Compare commits
6 Commits
security/h
...
3795d9e4ff
| Author | SHA1 | Date | |
|---|---|---|---|
3795d9e4ff
|
|||
|
3cf221a1ed
|
|||
|
13a0e6ceed
|
|||
|
e8e2aa93d6
|
|||
|
8403e30b3a
|
|||
|
f0649be5de
|
381
README.md
381
README.md
@@ -1,313 +1,180 @@
|
|||||||
# yt-local
|
# yt-local
|
||||||
|
|
||||||
[](https://www.gnu.org/licenses/agpl-3.0)
|
Fork of [youtube-local](https://github.com/user234683/youtube-local)
|
||||||
[](https://www.python.org/downloads/)
|
|
||||||
[](https://github.com/user234683/youtube-local)
|
|
||||||
|
|
||||||
A privacy-focused, browser-based YouTube client that routes requests through Tor for anonymous viewing—**without compromising on speed or features**.
|
yt-local is a browser-based client written in Python for watching YouTube anonymously and without the lag of the slow page used by YouTube. One of the primary features is that all requests are routed through Tor, except for the video file at googlevideo.com. This is analogous to what HookTube (defunct) and Invidious do, except that you do not have to trust a third-party to respect your privacy. The assumption here is that Google won't put the effort in to incorporate the video file requests into their tracking, as it's not worth pursuing the incredibly small number of users who care about privacy (Tor video routing is also provided as an option). Tor has high latency, so this will not be as fast network-wise as regular YouTube. However, using Tor is optional; when not routing through Tor, video pages may load faster than they do with YouTube's page depending on your browser.
|
||||||
|
|
||||||
[Features](#features) • [Install](#install) • [Usage](#usage) • [Screenshots](#screenshots)
|
The YouTube API is not used, so no keys or anything are needed. It uses the same requests as the YouTube webpage.
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
> [!NOTE]
|
|
||||||
> How it works: yt-local mirrors YouTube's web requests (using the same Invidious/InnerTube endpoints as yt-dlp and Invidious) but strips JavaScript and serves a lightweight HTML frontend. No API keys needed.
|
|
||||||
|
|
||||||
## Overview
|
|
||||||
|
|
||||||
yt-local is a lightweight, self-hosted YouTube client written in Python that gives you:
|
|
||||||
|
|
||||||
- **Privacy-first**: All requests route through Tor by default (video optional), keeping you anonymous.
|
|
||||||
- **Fast page loads**: No lazy-loading, no layout reflows, instant comment rendering.
|
|
||||||
- **Full control**: Customize subtitles, related videos, comments, and playback speed.
|
|
||||||
- **High quality**: Supports all YouTube video qualities (144p–2160p) via DASH muxing.
|
|
||||||
- **Zero ads**: Clean interface, no tracking, no sponsored content.
|
|
||||||
- **Self-hosted**: You control the instance—no third-party trust required.
|
|
||||||
|
|
||||||
## Features
|
|
||||||
|
|
||||||
| Category | Features |
|
|
||||||
|---------------|----------------------------------------------------------------------------------------|
|
|
||||||
| Core | Search, channels, playlists, watch pages, comments, subtitles (auto/manual) |
|
|
||||||
| Privacy | Optional Tor routing (including video), automatic circuit rotation on 429 errors |
|
|
||||||
| Local | Local playlists (durable against YouTube deletions), thumbnail caching |
|
|
||||||
| UI | 3 themes (Light/Gray/Dark), theater mode, custom font selection |
|
|
||||||
| Config | Fine-grained settings: subtitle mode, comment visibility, sponsorblock integration |
|
|
||||||
| Performance | No JavaScript required, instant page rendering, rate limiting with exponential backoff |
|
|
||||||
| Subscriptions | Import from YouTube Takeout (CSV/JSON), tag organization, mute channels |
|
|
||||||
|
|
||||||
### Advanced Capabilities
|
|
||||||
|
|
||||||
- SponsorBlock integration — skip sponsored segments automatically
|
|
||||||
- Custom video speeds — 0.25x to 4x playback rate
|
|
||||||
- Video transcripts — accessible via transcript button
|
|
||||||
- Video quality muxing — combine separate video/audio streams for non-360p/720p resolutions
|
|
||||||
- Tor circuit rotation — automatic new identity on rate limiting (429)
|
|
||||||
- File downloading — download videos/audio (disabled by default, configurable)
|
|
||||||
|
|
||||||
## Screenshots
|
## Screenshots
|
||||||
|
|
||||||
| Light Theme | Gray Theme | Dark Theme |
|
[Light theme](https://pic.infini.fr/l7WINjzS/0Ru6MrhA.png)
|
||||||
|:-----------------------------------------------------:|:----------------------------------------------------:|:----------------------------------------------------:|
|
|
||||||
|  |  |  |
|
|
||||||
|
|
||||||
| Channel View | Playlist View |
|
[Gray theme](https://pic.infini.fr/znnQXWNc/hL78CRzo.png)
|
||||||
|:-------------------------------------------------------:|:---------------------:|
|
|
||||||
|  | *(similar structure)* |
|
|
||||||
|
|
||||||
---
|
[Dark theme](https://pic.infini.fr/iXwFtTWv/mt2kS5bv.png)
|
||||||
|
|
||||||
## Install
|
[Channel](https://pic.infini.fr/JsenWVYe/SbdIQlS6.png)
|
||||||
|
|
||||||
|
## Features
|
||||||
|
* Standard pages of YouTube: search, channels, playlists
|
||||||
|
* Anonymity from Google's tracking by routing requests through Tor
|
||||||
|
* Local playlists: These solve the two problems with creating playlists on YouTube: (1) they're datamined and (2) videos frequently get deleted by YouTube and lost from the playlist, making it very difficult to find a reupload as the title of the deleted video is not displayed.
|
||||||
|
* Themes: Light, Gray, and Dark
|
||||||
|
* Subtitles
|
||||||
|
* Easily download videos or their audio. (Disabled by default)
|
||||||
|
* No ads
|
||||||
|
* View comments
|
||||||
|
* JavaScript not required
|
||||||
|
* Theater and non-theater mode
|
||||||
|
* Subscriptions that are independent from YouTube
|
||||||
|
* Can import subscriptions from YouTube
|
||||||
|
* Works by checking channels individually
|
||||||
|
* Can be set to automatically check channels.
|
||||||
|
* For efficiency of requests, frequency of checking is based on how quickly channel posts videos
|
||||||
|
* Can mute channels, so as to have a way to "soft" unsubscribe. Muted channels won't be checked automatically or when using the "Check all" button. Videos from these channels will be hidden.
|
||||||
|
* Can tag subscriptions to organize them or check specific tags
|
||||||
|
* Fast page
|
||||||
|
* No distracting/slow layout rearrangement
|
||||||
|
* No lazy-loading of comments; they are ready instantly.
|
||||||
|
* Settings allow fine-tuned control over when/how comments or related videos are shown:
|
||||||
|
1. Shown by default, with click to hide
|
||||||
|
2. Hidden by default, with click to show
|
||||||
|
3. Never shown
|
||||||
|
* Optionally skip sponsored segments using [SponsorBlock](https://github.com/ajayyy/SponsorBlock)'s API
|
||||||
|
* Custom video speeds
|
||||||
|
* Video transcript
|
||||||
|
* Supports all available video qualities: 144p through 2160p
|
||||||
|
|
||||||
|
## Planned features
|
||||||
|
- [ ] Putting videos from subscriptions or local playlists into the related videos
|
||||||
|
- [x] Information about video (geographic regions, region of Tor exit node, etc)
|
||||||
|
- [ ] Ability to delete playlists
|
||||||
|
- [ ] Auto-saving of local playlist videos
|
||||||
|
- [ ] Import youtube playlist into a local playlist
|
||||||
|
- [ ] Rearrange items of local playlist
|
||||||
|
- [x] Video qualities other than 360p and 720p by muxing video and audio
|
||||||
|
- [x] Indicate if comments are disabled
|
||||||
|
- [x] Indicate how many comments a video has
|
||||||
|
- [ ] Featured channels page
|
||||||
|
- [ ] Channel comments
|
||||||
|
- [x] Video transcript
|
||||||
|
- [x] Automatic Tor circuit change when blocked
|
||||||
|
- [x] Support &t parameter
|
||||||
|
- [ ] Subscriptions: Option to mark what has been watched
|
||||||
|
- [ ] Subscriptions: Option to filter videos based on keywords in title or description
|
||||||
|
- [ ] Subscriptions: Delete old entries and thumbnails
|
||||||
|
- [ ] Support for more sites, such as Vimeo, Dailymotion, LBRY, etc.
|
||||||
|
|
||||||
|
## Installing
|
||||||
|
|
||||||
### Windows
|
### Windows
|
||||||
|
|
||||||
1. Download the latest [release ZIP](https://github.com/user234683/yt-local/releases)
|
Download the zip file under the Releases page. Unzip it anywhere you choose.
|
||||||
2. Extract to any folder
|
|
||||||
3. Run `run.bat` to start
|
|
||||||
|
|
||||||
### GNU/Linux / macOS
|
### GNU+Linux/MacOS
|
||||||
|
|
||||||
```bash
|
Download the tarball under the Releases page and extract it. `cd` into the directory and run
|
||||||
# 1. Clone or extract the release
|
|
||||||
git clone https://github.com/user234683/yt-local.git
|
|
||||||
cd yt-local
|
|
||||||
|
|
||||||
# 2. Create and activate virtual environment
|
1. `cd yt-local`
|
||||||
python3 -m venv venv
|
2. `virtualenv -p python3 venv`
|
||||||
source venv/bin/activate # or `venv\Scripts\activate` on Windows
|
3. `source venv/bin/activate`
|
||||||
|
4. `pip install -r requirements.txt`
|
||||||
|
5. `python server.py`
|
||||||
|
|
||||||
# 3. Install dependencies
|
|
||||||
pip install -r requirements.txt
|
|
||||||
|
|
||||||
# 4. Run the server
|
**Note**: If pip isn't installed, first try installing it from your package manager. Make sure you install pip for python 3. For example, the package you need on debian is python3-pip rather than python-pip. If your package manager doesn't provide it, try to install it according to [this answer](https://unix.stackexchange.com/a/182467), but make sure you run `python3 get-pip.py` instead of `python get-pip.py`
|
||||||
python3 server.py
|
|
||||||
```
|
|
||||||
|
|
||||||
> [!TIP]
|
|
||||||
> If `pip` isn't installed, use your distro's package manager (e.g., `sudo apt install python3-pip` on Debian/Ubuntu).
|
|
||||||
|
|
||||||
### Portable Mode
|
|
||||||
|
|
||||||
To keep settings and data in the same directory as the app:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
# Create an empty settings.txt in the project root
|
|
||||||
touch settings.txt
|
|
||||||
python3 server.py
|
|
||||||
# Data now stored in ./data/ instead of ~/.yt-local/
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Usage
|
## Usage
|
||||||
|
|
||||||
### Basic Access
|
Firstly, if you wish to run this in portable mode, create the empty file "settings.txt" in the program's main directory. If the file is there, settings and data will be stored in the same directory as the program. Otherwise, settings and data will be stored in `C:\Users\[your username]\.yt-local` on Windows and `~/.yt-local` on GNU+Linux/MacOS.
|
||||||
|
|
||||||
1. Start the server:
|
To run the program on windows, open `run.bat`. On GNU+Linux/MacOS, run `python3 server.py`.
|
||||||
|
|
||||||
```bash
|
Access youtube URLs by prefixing them with `http://localhost:9010/`.
|
||||||
python3 server.py
|
For instance, `http://localhost:9010/https://www.youtube.com/watch?v=vBgulDeV2RU`
|
||||||
# Server runs on http://127.0.0.1:9010 (configurable in /settings)
|
You can use an addon such as Redirector ([Firefox](https://addons.mozilla.org/en-US/firefox/addon/redirector/)|[Chrome](https://chrome.google.com/webstore/detail/redirector/ocgpenflpmgnfapjedencafcfakcekcd)) to automatically redirect YouTube URLs to yt-local. I use the include pattern `^(https?://(?:[a-zA-Z0-9_-]*\.)?(?:youtube\.com|youtu\.be|youtube-nocookie\.com)/.*)` and redirect pattern `http://localhost:9010/$1` (Make sure you're using regular expression mode).
|
||||||
```
|
|
||||||
|
|
||||||
2. Access YouTube via proxy:
|
If you want embeds on web to also redirect to yt-local, make sure "Iframes" is checked under advanced options in your redirector rule. Check test `http://localhost:9010/youtube.com/embed/vBgulDeV2RU`
|
||||||
|
|
||||||
```bash
|
yt-local can be added as a search engine in firefox to make searching more convenient. See [here](https://support.mozilla.org/en-US/kb/add-or-remove-search-engine-firefox) for information on firefox search plugins.
|
||||||
http://localhost:9010/https://www.youtube.com/watch?v=vBgulDeV2RU
|
|
||||||
```
|
|
||||||
|
|
||||||
All YouTube URLs must be prefixed with `http://localhost:9010/https://`.
|
### Using Tor
|
||||||
|
|
||||||
3. (Optional) Use Redirector to auto-redirect YouTube URLs:
|
In the settings page, set "Route Tor" to "On, except video" (the second option). Be sure to save the settings.
|
||||||
|
|
||||||
- **Firefox**: [Redirector addon](https://addons.mozilla.org/firefox/addon/redirector/)
|
Ensure Tor is listening for Socks5 connections on port 9150. A simple way to accomplish this is by opening the Tor Browser Bundle and leaving it open. However, you will not be accessing the program (at https://localhost:8080) through the Tor Browser. You will use your regular browser for that. Rather, this is just a quick way to give the program access to Tor routing.
|
||||||
- **Chrome**: [Redirector addon](https://chrome.google.com/webstore/detail/redirector/ocgpenflpmgnfapjedencafcfakcekcd)
|
|
||||||
- **Pattern**: `^(https?://(?:[a-zA-Z0-9_-]*\.)?(?:youtube\.com|youtu\.be|youtube-nocookie\.com)/.*)`
|
|
||||||
- **Redirect to**: `http://localhost:9010/$1`
|
|
||||||
|
|
||||||
> [!NOTE]
|
### Standalone Tor
|
||||||
> To use embeds on web pages, make sure "Iframes" is checked under advanced options in your redirector rule.
|
|
||||||
|
|
||||||
### Tor Routing
|
If you don't want to waste system resources leaving the Tor Browser open in addition to your regular browser, you can configure standalone Tor to run instead using the following instructions.
|
||||||
|
|
||||||
> [!IMPORTANT]
|
For Windows, to make standalone Tor run at startup, press Windows Key + R and type `shell:startup` to open the Startup folder. Create a new shortcut there. For the command of the shortcut, enter `"C:\[path-to-Tor-Browser-directory]\Tor\tor.exe" SOCKSPort 9150 ControlPort 9151`. You can then launch this shortcut to start it. Alternatively, if something isn't working, to see what's wrong, open `cmd.exe` and go to the directory `C:\[path-to-Tor-Browser-directory]\Tor`. Then run `tor SOCKSPort 9150 ControlPort 9151 | more`. The `more` part at the end is just to make sure any errors are displayed, to fix a bug in Windows cmd where tor doesn't display any output. You can stop tor in the task manager.
