" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <g
+       id="g855"
+       transform="matrix(1.9016362,0,0,1.9016362,-197.93838,-58.9418)">
+      <path
+         inkscape:connector-curvature="0"
+         id="rect1208"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+         d="m 124.57603,151.92962 c -0.0433,2.30016 2.0751,4.19245 4.75007,4.24278 l 30.26401,0.43007 -6.00195,5.78023 3.43246,3.56154 10.2778,-9.9006 0.002,0.002 3.5183,-3.3908 -3.42991,-3.564 -9.8737,-10.24989 -3.51834,3.39083 5.84388,6.06803 -30.35875,-0.43185 c -2.67494,-0.0503 -4.86301,1.76094 -4.90629,4.06112 z m -17.65039,-32.01644 v 64.95883 h 7.44347 v -58.27707 h 26.3896 v 18.5229 h 7.44296 v -25.20466 z m 33.83307,39.75416 v 25.20467 h 7.44296 v -25.20467 z" />
+    </g>
+  </g>
+</svg>

tubearchivist/static/img/icon-gridview.svg

@@ -0,0 +1,122 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="2000"
+   height="2000"
+   viewBox="0 0 529.16666 529.16735"
+   version="1.1"
+   id="svg8"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Gridview.svg">
+  <defs
+     id="defs2" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.35729063"
+     inkscape:cx="901.7564"
+     inkscape:cy="1021.9111"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     showguides="true"
+     inkscape:guide-bbox="true"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1">
+    <sodipodi:guide
+       position="247.25932,291.92959"
+       orientation="1,0"
+       id="guide853"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="337.22901,167.98535"
+       orientation="0,1"
+       id="guide855"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="266.76325,305.4565"
+       orientation="0,1"
+       id="guide857"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="257.79774,279.50371"
+       orientation="0,1"
+       id="guide861"
+       inkscape:locked="false" />
+  </sodipodi:namedview>
+  <metadata
+     id="metadata5">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,232.16736)">
+    <g
+       id="g873"
+       transform="matrix(1.3431799,0,0,1.3431799,-84.854433,26.13855)"
+       style="stroke:none">
+      <rect
+         ry="7.445024"
+         rx="7.445024"
+         y="-121.39048"
+         x="79.903137"
+         height="113.24854"
+         width="167.35619"
+         id="rect815"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.56300002;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.12600005, 0.56300002999999998;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+      <rect
+         ry="7.445024"
+         rx="7.445024"
+         y="-121.7837"
+         x="273.05484"
+         height="113.24854"
+         width="167.35619"
+         id="rect815-4"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.56300002;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.12600006, 0.56300004000000003;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+      <rect
+         ry="7.445024"
+         rx="7.445024"
+         y="17.882772"
+         x="79.903137"
+         height="113.24854"
+         width="167.35619"
+         id="rect815-2"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.56300002;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.12600006, 0.56300004000000003;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+      <rect
+         ry="7.445024"
+         rx="7.445024"
+         y="17.453594"
+         x="273.05484"
+         height="113.24854"
+         width="167.35619"
+         id="rect815-7"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.56300002;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.12600006, 0.56300004000000003;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+    </g>
+  </g>
+</svg>

tubearchivist/static/img/icon-listview.svg

@@ -0,0 +1,122 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="2000"
+   height="2000"
+   viewBox="0 0 529.16666 529.16735"
+   version="1.1"
+   id="svg8"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Listview.svg">
+  <defs
+     id="defs2" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.42053519"
+     inkscape:cx="851.82064"
+     inkscape:cy="1105.7974"
+     inkscape:document-units="mm"
+     inkscape:current-layer="g873"
+     showgrid="false"
+     units="px"
+     showguides="true"
+     inkscape:guide-bbox="true"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1">
+    <sodipodi:guide
+       position="247.25932,291.92959"
+       orientation="1,0"
+       id="guide853"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="337.22901,167.98535"
+       orientation="0,1"
+       id="guide855"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="266.76325,305.4565"
+       orientation="0,1"
+       id="guide857"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="257.79774,279.50371"
+       orientation="0,1"
+       id="guide861"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="22.413775,336.67894"
+       orientation="1,0"
+       id="guide926"
+       inkscape:locked="false" />
+    <sodipodi:guide
+       position="503.71355,217.50031"
+       orientation="1,0"
+       id="guide928"
+       inkscape:locked="false" />
+  </sodipodi:namedview>
+  <metadata
+     id="metadata5">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,232.16736)">
+    <g
+       id="g873"
+       transform="matrix(1.3431799,0,0,1.3431799,-84.854433,26.13855)">
+      <rect
+         ry="7.445024"
+         rx="7.445024"
+         y="-121.34892"
+         x="79.944702"
+         height="70.107315"
+         width="358.24551"
+         id="rect815"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.64810181;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.29620369, 0.64810185;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+      <rect
+         ry="7.4450235"
+         rx="7.4450235"
+         y="-31.167784"
+         x="79.861153"
+         height="70.107315"
+         width="358.32907"
+         id="rect815-20"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.64817739;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.29635485, 0.64817743;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+      <rect
+         ry="7.4450235"
+         rx="7.4450231"
+         y="60.024326"
+         x="79.908524"
+         height="70.106117"
+         width="358.28171"
+         id="rect815-8"
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.64812905;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:1.29625813, 0.64812907;stroke-dashoffset:0;stroke-opacity:0.22508042;paint-order:markers fill stroke" />
+    </g>
+  </g>
+</svg>

tubearchivist/static/img/icon-star-empty.svg

@@ -0,0 +1,65 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="1.1.1 (3bf5ae0d25, 2021-09-20)"
+   sodipodi:docname="icon-star-empty.svg"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="2.4005076"
+     inkscape:cx="40.40812"
+     inkscape:cy="211.20533"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="3840"
+     inkscape:window-height="2112"
+     inkscape:window-x="0"
+     inkscape:window-y="48"
+     inkscape:window-maximized="1"
+     inkscape:pagecheckerboard="0" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       id="path1255"
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       inkscape:transform-center-y="-6.4703827"
+       d="M 250 21.158203 L 189.78906 194.37891 L 6.4375 198.11523 L 152.57617 308.9082 L 99.470703 484.43945 L 250 379.69141 L 400.5293 484.43945 L 347.42383 308.9082 L 493.5625 198.11523 L 310.21094 194.37891 L 250 21.158203 z M 250 96.408203 L 291.69141 216.34766 L 418.64453 218.93555 L 317.45703 295.65039 L 354.22852 417.18945 L 250 344.66211 L 145.77148 417.18945 L 182.54297 295.65039 L 81.355469 218.93555 L 208.30859 216.34766 L 250 96.408203 z "
+       transform="matrix(0.26458394,0,0,0.26458394,0,164.70749)" />
+  </g>
+</svg>

tubearchivist/static/img/icon-star-full.svg

@@ -0,0 +1,74 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_star.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0105705"
+     inkscape:cx="61.891881"
+     inkscape:cy="148.25167"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       sodipodi:type="star"
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       id="path1255"
+       sodipodi:sides="5"
+       sodipodi:cx="66.145981"
+       sodipodi:cy="237.32387"
+       sodipodi:r1="67.758904"
+       sodipodi:r2="27.103561"
+       sodipodi:arg1="-1.5707963"
+       sodipodi:arg2="-0.9424778"
+       inkscape:flatsided="false"
+       inkscape:rounded="-3.46945e-18"
+       inkscape:randomized="0"
+       d="m 66.145983,169.56496 15.931071,45.83167 48.511476,0.98859 L 91.923,245.69933 105.97366,292.14197 66.145981,264.42743 26.318295,292.14197 40.368962,245.69933 1.7034347,216.38521 50.214907,215.39663 Z"
+       inkscape:transform-center-y="-6.4703827" />
+  </g>
+</svg>