|
||||||
> Recommended for privacy. In `/settings`, set **Route Tor** to `"On, except video"` (or `"On, including video"`), then save.
|
|
||||||
|
|
||||||
#### Running Tor
|
For Debian/Ubuntu, you can `sudo apt install tor` to install the command line version of Tor, and then run `sudo systemctl start tor` to run it as a background service that will get started during boot as well. However, Tor on the command line uses the port `9050` by default (rather than the 9150 used by the Tor Browser). So you will need to change `Tor port` to 9050 and `Tor control port` to `9051` in yt-local settings page. Additionally, you will need to enable the Tor control port by uncommenting the line `ControlPort 9051`, and setting `CookieAuthentication` to 0 in `/etc/tor/torrc`. If no Tor package is available for your distro, you can configure the `tor` binary located at `./Browser/TorBrowser/Tor/tor` inside the Tor Browser installation location to run at start time, or create a service to do it.
|
||||||
|
|
||||||
Option A: Tor Browser (easiest)
|
### Tor video routing
|
||||||
|
|
||||||
- Launch Tor Browser and leave it running
|
If you wish to route the video through Tor, set "Route Tor" to "On, including video". Because this is bandwidth-intensive, you are strongly encouraged to donate to the [consortium of Tor node operators](https://torservers.net/donate.html). For instance, donations to [NoiseTor](https://noisetor.net/) go straight towards funding nodes. Using their numbers for bandwidth costs, together with an average of 485 kbit/sec for a diverse sample of videos, and assuming n hours of video watched per day, gives $0.03n/month. A $1/month donation will be a very generous amount to not only offset losses, but help keep the network healthy.
|
||||||
- yt-local uses port `9150` (Tor Browser default)
|
|
||||||
|
|
||||||
Option B: Standalone Tor
|
In general, Tor video routing will be slower (for instance, moving around in the video is quite slow). I've never seen any signs that watch history in yt-local affects on-site Youtube recommendations. It's likely that requests to googlevideo are logged for some period of time, but are not integrated into Youtube's larger advertisement/recommendation systems, since those presumably depend more heavily on in-page tracking through Javascript rather than CDN requests to googlevideo.
|
||||||
|
|
||||||
```bash
|
### Importing subscriptions
|
||||||
# Linux (Debian/Ubuntu)
|
|
||||||
sudo apt install tor
|
|
||||||
sudo systemctl enable --now tor
|
|
||||||
|
|
||||||
# Configure yt-local ports (if using default Tor ports):
|
1. Go to the [Google takeout manager](https://takeout.google.com/takeout/custom/youtube).
|
||||||
# Tor port: 9150
|
2. Log in if asked.
|
||||||
# Tor control port: 9151
|
3. Click on "All data included", then on "Deselect all", then select only "subscriptions" and click "OK".
|
||||||
```
|
4. Click on "Next step" and then on "Create export".
|
||||||
|
5. Click on the "Download" button after it appears.
|
||||||
> [!WARNING]
|
6. From the downloaded takeout zip extract the .csv file. It is usually located under `YouTube and YouTube Music/subscriptions/subscriptions.csv`
|
||||||
> Video over Tor is bandwidth-intensive. Consider donating to [Tor node operators](https://torservers.net/donate.html) to sustain the network.
|
7. Go to the subscriptions manager in yt-local. In the import area, select your .csv file, then press import.
|
||||||
|
|
||||||
### Import Subscriptions
|
|
||||||
|
|
||||||
1. Go to [Google Takeout](https://takeout.google.com/takeout/custom/youtube)
|
|
||||||
2. Deselect all → select only **Subscriptions** → create export
|
|
||||||
3. Download and extract `subscriptions.csv` (path: `YouTube and YouTube Music/subscriptions/subscriptions.csv`)
|
|
||||||
4. In yt-local: **Subscriptions** → **Import** → upload CSV
|
|
||||||
|
|
||||||
> [!IMPORTANT]
|
|
||||||
> The CSV file must contain columns: `channel_id,channel_name,channel_url`
|
|
||||||
|
|
||||||
## Supported formats
|
|
||||||
|
|
||||||
|
Supported subscriptions import formats:
|
||||||
|
- NewPipe subscriptions export JSON
|
||||||
- Google Takeout CSV
|
- Google Takeout CSV
|
||||||
- Google Takeout JSON (legacy)
|
- Old Google Takeout JSON
|
||||||
- NewPipe JSON export
|
- OPML format from now-removed YouTube subscriptions manager
|
||||||
- OPML (from YouTube's old subscription manager)
|
|
||||||
|
|
||||||
---
|
## Contributing
|
||||||
|
|
||||||
## Configuration
|
Pull requests and issues are welcome
|
||||||
|
|
||||||
Visit `http://localhost:9010/settings` to configure:
|
For coding guidelines and an overview of the software architecture, see the [HACKING.md](docs/HACKING.md) file.
|
||||||
|
|
||||||
| Setting | Description |
|
## GPG public KEY
|
||||||
|--------------------|-------------------------------------------------|
|
|
||||||
| Route Tor | Off / On (except video) / On (including video) |
|
|
||||||
| Default subtitles | Off / Manual only / Auto + Manual |
|
|
||||||
| Comments mode | Shown by default / Hidden by default / Never |
|
|
||||||
| Related videos | Same options as comments |
|
|
||||||
| Theme | Light / Gray / Dark |
|
|
||||||
| Font | Browser default / Serif / Sans-serif |
|
|
||||||
| Default resolution | Auto / 144p–2160p |
|
|
||||||
| SponsorBlock | Enable Sponsored segments skipping |
|
|
||||||
| Proxy images | Route thumbnails through yt-local (for privacy) |
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Troubleshooting
|
|
||||||
|
|
||||||
| Issue | Solution |
|
|
||||||
|------------------------------|----------------------------------------------------------------------------------------------|
|
|
||||||
| Port already in use | Change `port_number` in `/settings` or kill existing process: `pkill -f "python3 server.py"` |
|
|
||||||
| 429 Too Many Requests | Enable Tor routing for automatic IP rotation, or wait 5-10 minutes |
|
|
||||||
| Failed to connect to Tor | Verify Tor is running: `tor --version` or launch Tor Browser |
|
|
||||||
| Subscriptions not importing | Ensure CSV has columns: `channel_id,channel_name,channel_url` |
|
|
||||||
| Settings persist across runs | Check `~/.yt-local/settings.txt` (non-portable) or `./settings.txt` (portable) |
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Development
|
|
||||||
|
|
||||||
### Running Tests
|
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
source venv/bin/activate # if not already in venv
|
72CFB264DFC43F63E098F926E607CE7149F4D71C
|
||||||
make test
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### Project Structure
|
## Public instances
|
||||||
|
|
||||||
```bash
|
yt-local is not made to work in public mode, however there is an instance of yt-local in public mode but with less features
|
||||||
yt-local/
|
|
||||||
├── youtube/ # Core application logic
|
|
||||||
│ ├── __init__.py # Flask app entry point
|
|
||||||
│ ├── util.py # HTTP utilities, Tor manager, fetch_url
|
|
||||||
│ ├── watch.py # Video/playlist page handlers
|
|
||||||
│ ├── channel.py # Channel page handlers
|
|
||||||
│ ├── playlist.py # Playlist handlers
|
|
||||||
│ ├── search.py # Search handlers
|
|
||||||
│ ├── comments.py # Comment extraction/rendering
|
|
||||||
│ ├── subscriptions.py # Subscription management + SQLite
|
|
||||||
│ ├── local_playlist.py # Local playlist CRUD
|
|
||||||
│ ├── proto.py # YouTube protobuf token generation
|
|
||||||
│ ├── yt_data_extract/ # Polymer JSON parsing abstractions
|
|
||||||
│ └── hls_cache.py # HLS audio/video streaming proxy
|
|
||||||
├── templates/ # Jinja2 HTML templates
|
|
||||||
├── static/ # CSS/JS assets
|
|
||||||
├── translations/ # i18n files (Babel)
|
|
||||||
├── tests/ # pytest test suite
|
|
||||||
├── server.py # WSGI entry point
|
|
||||||
├── settings.py # Settings parser + admin page
|
|
||||||
├── generate_release.py # Windows release builder
|
|
||||||
└── manage_translations.py # i18n maintenance script
|
|
||||||
```
|
|
||||||
|
|
||||||
> [!NOTE]
|
- <https://m.fridu.us/https://youtube.com>
|
||||||
> For detailed architecture guidance, see [`docs/HACKING.md`](docs/HACKING.md).
|
|
||||||
|
|
||||||
### Contributing
|
|
||||||
|
|
||||||
Contributions welcome! Please:
|
|
||||||
|
|
||||||
1. Read [`docs/HACKING.md`](docs/HACKING.md) for coding guidelines
|
|
||||||
2. Follow [PEP 8](https://peps.python.org/pep-0008/) style (use `ruff format`)
|
|
||||||
3. Run tests before submitting: `pytest`
|
|
||||||
4. Ensure no security issues: `bandit -r .`
|
|
||||||
5. Update docs for new features
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Security Notes
|
|
||||||
|
|
||||||
- **No API keys required** — uses same endpoints as public YouTube web interface
|
|
||||||
- **Tor is optional** — disable in `/settings` if you prefer performance over anonymity
|
|
||||||
- **Rate limiting handled** — exponential backoff (max 5 retries) with automatic Tor circuit rotation
|
|
||||||
- **Path traversal protected** — user input validated against regex whitelists (CWE-22)
|
|
||||||
- **Subprocess calls secure** — build scripts use `subprocess.run([...])` instead of shell (CWE-78)
|
|
||||||
|
|
||||||
> [!NOTE]
|
|
||||||
> GPG key for release verification: `72CFB264DFC43F63E098F926E607CE7149F4D71C`
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Public Instances
|
|
||||||
|
|
||||||
yt-local is designed for self-hosting.
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Donate
|
|
||||||
|
|
||||||
This project is 100% free and open-source. If you'd like to support development:
|
|
||||||
|
|
||||||
- **Bitcoin**: `1JrC3iqs3PP5Ge1m1vu7WE8LEf4S85eo7y`
|
|
||||||
- **Tor node donation**: https://torservers.net/donate
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## License
|
## License
|
||||||
|
|
||||||
GNU Affero General Public License v3.0+
|
This project is licensed under the GNU Affero General Public License v3 (GNU AGPLv3) or any later version.
|
||||||
|
|
||||||
See [`LICENSE`](LICENSE) for full text.
|
Permission is hereby granted to the youtube-dl project at [https://github.com/ytdl-org/youtube-dl](https://github.com/ytdl-org/youtube-dl) to relicense any portion of this software under the Unlicense, public domain, or whichever license is in use by youtube-dl at the time of relicensing, for the purpose of inclusion of said portion into youtube-dl. Relicensing permission is not granted for any purpose outside of direct inclusion into the [official repository](https://github.com/ytdl-org/youtube-dl) of youtube-dl. If inclusion happens during the process of a pull-request, relicensing happens at the moment the pull request is merged into youtube-dl; until that moment, any cloned repositories of youtube-dl which make use of this software are subject to the terms of the GNU AGPLv3.
|
||||||
|
|
||||||
### Exception for youtube-dl
|
## Donate
|
||||||
|
This project is completely free/Libre and will always be.
|
||||||
|
|
||||||
Permission is granted to relicense code portions into youtube-dl's license (currently GPL) for direct inclusion into the [official youtube-dl repository](https://github.com/ytdl-org/youtube-dl). This exception **does not apply** to forks or other uses—those remain under AGPLv3.
|
#### Crypto:
|
||||||
|
- **Bitcoin**: `1JrC3iqs3PP5Ge1m1vu7WE8LEf4S85eo7y`
|
||||||
|
|
||||||
---
|
## Similar projects
|
||||||
|
- [invidious](https://github.com/iv-org/invidious) Similar to this project, but also allows it to be hosted as a server to serve many users
|
||||||
## Similar Projects
|
- [Yotter](https://github.com/ytorg/Yotter) Similar to this project and to invidious. Also supports Twitter
|
||||||
|
- [FreeTube](https://github.com/FreeTubeApp/FreeTube) (Similar to this project, but is an electron app outside the browser)
|
||||||
| Project | Type | Notes |
|
- [youtube-local](https://github.com/user234683/youtube-local) first project on which yt-local is based
|
||||||
|--------------------------------------------------------------|----------|--------------------------------------|
|
- [NewPipe](https://newpipe.schabi.org/) (app for android)
|
||||||
| [invidious](https://github.com/iv-org/invidious) | Server | Multi-user instance, REST API |
|
- [mps-youtube](https://github.com/mps-youtube/mps-youtube) (terminal-only program)
|
||||||
| [Yotter](https://github.com/ytorg/Yotter) | Server | YouTube + Twitter integration |
|
- [youtube-viewer](https://github.com/trizen/youtube-viewer)
|
||||||
| [FreeTube](https://github.com/FreeTubeApp/FreeTube) | Desktop | Electron-based client |
|
- [smtube](https://www.smtube.org/)
|
||||||
| [NewPipe](https://newpipe.schabi.org/) | Mobile | Android-only, no JavaScript |
|
- [Minitube](https://flavio.tordini.org/minitube), [github here](https://github.com/flaviotordini/minitube)
|
||||||
| [mps-youtube](https://github.com/mps-youtube/mps-youtube) | Terminal | CLI-based, text UI |
|
- [toogles](https://github.com/mikecrittenden/toogles) (only embeds videos, doesn't use mp4)
|
||||||
| [youtube-local](https://github.com/user234683/youtube-local) | Browser | Original project (base for yt-local) |
|
- [YTLibre](https://git.sr.ht/~heckyel/ytlibre) only extract video
|
||||||
|
- [youtube-dl](https://rg3.github.io/youtube-dl/), which this project was based off
|
||||||
---
|
|
||||||
|
|
||||||
Made for privacy-conscious users
|
|
||||||
|
|
||||||
Last updated: 2026-04-19
|
|
||||||
|
|||||||
@@ -1,108 +1,76 @@
|
|||||||
# Basic init yt-local for openrc
|
## Basic init yt-local for openrc
|
||||||
|
|
||||||
## Prerequisites
|
1. Write `/etc/init.d/ytlocal` file.
|
||||||
|
|
||||||
- System with OpenRC installed and configured.
|
```
|
||||||
- Administrative privileges (doas or sudo).
|
#!/sbin/openrc-run
|
||||||
- `ytlocal` script located at `/usr/sbin/ytlocal` and application files in an accessible directory.