tubearchivist/static/img/icon-star-half.svg

@@ -0,0 +1,66 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="1.1.1 (3bf5ae0d25, 2021-09-20)"
+   sodipodi:docname="icon-star-half.svg"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0105705"
+     inkscape:cx="44.034533"
+     inkscape:cy="168.22181"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="3840"
+     inkscape:window-height="2078"
+     inkscape:window-x="0"
+     inkscape:window-y="82"
+     inkscape:window-maximized="1"
+     inkscape:pagecheckerboard="0" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       id="path1255"
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       inkscape:transform-center-x="1.1220981e-06"
+       inkscape:transform-center-y="-6.4703827"
+       d="M 250 21.158203 L 189.78906 194.37891 L 6.4375 198.11523 L 152.57617 308.9082 L 99.470703 484.43945 L 250 379.69141 L 400.5293 484.43945 L 347.42383 308.9082 L 493.5625 198.11523 L 310.21094 194.37891 L 250 21.158203 z M 250 96.408203 L 291.69141 216.34766 L 418.64453 218.93555 L 317.45703 295.65039 L 354.22852 417.18945 L 250 344.66211 L 250 96.408203 z "
+       transform="matrix(0.26458394,0,0,0.26458394,0,164.70749)" />
+  </g>
+</svg>

tubearchivist/static/img/icon-stop.svg

@@ -0,0 +1,67 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_stop.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0105705"
+     inkscape:cx="43.182711"
+     inkscape:cy="168.09972"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <rect
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       id="rect836"
+       width="118.86465"
+       height="118.86465"
+       x="6.7136617"
+       y="171.42116"
+       rx="10.00003"
+       ry="10.00003" />
+  </g>
+</svg>

tubearchivist/static/progress.js

@@ -15,9 +15,13 @@ function checkMessage() {
     req.open('GET', '/downloads/progress', true);
     req.onload = function() {
         var dlProgress = req.response;
+        // var dlStatus = dlProgress['status'];
         if (dlProgress['status']) {
             buildDownloadMessage(dlProgress);
             handleInterval();
+            // if (dlStatus == 'downloading') {
+            //     buildDownloadIcons();
+            // };
         };
     };
     req.send();
@@ -28,7 +32,7 @@ function handleInterval() {
     var watchDownload = setInterval(function() {
         var req = new XMLHttpRequest();
         req.responseType = 'json';
-        req.open('GET', '/downloads/progress', true);
+        req.open('GET', '/downloads/progress/', true);
         req.onload = function() {
             var dlProgress = req.response;
             if (dlProgress['status']) {
@@ -70,4 +74,33 @@ function buildDownloadMessage(dlProgress) {
     message.appendChild(title);
     message.appendChild(messageText);
     box.appendChild(message);
+    if (dlStatus == 'downloading' && dlLevel != 'error') {
+        box.appendChild(buildDownloadIcons());
+    };
 };
+
+
+// add dl control icons
+function buildDownloadIcons() {
+    var iconBox = document.createElement('div');
+    iconBox.classList = 'dl-control-icons';
+    // stop icon
+    var stopIcon = document.createElement('img');
+    stopIcon.setAttribute('id', "stop-icon");
+    stopIcon.setAttribute('title', "Stop Download Queue");
+    stopIcon.setAttribute('src', "/static/img/icon-stop.svg");
+    stopIcon.setAttribute('alt', "stop icon");
+    stopIcon.setAttribute('onclick', 'stopQueue()');
+    // kill icon
+    var killIcon = document.createElement('img');
+    killIcon.setAttribute('id', "kill-icon");
+    killIcon.setAttribute('title', "Kill Download Queue");
+    killIcon.setAttribute('src', "/static/img/icon-close.svg");
+    killIcon.setAttribute('alt', "kill icon");
+    killIcon.setAttribute('onclick', 'killQueue()');
+    // stich together
+    iconBox.appendChild(stopIcon);
+    iconBox.appendChild(killIcon);
+    
+    return iconBox
+}