|
# Distributed under the terms of the GNU General Public License v3 or later
|
||||||
|
name="yt-local"
|
||||||
|
pidfile="/var/run/ytlocal.pid"
|
||||||
|
command="/usr/sbin/ytlocal"
|
||||||
|
|
||||||
## Service Installation
|
depend() {
|
||||||
|
use net
|
||||||
|
}
|
||||||
|
|
||||||
1. **Create the OpenRC service script** `/etc/init.d/ytlocal`:
|
start_pre() {
|
||||||
|
if [ ! -f /usr/sbin/ytlocal ] ; then
|
||||||
|
eerror "Please create script file of ytlocal in '/usr/sbin/ytlocal'"
|
||||||
|
return 1
|
||||||
|
else
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
```sh
|
start() {
|
||||||
#!/sbin/openrc-run
|
ebegin "Starting yt-local"
|
||||||
# Distributed under the terms of the GNU General Public License v3 or later
|
start-stop-daemon --start --exec "${command}" --pidfile "${pidfile}"
|
||||||
name="yt-local"
|
eend $?
|
||||||
pidfile="/var/run/ytlocal.pid"
|
}
|
||||||
command="/usr/sbin/ytlocal"
|
|
||||||
|
|
||||||
depend() {
|
reload() {
|
||||||
use net
|
ebegin "Reloading ${name}"
|
||||||
}
|
start-stop-daemon --signal HUP --pidfile "${pidfile}"
|
||||||
|
eend $?
|
||||||
|
}
|
||||||
|
|
||||||
start_pre() {
|
stop() {
|
||||||
if [ ! -f /usr/sbin/ytlocal ]; then
|
ebegin "Stopping ${name}"
|
||||||
eerror "Please create script file of ytlocal in '/usr/sbin/ytlocal'"
|
start-stop-daemon --quiet --stop --exec "${command}" --pidfile "${pidfile}"
|
||||||
return 1
|
eend $?
|
||||||
else
|
}
|
||||||
return 0
|
```
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
start() {
|
after, modified execute permissions:
|
||||||
ebegin "Starting yt-local"
|
|
||||||
start-stop-daemon --start --exec "${command}" --pidfile "${pidfile}"
|
|
||||||
eend $?
|
|
||||||
}
|
|
||||||
|
|
||||||
reload() {
|
$ doas chmod a+x /etc/init.d/ytlocal
|
||||||
ebegin "Reloading ${name}"
|
|
||||||
start-stop-daemon --signal HUP --pidfile "${pidfile}"
|
|
||||||
eend $?
|
|
||||||
}
|
|
||||||
|
|
||||||
stop() {
|
|
||||||
ebegin "Stopping ${name}"
|
|
||||||
start-stop-daemon --quiet --stop --exec "${command}" --pidfile "${pidfile}"
|
|
||||||
eend $?
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
> [!NOTE]
|
2. Write `/usr/sbin/ytlocal` and configure path.
|
||||||
> Ensure the script is executable:
|
|
||||||
>
|
|
||||||
> ```sh
|
|
||||||
> doas chmod a+x /etc/init.d/ytlocal
|
|
||||||
> ```
|
|
||||||
|
|
||||||
2. **Create the executable script** `/usr/sbin/ytlocal`:
|
```
|
||||||
|
#!/usr/bin/env bash
|
||||||
|
|
||||||
```bash
|
cd /home/your-path/ytlocal/ # change me
|
||||||
#!/usr/bin/env bash
|
source venv/bin/activate
|
||||||
|
python server.py > /dev/null 2>&1 &
|
||||||
|
echo $! > /var/run/ytlocal.pid
|
||||||
|
```
|
||||||
|
|
||||||
# Change the working directory according to your installation path
|
after, modified execute permissions:
|
||||||
# Example: if installed in /usr/local/ytlocal, use:
|
|
||||||
cd /home/your-path/ytlocal/ # <-- MODIFY TO YOUR PATH
|
|
||||||
source venv/bin/activate
|
|
||||||
python server.py > /dev/null 2>&1 &
|
|
||||||
echo $! > /var/run/ytlocal.pid
|
|
||||||
```
|
|
||||||
|
|
||||||
> [!WARNING]
|
$ doas chmod a+x /usr/sbin/ytlocal
|
||||||
> Run this script only as root or via `doas`, as it writes to `/var/run` and uses network privileges.
|
|
||||||
|
|
||||||
> [!TIP]
|
|
||||||
> To store the PID in a different location, adjust the `pidfile` variable in the service script.
|
|
||||||
|
|
||||||
> [!IMPORTANT]
|
3. OpenRC check
|
||||||
> Verify that the virtual environment (`venv`) is correctly set up and that `python` points to the appropriate version.
|
|
||||||
|
|
||||||
> [!CAUTION]
|
- status: `doas rc-service ytlocal status`
|
||||||
> Do not stop the process manually; use OpenRC commands (`rc-service ytlocal stop`) to avoid race conditions.
|
- start: `doas rc-service ytlocal start`
|
||||||
|
- restart: `doas rc-service ytlocal restart`
|
||||||
|
- stop: `doas rc-service ytlocal stop`
|
||||||
|
|
||||||
> [!NOTE]
|
- enable: `doas rc-update add ytlocal default`
|
||||||
> When run with administrative privileges, the configuration is saved in `/root/.yt-local`, which is root‑only.
|
- disable: `doas rc-update del ytlocal`
|
||||||
|
|
||||||
## Service Management
|
When yt-local is run with administrator privileges,
|
||||||
|
the configuration file is stored in /root/.yt-local
|
||||||
- **Status**: `doas rc-service ytlocal status`
|
|
||||||
- **Start**: `doas rc-service ytlocal start`
|
|
||||||
- **Restart**: `doas rc-service ytlocal restart`
|
|
||||||
- **Stop**: `doas rc-service ytlocal stop`
|
|
||||||
- **Enable at boot**: `doas rc-update add ytlocal default`
|
|
||||||
- **Disable**: `doas rc-update del ytlocal`
|
|
||||||
|
|
||||||
## Post‑Installation Verification
|
|
||||||
|
|
||||||
- Confirm the process is running: `doas rc-service ytlocal status`
|
|
||||||
- Inspect logs for issues: `doas tail -f /var/log/ytlocal.log` (if logging is configured).
|
|
||||||
|
|
||||||
## Troubleshooting Common Issues
|
|
||||||
|
|
||||||
- **Service fails to start**: verify script permissions, correct `command=` path, and that the virtualenv exists.
|
|
||||||
- **Port conflict**: adjust the server’s port configuration before launching.
|
|
||||||
- **Import errors**: ensure all dependencies are installed in the virtual environment.
|
|
||||||
|
|
||||||
[!IMPORTANT]
|
|
||||||
Keep the service script updated when modifying startup logic or adding new dependencies.
|
|
||||||
|
|||||||
@@ -33,7 +33,7 @@ def check_subp(x):
|
|||||||
raise Exception('Got nonzero exit code from command')
|
raise Exception('Got nonzero exit code from command')
|
||||||
|
|
||||||
def log(line):
|
def log(line):
|
||||||
print(f'[generate_release.py] {line}')
|
print('[generate_release.py] ' + line)
|
||||||
|
|
||||||
# https://stackoverflow.com/questions/7833715/python-deleting-certain-file-extensions
|
# https://stackoverflow.com/questions/7833715/python-deleting-certain-file-extensions
|
||||||
def remove_files_with_extensions(path, extensions):
|
def remove_files_with_extensions(path, extensions):
|
||||||
@@ -43,33 +43,27 @@ def remove_files_with_extensions(path, extensions):
|
|||||||
os.remove(os.path.join(root, file))
|
os.remove(os.path.join(root, file))
|
||||||
|
|
||||||
def download_if_not_exists(file_name, url, sha256=None):
|
def download_if_not_exists(file_name, url, sha256=None):
|
||||||
if not os.path.exists(f'./{file_name}'):
|
if not os.path.exists('./' + file_name):
|
||||||
# Reject non-https URLs so a mistaken constant cannot cause a
|
log('Downloading ' + file_name + '..')
|
||||||
# plaintext download (bandit B310 hardening).
|
|
||||||
if not url.startswith('https://'):
|
|
||||||
raise Exception(f'Refusing to download over non-https URL: {url}')
|
|
||||||
log(f'Downloading {file_name}..')
|
|
||||||
data = urllib.request.urlopen(url).read()
|
data = urllib.request.urlopen(url).read()
|
||||||
log(f'Finished downloading {file_name}')
|
log('Finished downloading ' + file_name)
|
||||||
with open(f'./{file_name}', 'wb') as f:
|
with open('./' + file_name, 'wb') as f:
|
||||||
f.write(data)
|
f.write(data)
|
||||||
if sha256:
|
if sha256:
|
||||||
digest = hashlib.sha256(data).hexdigest()
|
digest = hashlib.sha256(data).hexdigest()
|
||||||
if digest != sha256:
|
if digest != sha256:
|
||||||
log(f'Error: {file_name} has wrong hash: {digest}')
|
log('Error: ' + file_name + ' has wrong hash: ' + digest)
|
||||||
sys.exit(1)
|
sys.exit(1)
|
||||||
else:
|
else:
|
||||||
log(f'Using existing {file_name}')
|
log('Using existing ' + file_name)
|
||||||
|
|
||||||
def wine_run_shell(command):
|
def wine_run_shell(command):
|
||||||
# Keep argv-style invocation (no shell) to avoid command injection.
|
|
||||||
if os.name == 'posix':
|
if os.name == 'posix':
|
||||||
parts = ['wine'] + command.replace('\\', '/').split()
|
check(os.system('wine ' + command.replace('\\', '/')))
|
||||||
elif os.name == 'nt':
|
elif os.name == 'nt':
|
||||||
parts = command.split()
|
check(os.system(command))
|
||||||
else:
|
else:
|
||||||
raise Exception('Unsupported OS')
|
raise Exception('Unsupported OS')
|
||||||
check(subprocess.run(parts).returncode)
|
|
||||||
|
|
||||||
def wine_run(command_parts):
|
def wine_run(command_parts):
|
||||||
if os.name == 'posix':
|
if os.name == 'posix':
|
||||||
@@ -98,20 +92,7 @@ if os.path.exists('./yt-local'):
|
|||||||
# confused with working directory. I'm calling it the same thing so it will
|
# confused with working directory. I'm calling it the same thing so it will
|
||||||
# have that name when extracted from the final release zip archive)
|
# have that name when extracted from the final release zip archive)
|
||||||
log('Making copy of yt-local files')
|
log('Making copy of yt-local files')
|
||||||
# Avoid the shell: pipe `git archive` into 7z directly via subprocess.
|
check(os.system('git archive --format tar master | 7z x -si -ttar -oyt-local'))
|
||||||
_git_archive = subprocess.Popen(
|
|
||||||
['git', 'archive', '--format', 'tar', 'master'],
|
|
||||||
stdout=subprocess.PIPE,
|
|
||||||
)
|
|
||||||
_sevenz = subprocess.Popen(
|
|
||||||
['7z', 'x', '-si', '-ttar', '-oyt-local'],
|
|
||||||
stdin=_git_archive.stdout,
|
|
||||||
)
|
|
||||||
_git_archive.stdout.close()
|
|
||||||
_sevenz.wait()
|
|
||||||
_git_archive.wait()
|
|
||||||
check(_sevenz.returncode)
|
|
||||||
check(_git_archive.returncode)
|
|
||||||
|
|
||||||
if len(os.listdir('./yt-local')) == 0:
|
if len(os.listdir('./yt-local')) == 0:
|
||||||
raise Exception('Failed to copy yt-local files')
|
raise Exception('Failed to copy yt-local files')
|
||||||
@@ -120,7 +101,7 @@ if len(os.listdir('./yt-local')) == 0:
|
|||||||
# ----------- Generate embedded python distribution -----------
|
# ----------- Generate embedded python distribution -----------
|
||||||
os.environ['PYTHONDONTWRITEBYTECODE'] = '1' # *.pyc files double the size of the distribution
|
os.environ['PYTHONDONTWRITEBYTECODE'] = '1' # *.pyc files double the size of the distribution
|
||||||
get_pip_url = 'https://bootstrap.pypa.io/get-pip.py'
|
get_pip_url = 'https://bootstrap.pypa.io/get-pip.py'
|
||||||
latest_dist_url = f'https://www.python.org/ftp/python/{latest_version}/python-{latest_version}'
|
latest_dist_url = 'https://www.python.org/ftp/python/' + latest_version + '/python-' + latest_version
|
||||||
if bitness == '32':
|
if bitness == '32':
|
||||||
latest_dist_url += '-embed-win32.zip'
|
latest_dist_url += '-embed-win32.zip'
|
||||||
else:
|
else:
|
||||||
@@ -142,7 +123,7 @@ else:
|
|||||||
|
|
||||||
download_if_not_exists('get-pip.py', get_pip_url)
|
download_if_not_exists('get-pip.py', get_pip_url)
|
||||||
|
|
||||||
python_dist_name = f'python-dist-{latest_version}-{bitness}.zip'
|
python_dist_name = 'python-dist-' + latest_version + '-' + bitness + '.zip'
|
||||||
|
|
||||||
download_if_not_exists(python_dist_name, latest_dist_url)
|
download_if_not_exists(python_dist_name, latest_dist_url)
|
||||||
download_if_not_exists(visual_c_name,
|
download_if_not_exists(visual_c_name,
|
||||||
@@ -155,7 +136,7 @@ if os.path.exists('./python'):
|
|||||||
|
|
||||||
log('Extracting python distribution')
|
log('Extracting python distribution')
|
||||||
|
|
||||||
check_subp(subprocess.run(['7z', '-y', 'x', '-opython', python_dist_name]))
|
check(os.system(r'7z -y x -opython ' + python_dist_name))
|
||||||
|
|
||||||
log('Executing get-pip.py')
|
log('Executing get-pip.py')
|
||||||
wine_run(['./python/python.exe', '-I', 'get-pip.py'])
|
wine_run(['./python/python.exe', '-I', 'get-pip.py'])
|
||||||
@@ -203,7 +184,7 @@ and replaced with a .pth. Isolated mode will have to be specified manually.