tubearchivist/static/script.js

@@ -8,24 +8,6 @@ function sortChange(sortValue) {
     }, 500);
 }
 
-function hideWatched(hideValue) {
-    var payload = JSON.stringify({'hide_watched': hideValue});
-    sendPost(payload);
-    setTimeout(function(){
-        location.reload();
-        return false;
-    }, 500);
-}
-
-function showSubscribedOnly(showValue) {
-    var payload = JSON.stringify({'show_subed_only': showValue});
-    sendPost(payload);
-    setTimeout(function(){
-        location.reload();
-        return false;
-    }, 500);
-}
-
 function isWatched(youtube_id) {
     var payload = JSON.stringify({'watched': youtube_id});
     sendPost(payload);
@@ -33,16 +15,57 @@ function isWatched(youtube_id) {
     seenIcon.setAttribute('src', "/static/img/icon-seen.svg");
     seenIcon.setAttribute('alt', 'seen-icon');
     seenIcon.setAttribute('id', youtube_id);
+    seenIcon.setAttribute('title', "Mark as unwatched");
+    seenIcon.setAttribute('onclick', "isUnwatched(this.id)");
     seenIcon.classList = 'seen-icon';
     document.getElementById(youtube_id).replaceWith(seenIcon);
 }
 
+function isUnwatched(youtube_id) {
+    var payload = JSON.stringify({'un_watched': youtube_id});
+    sendPost(payload);
+    var unseenIcon = document.createElement('img');
+    unseenIcon.setAttribute('src', "/static/img/icon-unseen.svg");
+    unseenIcon.setAttribute('alt', 'unseen-icon');
+    unseenIcon.setAttribute('id', youtube_id);
+    unseenIcon.setAttribute('title', "Mark as watched");
+    unseenIcon.setAttribute('onclick', "isWatched(this.id)");
+    unseenIcon.classList = 'unseen-icon';
+    document.getElementById(youtube_id).replaceWith(unseenIcon);
+}
+
 function unsubscribe(channel_id) {
     var payload = JSON.stringify({'unsubscribe': channel_id});
     sendPost(payload);
     document.getElementById(channel_id).remove();
 }
 
+function changeView(image) {
+    var sourcePage = image.getAttribute("data-origin");
+    var newView = image.getAttribute("data-value");
+    var payload = JSON.stringify({'change_view': sourcePage + ":" + newView});
+    sendPost(payload);
+    setTimeout(function(){
+        location.reload();
+        return false;
+    }, 500);
+}
+
+function toggleCheckbox(checkbox) {
+    // pass checkbox id as key and checkbox.checked as value
+    var toggleId = checkbox.id;
+    var toggleVal = checkbox.checked;
+    var payloadDict = {};
+    payloadDict[toggleId] = toggleVal;
+    var payload = JSON.stringify(payloadDict);
+    sendPost(payload);
+    setTimeout(function(){
+        var currPage = window.location.pathname;
+        window.location.replace(currPage);
+        return false;
+    }, 500);
+}
+
 // download page buttons
 function rescanPending() {
     var payload = JSON.stringify({'rescan_pending': true});
@@ -79,6 +102,35 @@ function downloadNow(button) {
     }, 500);
 }
 
+function forgetIgnore(button) {
+    var youtube_id = button.getAttribute('data-id');
+    var payload = JSON.stringify({'forgetIgnore': youtube_id});
+    sendPost(payload);
+    document.getElementById("dl-" + youtube_id).remove();
+}
+
+function addSingle(button) {
+    var youtube_id = button.getAttribute('data-id');
+    var payload = JSON.stringify({'addSingle': youtube_id});
+    sendPost(payload);
+    document.getElementById("dl-" + youtube_id).remove();
+    setTimeout(function(){
+        handleInterval();
+    }, 500);
+}
+
+function stopQueue() {
+    var payload = JSON.stringify({'queue': 'stop'});
+    sendPost(payload);
+    document.getElementById('stop-icon').remove();
+}
+
+function killQueue() {
+    var payload = JSON.stringify({'queue': 'kill'});
+    sendPost(payload);
+    document.getElementById('kill-icon').remove();
+}
+
 // settings page buttons
 function manualImport() {
     var payload = JSON.stringify({'manual-import': true});
@@ -91,6 +143,17 @@ function manualImport() {
     toReplace.appendChild(message);
 }
 
+function reEmbed() {
+    var payload = JSON.stringify({'re-embed': true});
+    sendPost(payload);
+    // clear button
+    var message = document.createElement('p');
+    message.innerText = 'processing thumbnails';
+    var toReplace = document.getElementById('re-embed');
+    toReplace.innerHTML = '';
+    toReplace.appendChild(message);
+}
+
 function dbBackup() {
     var payload = JSON.stringify({'db-backup': true});
     sendPost(payload)
@@ -102,6 +165,62 @@ function dbBackup() {
     toReplace.appendChild(message);
 }
 
+function dbRestore() {
+    var payload = JSON.stringify({'db-restore': true});
+    sendPost(payload);
+    // clear button
+    var message = document.createElement('p');
+    message.innerText = 'restoring from backup';
+    var toReplace = document.getElementById('db-restore');
+    toReplace.innerHTML = '';
+    toReplace.appendChild(message);
+}
+
+function fsRescan() {
+    var payload = JSON.stringify({'fs-rescan': true});
+    sendPost(payload);
+    // clear button
+    var message = document.createElement('p');
+    message.innerText = 'File system scan in progress';
+    var toReplace = document.getElementById('fs-rescan');
+    toReplace.innerHTML = '';
+    toReplace.appendChild(message);
+}
+
+// delete from file system
+function deleteConfirm() {
+    to_show = document.getElementById("delete-button");
+    document.getElementById("delete-item").style.display = 'none';
+    to_show.style.display = "block";
+}
+
+function deleteVideo(button) {
+    var to_delete = button.getAttribute("data-id");
+    var to_redirect = button.getAttribute("data-redirect");
+    var payload = JSON.stringify({"delete-video": to_delete});
+    sendPost(payload);
+    setTimeout(function(){
+        var redirect = "/channel/" + to_redirect;
+        window.location.replace(redirect);
+        return false;
+    }, 1000);
+}
+
+function deleteChannel(button) {
+    var to_delete = button.getAttribute("data-id");
+    var payload = JSON.stringify({"delete-channel": to_delete});
+    sendPost(payload);
+    setTimeout(function(){
+        window.location.replace("/channel/");
+        return false;
+    }, 1000);
+}
+
+function cancelDelete() {
+    document.getElementById("delete-button").style.display = 'none';
+    document.getElementById("delete-item").style.display = 'block';
+}
+
 // player
 function createPlayer(button) {
     var mediaUrl = button.getAttribute('data-src');
@@ -122,6 +241,7 @@ function createPlayer(button) {
     videoPlayer.setAttribute('controls', true);
     videoPlayer.setAttribute('autoplay', true);
     videoPlayer.setAttribute('width', '100%');
+    videoPlayer.setAttribute('playsinline', true);
     videoPlayer.setAttribute('poster', mediaThumb);
     playerElement.appendChild(videoPlayer);
     // title bar
@@ -263,7 +383,7 @@ function showSearch() {
     } else {
         searchBox.style.display = "";
     }
-    var inputBox = document.getElementById('searchInput');
+    var inputBox = document.getElementById('id_searchInput');
     inputBox.focus();
 }
 

uwsgi.ini

@@ -1,8 +1,8 @@
 [uwsgi]
-; chdir = /app
-module=config.wsgi:application
-master=True
-pidfile=/tmp/project-master.pid
-vacuum=True
-max-requests=5000
-socket = :8080
+module = config.wsgi:application
+master = True
+pidfile = /tmp/project-master.pid
+vacuum = True
+max-requests = 5000
+socket = :8080
+buffer-size = 8192

version_check.py

@@ -1,17 +1,17 @@
 #!/usr/bin/env python
 """ check requirements.txt for outdated packages """
 
-import sys
 import pathlib
+import sys
 
 import requests
 
 
 class Requirements:
-    """ handle requirements.txt """
+    """handle requirements.txt"""
 