|
|||||||
|
|
||||||
log('Removing ._pth')
|
log('Removing ._pth')
|
||||||
major_release = latest_version.split('.')[1]
|
major_release = latest_version.split('.')[1]
|
||||||
os.remove(rf'./python/python3{major_release}._pth')
|
os.remove(r'./python/python3' + major_release + '._pth')
|
||||||
|
|
||||||
log('Adding path_fixes.pth')
|
log('Adding path_fixes.pth')
|
||||||
with open(r'./python/path_fixes.pth', 'w', encoding='utf-8') as f:
|
with open(r'./python/path_fixes.pth', 'w', encoding='utf-8') as f:
|
||||||
@@ -214,7 +195,7 @@ with open(r'./python/path_fixes.pth', 'w', encoding='utf-8') as f:
|
|||||||
# Need to add the directory where packages are installed,
|
# Need to add the directory where packages are installed,
|
||||||
# and the parent directory (which is where the yt-local files are)
|
# and the parent directory (which is where the yt-local files are)
|
||||||
major_release = latest_version.split('.')[1]
|
major_release = latest_version.split('.')[1]
|
||||||
with open(rf'./python/python3{major_release}._pth', 'a', encoding='utf-8') as f:
|
with open('./python/python3' + major_release + '._pth', 'a', encoding='utf-8') as f:
|
||||||
f.write('.\\Lib\\site-packages\n')
|
f.write('.\\Lib\\site-packages\n')
|
||||||
f.write('..\n')'''
|
f.write('..\n')'''
|
||||||
|
|
||||||
@@ -255,12 +236,12 @@ log('Copying python distribution into release folder')
|
|||||||
shutil.copytree(r'./python', r'./yt-local/python')
|
shutil.copytree(r'./python', r'./yt-local/python')
|
||||||
|
|
||||||
# ----------- Create release zip -----------
|
# ----------- Create release zip -----------
|
||||||
output_filename = f'yt-local-{release_tag}-{suffix}.zip'
|
output_filename = 'yt-local-' + release_tag + '-' + suffix + '.zip'
|
||||||
if os.path.exists(f'./{output_filename}'):
|
if os.path.exists('./' + output_filename):
|
||||||
log('Removing previous zipped release')
|
log('Removing previous zipped release')
|
||||||
os.remove(f'./{output_filename}')
|
os.remove('./' + output_filename)
|
||||||
log('Zipping release')
|
log('Zipping release')
|
||||||
check_subp(subprocess.run(['7z', '-mx=9', 'a', output_filename, './yt-local']))
|
check(os.system(r'7z -mx=9 a ' + output_filename + ' ./yt-local'))
|
||||||
|
|
||||||
print('\n')
|
print('\n')
|
||||||
log('Finished')
|
log('Finished')
|
||||||
|
|||||||
39
server.py
39
server.py
@@ -1,28 +1,22 @@
|
|||||||
#!/usr/bin/env python3
|
#!/usr/bin/env python3
|
||||||
# E402 is deliberately ignored in this file: `monkey.patch_all()` must run
|
|
||||||
# before any stdlib networking or gevent-dependent modules are imported.
|
|
||||||
from gevent import monkey
|
from gevent import monkey
|
||||||
monkey.patch_all()
|
monkey.patch_all()
|
||||||
|
import gevent.socket
|
||||||
|
|
||||||
from youtube import yt_app
|
from youtube import yt_app
|
||||||
from youtube import util
|
from youtube import util
|
||||||
|
|
||||||
# these are just so the files get run - they import yt_app and add routes to it
|
# these are just so the files get run - they import yt_app and add routes to it
|
||||||
from youtube import (
|
from youtube import watch, search, playlist, channel, local_playlist, comments, subscriptions
|
||||||
watch,
|
|
||||||
search,
|
|
||||||
playlist,
|
|
||||||
channel,
|
|
||||||
local_playlist,
|
|
||||||
comments,
|
|
||||||
subscriptions,
|
|
||||||
)
|
|
||||||
|
|
||||||
import settings
|
import settings
|
||||||
|
|
||||||
from gevent.pywsgi import WSGIServer
|
from gevent.pywsgi import WSGIServer
|
||||||
import urllib
|
import urllib
|
||||||
import urllib3
|
import urllib3
|
||||||
|
import socket
|
||||||
|
import socks, sockshandler
|
||||||
|
import subprocess
|
||||||
import re
|
import re
|
||||||
import sys
|
import sys
|
||||||
import time
|
import time
|
||||||
@@ -32,9 +26,9 @@ def youtu_be(env, start_response):
|
|||||||
id = env['PATH_INFO'][1:]
|
id = env['PATH_INFO'][1:]
|
||||||
env['PATH_INFO'] = '/watch'
|
env['PATH_INFO'] = '/watch'
|
||||||
if not env['QUERY_STRING']:
|
if not env['QUERY_STRING']:
|
||||||
env['QUERY_STRING'] = f'v={id}'
|
env['QUERY_STRING'] = 'v=' + id
|
||||||
else:
|
else:
|
||||||
env['QUERY_STRING'] += f'&v={id}'
|
env['QUERY_STRING'] += '&v=' + id
|
||||||
yield from yt_app(env, start_response)
|
yield from yt_app(env, start_response)
|
||||||
|
|
||||||
|
|
||||||
@@ -61,15 +55,17 @@ def proxy_site(env, start_response, video=False):
|
|||||||
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)',
|
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)',
|
||||||
'Accept': '*/*',
|
'Accept': '*/*',
|
||||||
}
|
}
|
||||||
|
current_range_start = 0
|
||||||
|
range_end = None
|
||||||
if 'HTTP_RANGE' in env:
|
if 'HTTP_RANGE' in env:
|
||||||
send_headers['Range'] = env['HTTP_RANGE']
|
send_headers['Range'] = env['HTTP_RANGE']
|
||||||
|
|
||||||
url = f"https://{env['SERVER_NAME']}{env['PATH_INFO']}"
|
url = "https://" + env['SERVER_NAME'] + env['PATH_INFO']
|
||||||
# remove /name portion
|
# remove /name portion
|
||||||
if video and '/videoplayback/name/' in url:
|
if video and '/videoplayback/name/' in url:
|
||||||
url = url[0:url.rfind('/name/')]
|
url = url[0:url.rfind('/name/')]
|
||||||
if env['QUERY_STRING']:
|
if env['QUERY_STRING']:
|
||||||
url += f'?{env["QUERY_STRING"]}'
|
url += '?' + env['QUERY_STRING']
|
||||||
|
|
||||||
try_num = 1
|
try_num = 1
|
||||||
first_attempt = True
|
first_attempt = True
|
||||||
@@ -96,7 +92,7 @@ def proxy_site(env, start_response, video=False):
|
|||||||
+[('Access-Control-Allow-Origin', '*')])
|
+[('Access-Control-Allow-Origin', '*')])
|
||||||
|
|
||||||
if first_attempt:
|
if first_attempt:
|
||||||
start_response(f"{response.status} {response.reason}",
|
start_response(str(response.status) + ' ' + response.reason,
|
||||||
response_headers)
|
response_headers)
|
||||||
|
|
||||||
content_length = int(dict(response_headers).get('Content-Length', 0))
|
content_length = int(dict(response_headers).get('Content-Length', 0))
|
||||||
@@ -136,8 +132,9 @@ def proxy_site(env, start_response, video=False):
|
|||||||
fail_byte = start + total_received
|
fail_byte = start + total_received
|
||||||
send_headers['Range'] = 'bytes=%d-%d' % (fail_byte, end)
|
send_headers['Range'] = 'bytes=%d-%d' % (fail_byte, end)
|
||||||
print(
|
print(
|
||||||
f'Warning: YouTube closed the connection before byte {fail_byte}. '
|
'Warning: YouTube closed the connection before byte',
|
||||||
f'Expected {start+content_length} bytes.'
|
str(fail_byte) + '.', 'Expected', start+content_length,
|
||||||
|
'bytes.'
|
||||||
)
|
)
|
||||||
|
|
||||||
retry = True
|
retry = True
|
||||||
@@ -184,7 +181,7 @@ def split_url(url):
|
|||||||
# python STILL doesn't have a proper regular expression engine like grep uses built in...
|
# python STILL doesn't have a proper regular expression engine like grep uses built in...
|
||||||
match = re.match(r'(?:https?://)?([\w-]+(?:\.[\w-]+)+?)(/.*|$)', url)
|
match = re.match(r'(?:https?://)?([\w-]+(?:\.[\w-]+)+?)(/.*|$)', url)
|
||||||
if match is None:
|
if match is None:
|
||||||
raise ValueError(f'Invalid or unsupported url: {url}')
|
raise ValueError('Invalid or unsupported url: ' + url)
|
||||||
|
|
||||||
return match.group(1), match.group(2)
|
return match.group(1), match.group(2)
|
||||||
|
|
||||||
@@ -237,7 +234,7 @@ def site_dispatch(env, start_response):
|
|||||||
if base_name == '':
|
if base_name == '':
|
||||||
base_name = domain
|
base_name = domain
|
||||||
else:
|
else:
|
||||||
base_name = f"{domain}.{base_name}"
|
base_name = domain + '.' + base_name
|
||||||
|
|
||||||
try:
|
try:
|
||||||
handler = site_handlers[base_name]
|
handler = site_handlers[base_name]
|
||||||
@@ -277,8 +274,6 @@ class FilteredRequestLog:
|
|||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
if settings.allow_foreign_addresses:
|
if settings.allow_foreign_addresses:
|
||||||
# Binding to all interfaces is opt-in via the
|
|
||||||
# `allow_foreign_addresses` setting and documented as discouraged.
|
|
||||||
server = WSGIServer(('0.0.0.0', settings.port_number), site_dispatch,
|
server = WSGIServer(('0.0.0.0', settings.port_number), site_dispatch,
|
||||||
log=FilteredRequestLog())
|
log=FilteredRequestLog())
|
||||||
ip_server = '0.0.0.0'
|
ip_server = '0.0.0.0'
|
||||||
|
|||||||
42
settings.py
42
settings.py
@@ -261,20 +261,10 @@ For security reasons, enabling this is not recommended.''',
|
|||||||
'category': 'interface',
|
'category': 'interface',
|
||||||
}),
|
}),
|
||||||
|
|
||||||
('native_player_storyboard', {
|
|
||||||
'type': bool,
|
|
||||||
'default': False,
|
|
||||||
'label': 'Storyboard preview (native)',
|
|
||||||
'comment': '''Show thumbnail preview on hover (native player modes).
|
|
||||||
Positioning is heuristic; may misalign in Firefox/Safari.
|
|
||||||
Works best on Chromium browsers.
|
|
||||||
No effect in Plyr.''',
|
|
||||||
'category': 'interface',
|
|
||||||
}),
|
|
||||||
|
|
||||||
('use_video_download', {
|
('use_video_download', {
|
||||||
'type': int,
|
'type': int,
|
||||||
'default': 0,
|
'default': 0,
|
||||||
|
'comment': '',
|
||||||
'options': [
|
'options': [
|
||||||
(0, 'Disabled'),
|
(0, 'Disabled'),
|
||||||
(1, 'Enabled'),
|
(1, 'Enabled'),
|
||||||
@@ -397,14 +387,14 @@ acceptable_targets = SETTINGS_INFO.keys() | {
|
|||||||
def comment_string(comment):
|
def comment_string(comment):
|
||||||
result = ''
|
result = ''
|
||||||
for line in comment.splitlines():
|
for line in comment.splitlines():
|
||||||
result += f'# {line}\n'
|
result += '# ' + line + '\n'
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
def save_settings(settings_dict):
|
def save_settings(settings_dict):
|
||||||
with open(settings_file_path, 'w', encoding='utf-8') as file:
|
with open(settings_file_path, 'w', encoding='utf-8') as file:
|
||||||
for setting_name, setting_info in SETTINGS_INFO.items():
|
for setting_name, setting_info in SETTINGS_INFO.items():
|
||||||
file.write(f"{comment_string(setting_info['comment'])}{setting_name} = {repr(settings_dict[setting_name])}\n\n")
|
file.write(comment_string(setting_info['comment']) + setting_name + ' = ' + repr(settings_dict[setting_name]) + '\n\n')
|
||||||
|
|
||||||
|
|
||||||
def add_missing_settings(settings_dict):
|
def add_missing_settings(settings_dict):
|
||||||
@@ -481,7 +471,7 @@ upgrade_functions = {
|
|||||||
|
|
||||||
|
|
||||||
def log_ignored_line(line_number, message):
|
def log_ignored_line(line_number, message):
|
||||||
print(f'WARNING: Ignoring settings.txt line {line_number} ({message})')
|
print("WARNING: Ignoring settings.txt line " + str(node.lineno) + " (" + message + ")")
|
||||||
|
|
||||||
|
|
||||||
if os.path.isfile("settings.txt"):
|
if os.path.isfile("settings.txt"):
|
||||||
@@ -509,33 +499,29 @@ else:
|
|||||||
else:
|
else:
|
||||||
# parse settings in a safe way, without exec
|
# parse settings in a safe way, without exec
|
||||||
current_settings_dict = {}
|
current_settings_dict = {}
|
||||||
# Python 3.8+ uses ast.Constant; older versions use ast.Num, ast.Str, ast.NameConstant
|
|
||||||
attributes = {
|
attributes = {
|
||||||
ast.Constant: 'value',
|
ast.Constant: 'value',
|
||||||
|
ast.NameConstant: 'value',
|
||||||
|
ast.Num: 'n',
|
||||||
|
ast.Str: 's',
|
||||||
}
|
}
|
||||||
try:
|
|
||||||
attributes[ast.Num] = 'n'
|
|
||||||
attributes[ast.Str] = 's'
|
|
||||||
attributes[ast.NameConstant] = 'value'
|
|
||||||
except AttributeError:
|
|
||||||
pass # Removed in Python 3.12+
|
|
||||||
module_node = ast.parse(settings_text)
|
module_node = ast.parse(settings_text)
|
||||||
for node in module_node.body:
|
for node in module_node.body:
|
||||||
if not isinstance(node, ast.Assign):
|
if type(node) != ast.Assign:
|
||||||
log_ignored_line(node.lineno, 'only assignments are allowed')
|
log_ignored_line(node.lineno, "only assignments are allowed")
|
||||||
continue
|
continue
|
||||||
|
|
||||||
if len(node.targets) > 1:
|
if len(node.targets) > 1:
|
||||||
log_ignored_line(node.lineno, 'only simple single-variable assignments allowed')
|
log_ignored_line(node.lineno, "only simple single-variable assignments allowed")
|
||||||
continue
|
continue
|
||||||
|
|
||||||
target = node.targets[0]
|
target = node.targets[0]
|
||||||
if not isinstance(target, ast.Name):
|
if type(target) != ast.Name:
|
||||||
log_ignored_line(node.lineno, 'only simple single-variable assignments allowed')
|
log_ignored_line(node.lineno, "only simple single-variable assignments allowed")
|
||||||
continue
|
continue
|
||||||
|
|
||||||
if target.id not in acceptable_targets:
|
if target.id not in acceptable_targets:
|
||||||
log_ignored_line(node.lineno, f"{target.id} is not a valid setting")
|
log_ignored_line(node.lineno, target.id + " is not a valid setting")
|
||||||
continue
|
continue
|
||||||
|
|
||||||
if type(node.value) not in attributes:
|
if type(node.value) not in attributes:
|
||||||
@@ -645,6 +631,6 @@ def settings_page():
|
|||||||
for func, old_value, value in to_call:
|
for func, old_value, value in to_call:
|
||||||
func(old_value, value)
|
func(old_value, value)
|
||||||
|
|
||||||
return flask.redirect(f'{util.URL_ORIGIN}/settings', 303)
|
return flask.redirect(util.URL_ORIGIN + '/settings', 303)
|
||||||
else:
|
else:
|
||||||
flask.abort(400)
|
flask.abort(400)
|
||||||
|
|||||||
@@ -11,7 +11,8 @@ import pytest
|
|||||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
||||||
import youtube.proto as proto
|
import youtube.proto as proto
|
||||||
from youtube.yt_data_extract.common import (
|
from youtube.yt_data_extract.common import (
|
||||||
extract_item_info, extract_items,
|
extract_item_info, extract_items, extract_shorts_lockup_view_model_info,
|
||||||
|
extract_approx_int,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@@ -27,7 +28,7 @@ class TestChannelCtokenV5:
|
|||||||
|
|
||||||
def _decode_outer(self, ctoken):
|
def _decode_outer(self, ctoken):
|
||||||
"""Decode the outer protobuf layer of a ctoken."""
|
"""Decode the outer protobuf layer of a ctoken."""
|
||||||
raw = base64.urlsafe_b64decode(f'{ctoken}==')
|
raw = base64.urlsafe_b64decode(ctoken + '==')
|
||||||
return {fn: val for _, fn, val in proto.read_protobuf(raw)}
|
return {fn: val for _, fn, val in proto.read_protobuf(raw)}
|
||||||
|
|
||||||
def test_shorts_token_generates_without_error(self):
|
def test_shorts_token_generates_without_error(self):
|
||||||
@@ -57,59 +58,6 @@ class TestChannelCtokenV5:
|
|||||||
assert t_shorts != t_streams
|
assert t_shorts != t_streams
|
||||||
assert t_videos != t_streams
|
assert t_videos != t_streams
|
||||||
|
|
||||||
def test_include_shorts_false_adds_filter(self):
|
|
||||||
"""Test that include_shorts=False adds the shorts filter (field 104)."""
|
|
||||||
# Token with shorts included (default)
|
|
||||||
t_with_shorts = self.channel_ctoken_v5('UCtest', '1', '3', 'videos', include_shorts=True)
|
|
||||||
# Token with shorts excluded
|
|
||||||
t_without_shorts = self.channel_ctoken_v5('UCtest', '1', '3', 'videos', include_shorts=False)
|
|
||||||
|
|
||||||
# The tokens should be different because of the shorts filter
|
|
||||||
assert t_with_shorts != t_without_shorts
|
|
||||||
|
|
||||||
# Decode and verify the filter is present
|
|
||||||
raw_with_shorts = base64.urlsafe_b64decode(f'{t_with_shorts}==')
|
|
||||||
raw_without_shorts = base64.urlsafe_b64decode(f'{t_without_shorts}==')
|
|
||||||
|
|
||||||
# Parse the outer protobuf structure
|
|
||||||
import youtube.proto as proto
|
|
||||||
outer_fields_with = list(proto.read_protobuf(raw_with_shorts))
|
|
||||||
outer_fields_without = list(proto.read_protobuf(raw_without_shorts))
|
|
||||||
|
|
||||||
# Field 80226972 contains the inner data
|
|
||||||
inner_with = [v for _, fn, v in outer_fields_with if fn == 80226972][0]
|
|
||||||
inner_without = [v for _, fn, v in outer_fields_without if fn == 80226972][0]
|
|
||||||
|
|
||||||
# Parse the inner data - field 3 contains percent-encoded base64 data
|
|
||||||
inner_fields_with = list(proto.read_protobuf(inner_with))
|
|
||||||
inner_fields_without = list(proto.read_protobuf(inner_without))
|
|
||||||
|
|
||||||
# Get field 3 data (the encoded inner which is percent-encoded base64)
|
|
||||||
encoded_inner_with = [v for _, fn, v in inner_fields_with if fn == 3][0]
|
|
||||||
encoded_inner_without = [v for _, fn, v in inner_fields_without if fn == 3][0]
|
|
||||||
|
|
||||||
# The inner without shorts should contain field 104
|
|
||||||
# Decode the percent-encoded base64 data
|
|
||||||
import urllib.parse
|
|
||||||
decoded_with = urllib.parse.unquote(encoded_inner_with.decode('ascii'))
|
|
||||||
decoded_without = urllib.parse.unquote(encoded_inner_without.decode('ascii'))
|
|
||||||
|
|
||||||
# Decode the base64 data
|
|
||||||
decoded_with_bytes = base64.urlsafe_b64decode(f'{decoded_with}==')
|
|
||||||
decoded_without_bytes = base64.urlsafe_b64decode(f'{decoded_without}==')
|
|
||||||
|
|
||||||
# Parse the decoded protobuf data
|
|
||||||
fields_with = list(proto.read_protobuf(decoded_with_bytes))
|
|
||||||
fields_without = list(proto.read_protobuf(decoded_without_bytes))
|
|
||||||
|
|
||||||
field_numbers_with = [fn for _, fn, _ in fields_with]
|
|
||||||
field_numbers_without = [fn for _, fn, _ in fields_without]
|
|
||||||
|
|
||||||
# The 'with' version should NOT have field 104
|
|
||||||
assert 104 not in field_numbers_with
|
|
||||||
# The 'without' version SHOULD have field 104
|
|
||||||
assert 104 in field_numbers_without
|
|
||||||
|
|
||||||
|
|
||||||
# --- shortsLockupViewModel parsing ---
|
# --- shortsLockupViewModel parsing ---
|
||||||
|
|
||||||
|
|||||||
@@ -39,8 +39,7 @@ class NewIdentityState():
|
|||||||
self.new_identities_till_success -= 1
|
self.new_identities_till_success -= 1
|
||||||
|
|
||||||
def fetch_url_response(self, *args, **kwargs):
|
def fetch_url_response(self, *args, **kwargs):
|
||||||
def cleanup_func(response):
|
cleanup_func = (lambda r: None)
|
||||||
return None
|
|
||||||
if self.new_identities_till_success == 0:
|
if self.new_identities_till_success == 0:
|
||||||
return MockResponse(), cleanup_func
|
return MockResponse(), cleanup_func
|
||||||
return MockResponse(body=html429, status=429), cleanup_func
|
return MockResponse(body=html429, status=429), cleanup_func
|
||||||
|
|||||||
@@ -1,17 +1,14 @@
|
|||||||
import logging
|
|
||||||
import os
|
|
||||||
import re
|
|
||||||
import traceback
|
|
||||||
from sys import exc_info
|
|
||||||
|
|
||||||
import flask
|
|
||||||
import jinja2
|
|
||||||
from flask import request
|
|
||||||
from flask_babel import Babel
|
|
||||||
|
|
||||||
from youtube import util
|
from youtube import util
|
||||||
from .get_app_version import app_version
|
from .get_app_version import app_version
|
||||||
|
import flask
|
||||||
|
from flask import request
|
||||||
|
import jinja2
|
||||||
import settings
|
import settings
|
||||||
|
import traceback
|
||||||
|
import logging
|
||||||
|
import re
|
||||||
|
from sys import exc_info
|
||||||
|
from flask_babel import Babel
|
||||||
|
|
||||||
yt_app = flask.Flask(__name__)
|
yt_app = flask.Flask(__name__)
|
||||||
yt_app.config['TEMPLATES_AUTO_RELOAD'] = True
|
yt_app.config['TEMPLATES_AUTO_RELOAD'] = True
|
||||||
@@ -29,6 +26,7 @@ yt_app.logger.addFilter(FetchErrorFilter())
|
|||||||
# yt_app.jinja_env.lstrip_blocks = True
|
# yt_app.jinja_env.lstrip_blocks = True
|
||||||
|
|
||||||
# Configure Babel for i18n
|
# Configure Babel for i18n
|
||||||
|
import os
|
||||||
yt_app.config['BABEL_DEFAULT_LOCALE'] = 'en'
|
yt_app.config['BABEL_DEFAULT_LOCALE'] = 'en'
|
||||||
# Use absolute path for translations directory to avoid issues with package structure changes
|
# Use absolute path for translations directory to avoid issues with package structure changes
|
||||||
_app_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
_app_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||||
@@ -76,7 +74,7 @@ theme_names = {
|
|||||||
@yt_app.context_processor
|
@yt_app.context_processor
|
||||||
def inject_theme_preference():
|
def inject_theme_preference():
|
||||||
return {
|
return {
|
||||||
'theme_path': f'/youtube.com/static/{theme_names[settings.theme]}.css',
|
'theme_path': '/youtube.com/static/' + theme_names[settings.theme] + '.css',
|
||||||
'settings': settings,
|
'settings': settings,
|
||||||
# Detect version
|
# Detect version
|
||||||
'current_version': app_version()['version'],
|
'current_version': app_version()['version'],
|
||||||
@@ -145,9 +143,9 @@ def error_page(e):
|
|||||||
' exit node is overutilized. Try getting a new exit node by'
|
' exit node is overutilized. Try getting a new exit node by'
|
||||||
' using the New Identity button in the Tor Browser.')
|
' using the New Identity button in the Tor Browser.')
|
||||||
if fetch_err.error_message:
|
if fetch_err.error_message:
|
||||||
error_message += f'\n\n{fetch_err.error_message}'
|
error_message += '\n\n' + fetch_err.error_message
|
||||||
if fetch_err.ip:
|
if fetch_err.ip:
|
||||||
error_message += f'\n\nExit node IP address: {fetch_err.ip}'
|
error_message += '\n\nExit node IP address: ' + fetch_err.ip
|
||||||
return flask.render_template('error.html', error_message=error_message, slim=slim), 502
|
return flask.render_template('error.html', error_message=error_message, slim=slim), 502
|
||||||
|
|
||||||
elif error_code == '429':
|
elif error_code == '429':
|
||||||
@@ -157,7 +155,7 @@ def error_page(e):
|
|||||||
'• Enable Tor routing in Settings for automatic IP rotation\n'
|
'• Enable Tor routing in Settings for automatic IP rotation\n'
|
||||||
'• Use a VPN to change your IP address')
|
'• Use a VPN to change your IP address')
|
||||||
if fetch_err.ip:
|
if fetch_err.ip:
|
||||||
error_message += f'\n\nYour IP: {fetch_err.ip}'
|
error_message += '\n\nYour IP: ' + fetch_err.ip
|
||||||
return flask.render_template('error.html', error_message=error_message, slim=slim), 429
|
return flask.render_template('error.html', error_message=error_message, slim=slim), 429
|
||||||
|
|
||||||
elif error_code == '502' and ('Failed to resolve' in str(fetch_err) or 'Failed to establish' in str(fetch_err)):
|
elif error_code == '502' and ('Failed to resolve' in str(fetch_err) or 'Failed to establish' in str(fetch_err)):
|
||||||
@@ -179,7 +177,7 @@ def error_page(e):
|
|||||||
# Catch-all for any other FetchError (400, etc.)
|
# Catch-all for any other FetchError (400, etc.)
|
||||||
error_message = f'Error communicating with YouTube ({error_code}).'
|
error_message = f'Error communicating with YouTube ({error_code}).'
|
||||||
if fetch_err.error_message:
|
if fetch_err.error_message:
|
||||||
error_message += f'\n\n{fetch_err.error_message}'
|
error_message += '\n\n' + fetch_err.error_message
|
||||||
return flask.render_template('error.html', error_message=error_message, slim=slim), 502
|
return flask.render_template('error.html', error_message=error_message, slim=slim), 502
|
||||||
|
|
||||||
return flask.render_template('error.html', traceback=traceback.format_exc(),
|
return flask.render_template('error.html', traceback=traceback.format_exc(),
|
||||||
|
|||||||
@@ -6,7 +6,9 @@ import settings
|
|||||||
|
|
||||||
import urllib
|
import urllib
|
||||||
import json
|
import json
|
||||||
|
from string import Template
|
||||||
import youtube.proto as proto
|
import youtube.proto as proto
|
||||||
|
import html
|
||||||
import math
|
import math
|
||||||
import gevent
|
import gevent
|
||||||
import re
|
import re
|
||||||
@@ -31,9 +33,9 @@ headers_mobile = (
|
|||||||
real_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=8XihrAcN1l4'),)
|
real_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=8XihrAcN1l4'),)
|
||||||
generic_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=ST1Ti53r4fU'),)
|
generic_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=ST1Ti53r4fU'),)