-    FILE_PATH = 'tubearchivist/requirements.txt'
-    LOCK = '/tmp/tubearchivist-requirements.lock'
+    FILE_PATH = "tubearchivist/requirements.txt"
+    LOCK = "/tmp/tubearchivist-requirements.lock"
 
     def __init__(self):
         self.exists = self.checked_today()
@@ -19,58 +19,57 @@ class Requirements:
         self.all_updates = False
 
     def checked_today(self):
-        """ skip requirements check when lock file exists """
+        """skip requirements check when lock file exists"""
         exists = pathlib.Path(self.LOCK).exists()
         return exists
 
     def look_for_updates(self):
-        """ look through requirements and check for updates """
+        """look through requirements and check for updates"""
         self.all_requirements = self.get_dependencies()
         self.all_updates = self.check_packages()
 
     def get_dependencies(self):
-        """ read out requirements.txt """
+        """read out requirements.txt"""
 
         all_requirements = []
-        with open(self.FILE_PATH, 'r', encoding='utf-8') as f:
+        with open(self.FILE_PATH, "r", encoding="utf-8") as f:
             dependencies = f.readlines()
 
         for dependency in dependencies:
-            package, version = dependency.split('==')
+            package, version = dependency.split("==")
             all_requirements.append((package, version.strip()))
 
-        all_requirements.sort(key = lambda x: x[0].lower())
+        all_requirements.sort(key=lambda x: x[0].lower())
 
         return all_requirements
 
     def check_packages(self):
-        """ compare installed with remote version """
+        """compare installed with remote version"""
 
         total = len(self.all_requirements)
-        print(f'checking versions for {total} packages...')
+        print(f"checking versions for {total} packages...")
 
         all_updates = {}
 
         for dependency in self.all_requirements:
             package, version_installed = dependency
-            url = f'https://pypi.org/pypi/{package}/json'
+            url = f"https://pypi.org/pypi/{package}/json"
             response = requests.get(url).json()
-            version_remote = response['info']['version']
-            homepage = response['info']['home_page']
+            version_remote = response["info"]["version"]
+            homepage = response["info"]["home_page"]
             if version_remote != version_installed:
                 to_update = {
-                    package: {
-                        "from": version_installed,
-                        "to": version_remote
-                    }
+                    package: {"from": version_installed, "to": version_remote}
                 }
                 all_updates.update(to_update)
-                message = (f'update {package} {version_installed}' +
-                           f'==> {version_remote}\n    {homepage}')
+                message = (
+                    f"update {package} {version_installed}"
+                    + f"==> {version_remote}\n    {homepage}"
+                )
                 print(message)
 
         if not all_updates:
-            print('no updates found')
+            print("no updates found")
 
         # remember that
         pathlib.Path(self.LOCK).touch()
@@ -78,7 +77,7 @@ class Requirements:
         return all_updates
 
     def apply_updates(self):
-        """ update requirements.txt file with new versions """
+        """update requirements.txt file with new versions"""
 
         to_write = []
 
@@ -86,32 +85,33 @@ class Requirements:
             package, old_version = requirement
 
             if package in self.all_updates.keys():
-                package_version = self.all_updates[package]['to']
+                package_version = self.all_updates[package]["to"]
             else:
                 package_version = old_version
 
-            to_write.append(f'{package}=={package_version}\n')
+            to_write.append(f"{package}=={package_version}\n")
 
-        with open(self.FILE_PATH, 'w', encoding='utf-8') as f:
+        with open(self.FILE_PATH, "w", encoding="utf-8") as f:
             f.writelines(to_write)
 
-        print('requirements.txt updates')
+        print("requirements.txt updates")
 
 
 def main():
-    """ main to check for updates """
+    """main to check for updates"""
     handler = Requirements()
     if handler.exists:
         return
 
     handler.look_for_updates()
     if handler.all_updates:
-        input_response = input('\nupdate requirements.txt? [y/n] ')
-        if input_response == 'y':
+        input_response = input("\nupdate requirements.txt? [y/n] ")
+        if input_response == "y":
             handler.apply_updates()
         else:
-            print('cancle update...')
+            print("cancel update...")
             sys.exit(1)
 
+
 if __name__ == "__main__":
     main()