|
||||||
|
|
||||||
|
# FIXED 2026: YouTube changed continuation token structure (from Invidious commit a9f8127)
|
||||||
# Sort values for YouTube API (from Invidious): 2=popular, 4=newest, 5=oldest
|
# Sort values for YouTube API (from Invidious): 2=popular, 4=newest, 5=oldest
|
||||||
# include_shorts only applies to tab='videos'; tab='shorts'/'streams' always include their own content.
|
def channel_ctoken_v5(channel_id, page, sort, tab, view=1):
|
||||||
def channel_ctoken_v5(channel_id, page, sort, tab, view=1, include_shorts=True):
|
|
||||||
# Tab-specific protobuf field numbers (from Invidious source)
|
# Tab-specific protobuf field numbers (from Invidious source)
|
||||||
# Each tab uses different field numbers in the protobuf structure:
|
# Each tab uses different field numbers in the protobuf structure:
|
||||||
# videos: 110 -> 3 -> 15 -> { 2:{1:UUID}, 4:sort, 8:{1:UUID, 3:sort} }
|
# videos: 110 -> 3 -> 15 -> { 2:{1:UUID}, 4:sort, 8:{1:UUID, 3:sort} }
|
||||||
@@ -72,11 +74,6 @@ def channel_ctoken_v5(channel_id, page, sort, tab, view=1, include_shorts=True):
|
|||||||
inner_container = proto.string(3, tab_wrapper)
|
inner_container = proto.string(3, tab_wrapper)
|
||||||
outer_container = proto.string(110, inner_container)
|
outer_container = proto.string(110, inner_container)
|
||||||
|
|
||||||
# Add shorts filter when include_shorts=False (field 104, same as playlist.py)
|
|
||||||
# This tells YouTube to exclude shorts from the results
|
|
||||||
if not include_shorts:
|
|
||||||
outer_container += proto.string(104, proto.uint(2, 1))
|
|
||||||
|
|
||||||
encoded_inner = proto.percent_b64encode(outer_container)
|
encoded_inner = proto.percent_b64encode(outer_container)
|
||||||
|
|
||||||
pointless_nest = proto.string(80226972,
|
pointless_nest = proto.string(80226972,
|
||||||
@@ -239,12 +236,12 @@ def channel_ctoken_v1(channel_id, page, sort, tab, view=1):
|
|||||||
|
|
||||||
|
|
||||||
def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
|
def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
|
||||||
ctoken=None, print_status=True, include_shorts=True):
|
ctoken=None, print_status=True):
|
||||||
message = 'Got channel tab' if print_status else None
|
message = 'Got channel tab' if print_status else None
|
||||||
|
|
||||||
if not ctoken:
|
if not ctoken:
|
||||||
if tab in ('videos', 'shorts', 'streams'):
|
if tab in ('videos', 'shorts', 'streams'):
|
||||||
ctoken = channel_ctoken_v5(channel_id, page, sort, tab, view, include_shorts)
|
ctoken = channel_ctoken_v5(channel_id, page, sort, tab, view)
|
||||||
else:
|
else:
|
||||||
ctoken = channel_ctoken_v3(channel_id, page, sort, tab, view)
|
ctoken = channel_ctoken_v3(channel_id, page, sort, tab, view)
|
||||||
ctoken = ctoken.replace('=', '%3D')
|
ctoken = ctoken.replace('=', '%3D')
|
||||||
@@ -253,7 +250,7 @@ def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
|
|||||||
# For now it seems to be constant for the API endpoint, not dependent
|
# For now it seems to be constant for the API endpoint, not dependent
|
||||||
# on the browsing session or channel
|
# on the browsing session or channel
|
||||||
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
||||||
url = f'https://www.youtube.com/youtubei/v1/browse?key={key}'
|
url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
|
||||||
|
|
||||||
data = {
|
data = {
|
||||||
'context': {
|
'context': {
|
||||||
@@ -285,36 +282,25 @@ def get_number_of_videos_channel(channel_id):
|
|||||||
return 1000
|
return 1000
|
||||||
|
|
||||||
# Uploads playlist
|
# Uploads playlist
|
||||||
playlist_id = f'UU{channel_id[2:]}'
|
playlist_id = 'UU' + channel_id[2:]
|
||||||
url = f'https://m.youtube.com/playlist?list={playlist_id}&pbj=1'
|
url = 'https://m.youtube.com/playlist?list=' + playlist_id + '&pbj=1'
|
||||||
|
|
||||||
try:
|
try:
|
||||||
response = util.fetch_url(url, headers_mobile,
|
response = util.fetch_url(url, headers_mobile,
|
||||||
debug_name='number_of_videos', report_text='Got number of videos')
|
debug_name='number_of_videos', report_text='Got number of videos')
|
||||||
except (urllib.error.HTTPError, util.FetchError):
|
except (urllib.error.HTTPError, util.FetchError) as e:
|
||||||
traceback.print_exc()
|
traceback.print_exc()
|
||||||
print("Couldn't retrieve number of videos")
|
print("Couldn't retrieve number of videos")
|
||||||
return 1000
|
return 1000
|
||||||
|
|
||||||
response = response.decode('utf-8')
|
response = response.decode('utf-8')
|
||||||
|
|
||||||
# Try several patterns since YouTube's format changes:
|
# match = re.search(r'"numVideosText":\s*{\s*"runs":\s*\[{"text":\s*"([\d,]*) videos"', response)
|
||||||
# "numVideosText":{"runs":[{"text":"1,234"},{"text":" videos"}]}
|
match = re.search(r'"numVideosText".*?([,\d]+)', response)
|
||||||
# "stats":[..., {"runs":[{"text":"1,234"},{"text":" videos"}]}]
|
if match:
|
||||||
for pattern in (
|
return int(match.group(1).replace(',',''))
|
||||||
r'"numVideosText".*?"text":\s*"([\d,]+)"',
|
else:
|
||||||
r'"numVideosText".*?([\d,]+)\s*videos?',
|
return 0
|
||||||
r'"numVideosText".*?([,\d]+)',
|
|
||||||
r'([\d,]+)\s*videos?\s*</span>',
|
|
||||||
):
|
|
||||||
match = re.search(pattern, response)
|
|
||||||
if match:
|
|
||||||
try:
|
|
||||||
return int(match.group(1).replace(',', ''))
|
|
||||||
except ValueError:
|
|
||||||
continue
|
|
||||||
# Fallback: unknown count
|
|
||||||
return 0
|
|
||||||
def set_cached_number_of_videos(channel_id, num_videos):
|
def set_cached_number_of_videos(channel_id, num_videos):
|
||||||
@cachetools.cached(number_of_videos_cache)
|
@cachetools.cached(number_of_videos_cache)
|
||||||
def dummy_func_using_same_cache(channel_id):
|
def dummy_func_using_same_cache(channel_id):
|
||||||
@@ -328,7 +314,7 @@ def get_channel_id(base_url):
|
|||||||
# method that gives the smallest possible response at ~4 kb
|
# method that gives the smallest possible response at ~4 kb
|
||||||
# needs to be as fast as possible
|
# needs to be as fast as possible
|
||||||
base_url = base_url.replace('https://www', 'https://m') # avoid redirect
|
base_url = base_url.replace('https://www', 'https://m') # avoid redirect
|
||||||
response = util.fetch_url(f'{base_url}/about?pbj=1', headers_mobile,
|
response = util.fetch_url(base_url + '/about?pbj=1', headers_mobile,
|
||||||
debug_name='get_channel_id', report_text='Got channel id').decode('utf-8')
|
debug_name='get_channel_id', report_text='Got channel id').decode('utf-8')
|
||||||
match = channel_id_re.search(response)
|
match = channel_id_re.search(response)
|
||||||
if match:
|
if match:
|
||||||
@@ -372,7 +358,7 @@ def get_channel_search_json(channel_id, query, page):
|
|||||||
ctoken = base64.urlsafe_b64encode(proto.nested(80226972, ctoken)).decode('ascii')
|
ctoken = base64.urlsafe_b64encode(proto.nested(80226972, ctoken)).decode('ascii')
|
||||||
|
|
||||||
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
||||||
url = f'https://www.youtube.com/youtubei/v1/browse?key={key}'
|
url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
|
||||||
|
|
||||||
data = {
|
data = {
|
||||||
'context': {
|
'context': {
|
||||||
@@ -414,18 +400,18 @@ def post_process_channel_info(info):
|
|||||||
|
|
||||||
def get_channel_first_page(base_url=None, tab='videos', channel_id=None, sort=None):
|
def get_channel_first_page(base_url=None, tab='videos', channel_id=None, sort=None):
|
||||||
if channel_id:
|
if channel_id:
|
||||||
base_url = f'https://www.youtube.com/channel/{channel_id}'
|
base_url = 'https://www.youtube.com/channel/' + channel_id
|
||||||
|
|
||||||
# Build URL with sort parameter
|
# Build URL with sort parameter
|
||||||
# YouTube URL sort params: p=popular, dd=newest, lad=newest no shorts
|
# YouTube URL sort params: p=popular, dd=newest, lad=newest no shorts
|
||||||
# Note: 'da' (oldest) was removed by YouTube in January 2026
|
# Note: 'da' (oldest) was removed by YouTube in January 2026
|
||||||
url = f'{base_url}/{tab}?pbj=1&view=0'
|
url = base_url + '/' + tab + '?pbj=1&view=0'
|
||||||
if sort:
|
if sort:
|
||||||
# Map sort values to YouTube's URL parameter values
|
# Map sort values to YouTube's URL parameter values
|
||||||
sort_map = {'3': 'dd', '4': 'lad'}
|
sort_map = {'3': 'dd', '4': 'lad'}
|
||||||
url += f'&sort={sort_map.get(sort, "dd")}'
|
url += '&sort=' + sort_map.get(sort, 'dd')
|
||||||
|
|
||||||
return util.fetch_url(url, headers_desktop, debug_name=f'gen_channel_{tab}')
|
return util.fetch_url(url, headers_desktop, debug_name='gen_channel_' + tab)
|
||||||
|
|
||||||
|
|
||||||
playlist_sort_codes = {'2': "da", '3': "dd", '4': "lad"}
|
playlist_sort_codes = {'2': "da", '3': "dd", '4': "lad"}
|
||||||
@@ -439,35 +425,35 @@ def get_channel_page_general_url(base_url, tab, request, channel_id=None):
|
|||||||
page_number = int(request.args.get('page', 1))
|
page_number = int(request.args.get('page', 1))
|
||||||
# sort 1: views
|
# sort 1: views
|
||||||
# sort 2: oldest
|
# sort 2: oldest
|
||||||
# sort 3: newest (includes shorts, via UU uploads playlist)
|
# sort 4: newest - no shorts (Just a kludge on our end, not internal to yt)
|
||||||
# sort 4: newest - no shorts (uses channel Videos tab API directly, like Invidious)
|
|
||||||
default_sort = '3' if settings.include_shorts_in_channel else '4'
|
default_sort = '3' if settings.include_shorts_in_channel else '4'
|
||||||
sort = request.args.get('sort', default_sort)
|
sort = request.args.get('sort', default_sort)
|
||||||
view = request.args.get('view', '1')
|
view = request.args.get('view', '1')
|
||||||
query = request.args.get('query', '')
|
query = request.args.get('query', '')
|
||||||
ctoken = request.args.get('ctoken', '')
|
ctoken = request.args.get('ctoken', '')
|
||||||
|
include_shorts = (sort != '4')
|
||||||
default_params = (page_number == 1 and sort in ('3', '4') and view == '1')
|
default_params = (page_number == 1 and sort in ('3', '4') and view == '1')
|
||||||
continuation = bool(ctoken)
|
continuation = bool(ctoken) # whether or not we're using a continuation
|
||||||
page_size = 30
|
page_size = 30
|
||||||
|
try_channel_api = True
|
||||||
polymer_json = None
|
polymer_json = None
|
||||||
number_of_videos = 0
|
|
||||||
info = None
|
|
||||||
|
|
||||||
# -------------------------------------------------------------------------
|
# Use the special UU playlist which contains all the channel's uploads
|
||||||
# sort=3: use UU uploads playlist (includes shorts)
|
if tab == 'videos' and sort in ('3', '4'):
|
||||||
# -------------------------------------------------------------------------
|
|
||||||
if tab == 'videos' and sort == '3':
|
|
||||||
if not channel_id:
|
if not channel_id:
|
||||||
channel_id = get_channel_id(base_url)
|
channel_id = get_channel_id(base_url)
|
||||||
if page_number == 1:
|
if page_number == 1 and include_shorts:
|
||||||
tasks = (
|
tasks = (
|
||||||
gevent.spawn(playlist.playlist_first_page,
|
gevent.spawn(playlist.playlist_first_page,
|
||||||
f'UU{channel_id[2:]}',
|
'UU' + channel_id[2:],
|
||||||
report_text='Retrieved channel videos'),
|
report_text='Retrieved channel videos'),
|
||||||
gevent.spawn(get_metadata, channel_id),
|
gevent.spawn(get_metadata, channel_id),
|
||||||
)
|
)
|
||||||
gevent.joinall(tasks)
|
gevent.joinall(tasks)
|
||||||
util.check_gevent_exceptions(*tasks)
|
util.check_gevent_exceptions(*tasks)
|
||||||
|
|
||||||
|
# Ignore the metadata for now, it is cached and will be
|
||||||
|
# recalled later
|
||||||
pl_json = tasks[0].value
|
pl_json = tasks[0].value
|
||||||
pl_info = yt_data_extract.extract_playlist_info(pl_json)
|
pl_info = yt_data_extract.extract_playlist_info(pl_json)
|
||||||
number_of_videos = pl_info['metadata']['video_count']
|
number_of_videos = pl_info['metadata']['video_count']
|
||||||
@@ -477,71 +463,87 @@ def get_channel_page_general_url(base_url, tab, request, channel_id=None):
|
|||||||
set_cached_number_of_videos(channel_id, number_of_videos)
|
set_cached_number_of_videos(channel_id, number_of_videos)
|
||||||
else:
|
else:
|
||||||
tasks = (
|
tasks = (
|
||||||
gevent.spawn(playlist.get_videos, f'UU{channel_id[2:]}',
|
gevent.spawn(playlist.get_videos, 'UU' + channel_id[2:],
|
||||||
page_number, include_shorts=True),
|
page_number, include_shorts=include_shorts),
|
||||||
gevent.spawn(get_metadata, channel_id),
|
gevent.spawn(get_metadata, channel_id),
|
||||||
gevent.spawn(get_number_of_videos_channel, channel_id),
|
gevent.spawn(get_number_of_videos_channel, channel_id),
|
||||||
gevent.spawn(playlist.playlist_first_page, f'UU{channel_id[2:]}',
|
|
||||||
report_text='Retrieved channel video count'),
|
|
||||||
)
|
)
|
||||||
gevent.joinall(tasks)
|
gevent.joinall(tasks)
|
||||||
util.check_gevent_exceptions(*tasks)
|
util.check_gevent_exceptions(*tasks)
|
||||||
|
|
||||||
pl_json = tasks[0].value
|
pl_json = tasks[0].value
|
||||||
pl_info = yt_data_extract.extract_playlist_info(pl_json)
|
pl_info = yt_data_extract.extract_playlist_info(pl_json)
|
||||||
first_page_meta = yt_data_extract.extract_playlist_metadata(tasks[3].value)
|
number_of_videos = tasks[2].value
|
||||||
number_of_videos = (tasks[2].value
|
|
||||||
or first_page_meta.get('video_count')
|
|
||||||
or 0)
|
|
||||||
|
|
||||||
if pl_info['items']:
|
info = pl_info
|
||||||
info = pl_info
|
info['channel_id'] = channel_id
|
||||||
info['channel_id'] = channel_id
|
info['current_tab'] = 'videos'
|
||||||
info['current_tab'] = 'videos'
|
if info['items']: # Success
|
||||||
page_size = 100
|
page_size = 100
|
||||||
# else fall through to the channel browse API below
|
try_channel_api = False
|
||||||
|
else: # Try the first-page method next
|
||||||
|
try_channel_api = True
|
||||||
|
|
||||||
# -------------------------------------------------------------------------
|
# Use the regular channel API
|
||||||
# Channel browse API: sort=4 (videos tab, no shorts), shorts, streams,
|
if tab in ('shorts', 'streams') or (tab=='videos' and try_channel_api):
|
||||||
# or fallback when the UU playlist returned no items.
|
|
||||||
# Uses channel_ctoken_v5 per-tab tokens, mirroring Invidious's approach.
|
|
||||||
# Pagination is driven by the continuation token YouTube returns each page.
|
|
||||||
# -------------------------------------------------------------------------
|
|
||||||
used_channel_api = False
|
|
||||||
if info is None and (
|
|
||||||
tab in ('shorts', 'streams')
|
|
||||||
or (tab == 'videos' and sort == '4')
|
|
||||||
or (tab == 'videos' and sort == '3') # UU-playlist fallback
|
|
||||||
):
|
|
||||||
if not channel_id:
|
if not channel_id:
|
||||||
channel_id = get_channel_id(base_url)
|
channel_id = get_channel_id(base_url)
|
||||||
used_channel_api = True
|
|
||||||
|
|
||||||
# Determine what browse call to make
|
# For shorts/streams, use continuation token from cache or request
|
||||||
if ctoken:
|
if tab in ('shorts', 'streams'):
|
||||||
browse_call = (util.call_youtube_api, 'web', 'browse',
|
if ctoken:
|
||||||
{'continuation': ctoken})
|
# Use ctoken directly from request (passed via pagination)
|
||||||
continuation = True
|
polymer_json = util.call_youtube_api('web', 'browse', {
|
||||||
elif page_number > 1:
|
'continuation': ctoken,
|
||||||
cache_key = (channel_id, tab, sort, page_number - 1)
|
})
|
||||||
cached_ctoken = continuation_token_cache.get(cache_key)
|
continuation = True
|
||||||
if cached_ctoken:
|
elif page_number > 1:
|
||||||
browse_call = (util.call_youtube_api, 'web', 'browse',
|
# For page 2+, get ctoken from cache
|
||||||
{'continuation': cached_ctoken})
|
cache_key = (channel_id, tab, sort, page_number - 1)
|
||||||
|
cached_ctoken = continuation_token_cache.get(cache_key)
|
||||||
|
if cached_ctoken:
|
||||||
|
polymer_json = util.call_youtube_api('web', 'browse', {
|
||||||
|
'continuation': cached_ctoken,
|
||||||
|
})
|
||||||
|
continuation = True
|
||||||
|
else:
|
||||||
|
# Fallback: generate fresh ctoken
|
||||||
|
page_call = (get_channel_tab, channel_id, str(page_number), sort, tab, int(view))
|
||||||
|
continuation = True
|
||||||
|
polymer_json = gevent.spawn(*page_call)
|
||||||
|
polymer_json.join()
|
||||||
|
if polymer_json.exception:
|
||||||
|
raise polymer_json.exception
|
||||||
|
polymer_json = polymer_json.value
|
||||||
else:
|
else:
|
||||||
# Cache miss — restart from page 1 (better than an error)
|
# Page 1: generate fresh ctoken
|
||||||
browse_call = (get_channel_tab, channel_id, '1', sort, tab, int(view))
|
page_call = (get_channel_tab, channel_id, str(page_number), sort, tab, int(view))
|
||||||
continuation = True
|
continuation = True
|
||||||
|
polymer_json = gevent.spawn(*page_call)
|
||||||
|
polymer_json.join()
|
||||||
|
if polymer_json.exception:
|
||||||
|
raise polymer_json.exception
|
||||||
|
polymer_json = polymer_json.value
|
||||||
else:
|
else:
|
||||||
browse_call = (get_channel_tab, channel_id, '1', sort, tab, int(view))
|
# videos tab - original logic
|
||||||
|
page_call = (get_channel_tab, channel_id, str(page_number), sort,
|
||||||
|
tab, int(view))
|
||||||
continuation = True
|
continuation = True
|
||||||
|
|
||||||
# Single browse call; number_of_videos is computed from items actually
|
if tab == 'videos':
|
||||||
# fetched so we don't mislead the user with a total that includes
|
# Only need video count for the videos tab
|
||||||
# shorts (which this branch is explicitly excluding for sort=4).
|
if channel_id:
|
||||||
task = gevent.spawn(*browse_call)
|
num_videos_call = (get_number_of_videos_channel, channel_id)
|
||||||
task.join()
|
else:
|
||||||
util.check_gevent_exceptions(task)
|
num_videos_call = (get_number_of_videos_general, base_url)
|
||||||
polymer_json = task.value
|
tasks = (
|
||||||
|
gevent.spawn(*num_videos_call),
|
||||||
|
gevent.spawn(*page_call),
|
||||||
|
)
|
||||||
|
gevent.joinall(tasks)
|
||||||
|
util.check_gevent_exceptions(*tasks)
|
||||||
|
number_of_videos, polymer_json = tasks[0].value, tasks[1].value
|
||||||
|
# For shorts/streams, polymer_json is already set above, nothing to do here
|
||||||
|
|
||||||
elif tab == 'about':
|
elif tab == 'about':
|
||||||
# polymer_json = util.fetch_url(base_url + '/about?pbj=1', headers_desktop, debug_name='gen_channel_about')
|
# polymer_json = util.fetch_url(base_url + '/about?pbj=1', headers_desktop, debug_name='gen_channel_about')
|
||||||
@@ -567,23 +569,23 @@ def get_channel_page_general_url(base_url, tab, request, channel_id=None):
|
|||||||
elif tab == 'search' and channel_id:
|
elif tab == 'search' and channel_id:
|
||||||
polymer_json = get_channel_search_json(channel_id, query, page_number)
|
polymer_json = get_channel_search_json(channel_id, query, page_number)
|
||||||
elif tab == 'search':
|
elif tab == 'search':
|
||||||
url = f'{base_url}/search?pbj=1&query={urllib.parse.quote(query, safe="")}'
|
url = base_url + '/search?pbj=1&query=' + urllib.parse.quote(query, safe='')
|
||||||
polymer_json = util.fetch_url(url, headers_desktop, debug_name='gen_channel_search')
|
polymer_json = util.fetch_url(url, headers_desktop, debug_name='gen_channel_search')
|
||||||
elif tab != 'videos':
|
elif tab == 'videos':
|
||||||
flask.abort(404, f'Unknown channel tab: {tab}')
|
pass
|
||||||
|
else:
|
||||||
|
flask.abort(404, 'Unknown channel tab: ' + tab)
|
||||||
|
|
||||||
if polymer_json is not None and info is None:
|
if polymer_json is not None:
|
||||||
info = yt_data_extract.extract_channel_info(
|
info = yt_data_extract.extract_channel_info(
|
||||||
json.loads(polymer_json), tab, continuation=continuation
|
json.loads(polymer_json), tab, continuation=continuation
|
||||||
)
|
)
|
||||||
|
|
||||||
if info is None:
|
|
||||||
return flask.render_template('error.html', error_message='Could not retrieve channel data')
|
|
||||||
if info['error'] is not None:
|
if info['error'] is not None:
|
||||||
return flask.render_template('error.html', error_message=info['error'])
|
return flask.render_template('error.html', error_message=info['error'])
|
||||||
|
|
||||||
if channel_id:
|
if channel_id:
|
||||||
info['channel_url'] = f'https://www.youtube.com/channel/{channel_id}'
|
info['channel_url'] = 'https://www.youtube.com/channel/' + channel_id
|
||||||
info['channel_id'] = channel_id
|
info['channel_id'] = channel_id
|
||||||
else:
|
else:
|
||||||
channel_id = info['channel_id']
|
channel_id = info['channel_id']
|
||||||
@@ -608,40 +610,16 @@ def get_channel_page_general_url(base_url, tab, request, channel_id=None):
|
|||||||
item.update(additional_info)
|
item.update(additional_info)
|
||||||
|
|
||||||
if tab in ('videos', 'shorts', 'streams'):
|
if tab in ('videos', 'shorts', 'streams'):
|
||||||
# For any tab using the channel browse API (sort=4, shorts, streams),
|
if tab in ('shorts', 'streams'):
|
||||||
# pagination is driven by the ctoken YouTube returns in the response.
|
# For shorts/streams, use ctoken to determine pagination
|
||||||
# Cache it so the next page request can use it.
|
|
||||||
if info.get('ctoken'):
|
|
||||||
cache_key = (channel_id, tab, sort, page_number)
|
|
||||||
continuation_token_cache[cache_key] = info['ctoken']
|
|
||||||
|
|
||||||
# Determine is_last_page and final number_of_pages.
|
|
||||||
# For channel-API-driven tabs (sort=4, shorts, streams, UU fallback),
|
|
||||||
# YouTube doesn't give us a reliable total filtered count. So instead
|
|
||||||
# of displaying a misleading number (the total-including-shorts from
|
|
||||||
# get_number_of_videos_channel), we count only what we've actually
|
|
||||||
# paged through, and use the ctoken to know whether to show "next".
|
|
||||||
if used_channel_api:
|
|
||||||
info['is_last_page'] = (info.get('ctoken') is None)
|
info['is_last_page'] = (info.get('ctoken') is None)
|
||||||
items_on_page = len(info.get('items', []))
|
number_of_videos = len(info.get('items', []))
|
||||||
items_seen_so_far = (page_number - 1) * page_size + items_on_page
|
# Cache the ctoken for next page
|
||||||
|
|
||||||
# Use accumulated count as the displayed total so "N videos" shown
|
|
||||||
# to the user always matches what they could actually reach.
|
|
||||||
number_of_videos = items_seen_so_far
|
|
||||||
|
|
||||||
# If there's more content, bump by 1 so the Next-page button exists
|
|
||||||
if info.get('ctoken'):
|
if info.get('ctoken'):
|
||||||
number_of_videos = max(number_of_videos,
|
cache_key = (channel_id, tab, sort, page_number)
|
||||||
page_number * page_size + 1)
|
continuation_token_cache[cache_key] = info['ctoken']
|
||||||
# For sort=3 via UU playlist (used_channel_api=False), number_of_videos
|
|
||||||
# was already set from playlist metadata above.
|
|
||||||
|
|
||||||
info['number_of_videos'] = number_of_videos
|
info['number_of_videos'] = number_of_videos
|
||||||
info['number_of_pages'] = math.ceil(number_of_videos / page_size) if number_of_videos else 1
|
info['number_of_pages'] = math.ceil(number_of_videos/page_size) if number_of_videos else 1
|
||||||
# Never show fewer pages than the page the user is actually on
|
|
||||||
if info['number_of_pages'] < page_number:
|
|
||||||
info['number_of_pages'] = page_number
|
|
||||||
info['header_playlist_names'] = local_playlist.get_playlist_names()
|
info['header_playlist_names'] = local_playlist.get_playlist_names()
|
||||||
if tab in ('videos', 'shorts', 'streams', 'playlists'):
|
if tab in ('videos', 'shorts', 'streams', 'playlists'):
|
||||||
info['current_sort'] = sort
|
info['current_sort'] = sort
|
||||||
@@ -663,22 +641,22 @@ def get_channel_page_general_url(base_url, tab, request, channel_id=None):
|
|||||||
@yt_app.route('/channel/<channel_id>/')
|
@yt_app.route('/channel/<channel_id>/')
|
||||||
@yt_app.route('/channel/<channel_id>/<tab>')
|
@yt_app.route('/channel/<channel_id>/<tab>')
|
||||||
def get_channel_page(channel_id, tab='videos'):
|
def get_channel_page(channel_id, tab='videos'):
|
||||||
return get_channel_page_general_url(f'https://www.youtube.com/channel/{channel_id}', tab, request, channel_id)
|
return get_channel_page_general_url('https://www.youtube.com/channel/' + channel_id, tab, request, channel_id)
|
||||||
|
|
||||||
|
|
||||||
@yt_app.route('/user/<username>/')
|
@yt_app.route('/user/<username>/')
|
||||||
@yt_app.route('/user/<username>/<tab>')
|
@yt_app.route('/user/<username>/<tab>')
|
||||||
def get_user_page(username, tab='videos'):
|
def get_user_page(username, tab='videos'):
|
||||||
return get_channel_page_general_url(f'https://www.youtube.com/user/{username}', tab, request)
|
return get_channel_page_general_url('https://www.youtube.com/user/' + username, tab, request)
|
||||||
|
|
||||||
|
|
||||||
@yt_app.route('/c/<custom>/')
|
@yt_app.route('/c/<custom>/')
|
||||||
@yt_app.route('/c/<custom>/<tab>')
|
@yt_app.route('/c/<custom>/<tab>')
|
||||||
def get_custom_c_page(custom, tab='videos'):
|
def get_custom_c_page(custom, tab='videos'):
|
||||||
return get_channel_page_general_url(f'https://www.youtube.com/c/{custom}', tab, request)
|
return get_channel_page_general_url('https://www.youtube.com/c/' + custom, tab, request)
|
||||||
|
|
||||||
|
|
||||||
@yt_app.route('/<custom>')
|
@yt_app.route('/<custom>')
|
||||||
@yt_app.route('/<custom>/<tab>')
|
@yt_app.route('/<custom>/<tab>')
|
||||||
def get_toplevel_custom_page(custom, tab='videos'):
|
def get_toplevel_custom_page(custom, tab='videos'):
|
||||||
return get_channel_page_general_url(f'https://www.youtube.com/{custom}', tab, request)
|
return get_channel_page_general_url('https://www.youtube.com/' + custom, tab, request)
|
||||||
|
|||||||
@@ -104,19 +104,20 @@ def post_process_comments_info(comments_info):
|
|||||||
comment['replies_url'] = None
|
comment['replies_url'] = None
|
||||||
comment['replies_url'] = concat_or_none(
|
comment['replies_url'] = concat_or_none(
|
||||||
util.URL_ORIGIN,
|
util.URL_ORIGIN,
|
||||||
f'/comments?replies=1&ctoken={ctoken}')
|
'/comments?replies=1&ctoken=' + ctoken)
|
||||||
|
|
||||||
if reply_count == 0:
|
if reply_count == 0:
|
||||||
comment['view_replies_text'] = 'Reply'
|
comment['view_replies_text'] = 'Reply'
|
||||||
elif reply_count == 1:
|
elif reply_count == 1:
|
||||||
comment['view_replies_text'] = '1 reply'
|
comment['view_replies_text'] = '1 reply'
|
||||||
else:
|
else:
|
||||||
comment['view_replies_text'] = f'{reply_count} replies'
|
comment['view_replies_text'] = str(reply_count) + ' replies'
|
||||||
|
|
||||||
if comment['approx_like_count'] == '1':
|
if comment['approx_like_count'] == '1':
|
||||||
comment['likes_text'] = '1 like'
|
comment['likes_text'] = '1 like'
|
||||||
else:
|
else:
|
||||||
comment['likes_text'] = f"{comment['approx_like_count']} likes"
|
comment['likes_text'] = (str(comment['approx_like_count'])
|
||||||
|
+ ' likes')
|
||||||
|
|
||||||
comments_info['include_avatars'] = settings.enable_comment_avatars
|
comments_info['include_avatars'] = settings.enable_comment_avatars
|
||||||
if comments_info['ctoken']:
|
if comments_info['ctoken']:
|
||||||
@@ -154,48 +155,48 @@ def post_process_comments_info(comments_info):
|
|||||||
|
|
||||||
|
|
||||||
def video_comments(video_id, sort=0, offset=0, lc='', secret_key=''):
|
def video_comments(video_id, sort=0, offset=0, lc='', secret_key=''):
|
||||||
if not settings.comments_mode:
|
|
||||||
return {}
|
|
||||||
|
|
||||||
# Initialize the result dict up-front so that any exception path below
|
|
||||||
# can safely attach an 'error' field without risking UnboundLocalError.
|
|
||||||
comments_info = {'error': None}
|
|
||||||
try:
|
try:
|
||||||
other_sort_url = (
|
if settings.comments_mode:
|
||||||
f"{util.URL_ORIGIN}/comments?ctoken="
|
comments_info = {'error': None}
|
||||||
f"{make_comment_ctoken(video_id, sort=1 - sort, lc=lc)}"
|
other_sort_url = (
|
||||||
)
|
util.URL_ORIGIN + '/comments?ctoken='
|
||||||
other_sort_text = f'Sort by {"newest" if sort == 0 else "top"}'
|
+ make_comment_ctoken(video_id, sort=1 - sort, lc=lc)
|
||||||
|
)
|
||||||
|
other_sort_text = 'Sort by ' + ('newest' if sort == 0 else 'top')
|
||||||
|
|
||||||
this_sort_url = (f"{util.URL_ORIGIN}/comments?ctoken="
|
this_sort_url = (util.URL_ORIGIN
|
||||||
f"{make_comment_ctoken(video_id, sort=sort, lc=lc)}")
|
+ '/comments?ctoken='
|
||||||
|
+ make_comment_ctoken(video_id, sort=sort, lc=lc))
|
||||||
|
|
||||||
comments_info['comment_links'] = [
|
comments_info['comment_links'] = [
|
||||||
(other_sort_text, other_sort_url),
|
(other_sort_text, other_sort_url),
|
||||||
('Direct link', this_sort_url)
|
('Direct link', this_sort_url)
|
||||||
]
|
]
|
||||||
|
|
||||||
ctoken = make_comment_ctoken(video_id, sort, offset, lc)
|
ctoken = make_comment_ctoken(video_id, sort, offset, lc)
|
||||||
comments_info.update(yt_data_extract.extract_comments_info(
|
comments_info.update(yt_data_extract.extract_comments_info(
|
||||||
request_comments(ctoken), ctoken=ctoken
|
request_comments(ctoken), ctoken=ctoken
|
||||||
))
|
))
|
||||||
post_process_comments_info(comments_info)
|
post_process_comments_info(comments_info)
|
||||||
|
|
||||||
return comments_info
|
return comments_info
|
||||||
|
else:
|
||||||
|
return {}
|
||||||
except util.FetchError as e:
|
except util.FetchError as e:
|
||||||
if e.code == '429' and settings.route_tor:
|
if e.code == '429' and settings.route_tor:
|
||||||
comments_info['error'] = 'Error: YouTube blocked the request because the Tor exit node is overutilized.'
|
comments_info['error'] = 'Error: YouTube blocked the request because the Tor exit node is overutilized.'
|
||||||
if e.error_message:
|
if e.error_message:
|
||||||
comments_info['error'] += f'\n\n{e.error_message}'
|
comments_info['error'] += '\n\n' + e.error_message
|
||||||
comments_info['error'] += f'\n\nExit node IP address: {e.ip}'
|
comments_info['error'] += '\n\nExit node IP address: %s' % e.ip
|
||||||
else:
|
else:
|
||||||
comments_info['error'] = f'YouTube blocked the request. Error: {e}'
|
comments_info['error'] = 'YouTube blocked the request. Error: %s' % str(e)
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
comments_info['error'] = f'YouTube blocked the request. Error: {e}'
|
comments_info['error'] = 'YouTube blocked the request. Error: %s' % str(e)
|
||||||
|
|
||||||
if comments_info.get('error'):
|
if comments_info.get('error'):
|
||||||
print(f'Error retrieving comments for {video_id}:\n{comments_info["error"]}')
|
print('Error retrieving comments for ' + str(video_id) + ':\n' +
|
||||||
|
comments_info['error'])
|
||||||
|
|
||||||
return comments_info
|
return comments_info
|
||||||
|
|
||||||
@@ -215,10 +216,12 @@ def get_comments_page():
|
|||||||
other_sort_url = None
|
other_sort_url = None
|
||||||
else:
|
else:
|
||||||
other_sort_url = (
|
other_sort_url = (
|
||||||
f'{util.URL_ORIGIN}/comments?ctoken='
|
util.URL_ORIGIN
|
||||||
f'{make_comment_ctoken(comments_info["video_id"], sort=1-comments_info["sort"])}'
|
+ '/comments?ctoken='
|
||||||
|
+ make_comment_ctoken(comments_info['video_id'],
|
||||||
|
sort=1-comments_info['sort'])
|
||||||
)
|
)
|
||||||
other_sort_text = f'Sort by {"newest" if comments_info["sort"] == 0 else "top"}'
|
other_sort_text = 'Sort by ' + ('newest' if comments_info['sort'] == 0 else 'top')
|
||||||
comments_info['comment_links'] = [(other_sort_text, other_sort_url)]
|
comments_info['comment_links'] = [(other_sort_text, other_sort_url)]
|
||||||
|
|
||||||
return flask.render_template(
|
return flask.render_template(
|
||||||
|
|||||||
@@ -1,3 +1 @@
|
|||||||
from .get_app_version import app_version
|
from .get_app_version import *
|
||||||
|
|
||||||
__all__ = ['app_version']
|
|
||||||
|
|||||||
@@ -1,9 +1,11 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
import os
|
from subprocess import (
|
||||||
import shutil
|
call,
|
||||||
import subprocess
|
STDOUT
|
||||||
|
)
|
||||||
from ..version import __version__
|
from ..version import __version__
|
||||||
|
import os
|
||||||
|
import subprocess
|
||||||
|
|
||||||
|
|
||||||
def app_version():
|
def app_version():
|
||||||
@@ -11,46 +13,35 @@ def app_version():
|
|||||||
# make minimal environment
|
# make minimal environment
|
||||||
env = {k: os.environ[k] for k in ['SYSTEMROOT', 'PATH'] if k in os.environ}
|
env = {k: os.environ[k] for k in ['SYSTEMROOT', 'PATH'] if k in os.environ}
|
||||||
env.update({'LANGUAGE': 'C', 'LANG': 'C', 'LC_ALL': 'C'})
|
env.update({'LANGUAGE': 'C', 'LANG': 'C', 'LC_ALL': 'C'})
|
||||||
|
|
||||||
out = subprocess.Popen(cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
|
out = subprocess.Popen(cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
|
||||||
return out
|
return out
|
||||||
|
|
||||||
subst_list = {
|
subst_list = {
|
||||||
'version': __version__,
|
"version": __version__,
|
||||||
'branch': None,
|
"branch": None,
|
||||||
'commit': None,
|
"commit": None
|
||||||
}
|
}
|
||||||
|
|
||||||
# Use shutil.which instead of `command -v`/os.system so we don't spawn a
|
if os.system("command -v git > /dev/null 2>&1") != 0:
|
||||||
# shell (CWE-78 hardening) and so it works cross-platform.
|
|
||||||
if shutil.which('git') is None:
|
|
||||||
return subst_list
|
return subst_list
|
||||||
|
|
||||||
try:
|
if call(["git", "branch"], stderr=STDOUT, stdout=open(os.devnull, 'w')) != 0:
|
||||||
# Check we are inside a git work tree. Using DEVNULL avoids the
|
|
||||||
# file-handle leak from `open(os.devnull, 'w')`.
|
|
||||||
rc = subprocess.call(
|
|
||||||
['git', 'branch'],
|
|
||||||
stderr=subprocess.DEVNULL,
|
|
||||||
stdout=subprocess.DEVNULL,
|
|
||||||
)
|
|
||||||
except OSError:
|
|
||||||
return subst_list
|
|
||||||
if rc != 0:
|
|
||||||
return subst_list
|
return subst_list
|
||||||
|
|
||||||
describe = minimal_env_cmd(['git', 'describe', '--tags', '--always'])
|
describe = minimal_env_cmd(["git", "describe", "--tags", "--always"])
|
||||||
git_revision = describe.strip().decode('ascii')
|
git_revision = describe.strip().decode('ascii')
|
||||||
|
|
||||||
branch = minimal_env_cmd(['git', 'branch'])
|
branch = minimal_env_cmd(["git", "branch"])
|
||||||
git_branch = branch.strip().decode('ascii').replace('* ', '')
|
git_branch = branch.strip().decode('ascii').replace('* ', '')
|
||||||
|
|
||||||
subst_list.update({
|
subst_list.update({
|
||||||
'branch': git_branch,
|
"branch": git_branch,
|
||||||
'commit': git_revision,
|
"commit": git_revision
|
||||||
})
|
})
|
||||||
|
|
||||||
return subst_list
|
return subst_list
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == "__main__":
|
||||||
app_version()
|
app_version()
|
||||||
|
|||||||
@@ -1,42 +1,28 @@
|
|||||||
from youtube import util
|
from youtube import util, yt_data_extract
|
||||||
from youtube import yt_app
|
from youtube import yt_app
|
||||||
import settings
|
import settings
|
||||||
|
|
||||||
import os
|
import os
|
||||||
import json
|
import json
|
||||||
|
import html
|
||||||
import gevent
|
import gevent
|
||||||
|
import urllib
|
||||||
import math
|
import math
|
||||||
import glob
|
import glob
|
||||||
import re
|
|
||||||
|
|
||||||
import flask
|
import flask
|
||||||
from flask import request
|
from flask import request
|
||||||
|
|
||||||
playlists_directory = os.path.join(settings.data_dir, 'playlists')
|
playlists_directory = os.path.join(settings.data_dir, "playlists")
|
||||||
thumbnails_directory = os.path.join(settings.data_dir, 'playlist_thumbnails')
|
thumbnails_directory = os.path.join(settings.data_dir, "playlist_thumbnails")
|
||||||
|
|
||||||
# Whitelist accepted playlist names so user input cannot escape
|
|
||||||
# `playlists_directory` / `thumbnails_directory` (CWE-22, OWASP A01:2021).
|
|
||||||
# Allow letters, digits, spaces, dot, dash and underscore.
|
|
||||||
_PLAYLIST_NAME_RE = re.compile(r'^[\w .\-]{1,128}$')
|
|
||||||
|
|
||||||
|
|
||||||
def _validate_playlist_name(name):
|
|
||||||
'''Return the stripped name if safe, otherwise abort with 400.'''
|
|
||||||
if name is None:
|
|
||||||
flask.abort(400)
|
|
||||||
name = name.strip()
|
|
||||||
if not _PLAYLIST_NAME_RE.match(name):
|
|
||||||
flask.abort(400)
|
|
||||||
return name
|
|
||||||
|
|
||||||
|
|
||||||
def _find_playlist_path(name):
|
def _find_playlist_path(name):
|
||||||
'''Find playlist file robustly, handling trailing spaces in filenames'''
|
"""Find playlist file robustly, handling trailing spaces in filenames"""
|
||||||
name = _validate_playlist_name(name)
|
name = name.strip()
|
||||||
pattern = os.path.join(playlists_directory, name + '*.txt')
|
pattern = os.path.join(playlists_directory, name + "*.txt")
|
||||||
files = glob.glob(pattern)
|
files = glob.glob(pattern)
|
||||||
return files[0] if files else os.path.join(playlists_directory, name + '.txt')
|
return files[0] if files else os.path.join(playlists_directory, name + ".txt")
|
||||||
|
|
||||||
|
|
||||||
def _parse_playlist_lines(data):
|
def _parse_playlist_lines(data):
|
||||||
@@ -92,7 +78,9 @@ def add_extra_info_to_videos(videos, playlist_name):
|
|||||||
util.add_extra_html_info(video)
|
util.add_extra_html_info(video)
|
||||||
if video['id'] + '.jpg' in thumbnails:
|
if video['id'] + '.jpg' in thumbnails:
|
||||||
video['thumbnail'] = (
|
video['thumbnail'] = (
|
||||||
f'/https://youtube.com/data/playlist_thumbnails/{playlist_name}/{video["id"]}.jpg')
|
'/https://youtube.com/data/playlist_thumbnails/'
|
||||||
|
+ playlist_name
|
||||||
|
+ '/' + video['id'] + '.jpg')
|
||||||
else:
|
else:
|
||||||
video['thumbnail'] = util.get_thumbnail_url(video['id'])
|
video['thumbnail'] = util.get_thumbnail_url(video['id'])
|
||||||
missing_thumbnails.append(video['id'])
|
missing_thumbnails.append(video['id'])
|
||||||
@@ -191,9 +179,8 @@ def path_edit_playlist(playlist_name):
|
|||||||
redirect_page_number = min(int(request.values.get('page', 1)), math.ceil(number_of_videos_remaining/50))
|
redirect_page_number = min(int(request.values.get('page', 1)), math.ceil(number_of_videos_remaining/50))
|
||||||
return flask.redirect(util.URL_ORIGIN + request.path + '?page=' + str(redirect_page_number))
|
return flask.redirect(util.URL_ORIGIN + request.path + '?page=' + str(redirect_page_number))
|
||||||
elif request.values['action'] == 'remove_playlist':
|
elif request.values['action'] == 'remove_playlist':
|
||||||
safe_name = _validate_playlist_name(playlist_name)
|
|
||||||
try:
|
try:
|
||||||
os.remove(os.path.join(playlists_directory, safe_name + '.txt'))
|
os.remove(os.path.join(playlists_directory, playlist_name + ".txt"))
|
||||||
except OSError:
|
except OSError:
|
||||||
pass
|
pass
|
||||||
return flask.redirect(util.URL_ORIGIN + '/playlists')
|
return flask.redirect(util.URL_ORIGIN + '/playlists')
|
||||||
@@ -233,17 +220,8 @@ def edit_playlist():
|
|||||||
flask.abort(400)
|
flask.abort(400)
|
||||||
|
|
||||||
|
|
||||||
_THUMBNAIL_RE = re.compile(r'^[A-Za-z0-9_-]{11}\.jpg$')
|
|
||||||
|
|
||||||
|
|
||||||
@yt_app.route('/data/playlist_thumbnails/<playlist_name>/<thumbnail>')
|
@yt_app.route('/data/playlist_thumbnails/<playlist_name>/<thumbnail>')
|
||||||
def serve_thumbnail(playlist_name, thumbnail):
|
def serve_thumbnail(playlist_name, thumbnail):
|
||||||
# Validate both path components so a crafted URL cannot escape
|
# .. is necessary because flask always uses the application directory at ./youtube, not the working directory
|
||||||
# `thumbnails_directory` via `..` or NUL tricks (CWE-22).
|
|
||||||
safe_name = _validate_playlist_name(playlist_name)
|
|
||||||
if not _THUMBNAIL_RE.match(thumbnail):
|
|
||||||
flask.abort(400)
|
|
||||||
# .. is necessary because flask always uses the application directory at
|
|
||||||
# ./youtube, not the working directory.
|
|
||||||
return flask.send_from_directory(
|
return flask.send_from_directory(
|
||||||
os.path.join('..', thumbnails_directory, safe_name), thumbnail)
|
os.path.join('..', thumbnails_directory, playlist_name), thumbnail)
|
||||||
|
|||||||
@@ -3,7 +3,9 @@ from youtube import yt_app
|
|||||||
import settings
|
import settings
|
||||||
|
|
||||||
import base64
|
import base64
|
||||||
|
import urllib
|
||||||
import json
|
import json
|
||||||
|
import string
|
||||||
import gevent
|
import gevent
|
||||||
import math
|
import math
|
||||||
from flask import request, abort
|
from flask import request, abort
|
||||||
@@ -20,7 +22,7 @@ def playlist_ctoken(playlist_id, offset, include_shorts=True):
|
|||||||
|
|
||||||
continuation_info = proto.string(3, proto.percent_b64encode(offset))
|
continuation_info = proto.string(3, proto.percent_b64encode(offset))
|
||||||
|
|
||||||
playlist_id = proto.string(2, f'VL{playlist_id}')
|
playlist_id = proto.string(2, 'VL' + playlist_id)
|
||||||
pointless_nest = proto.string(80226972, playlist_id + continuation_info)
|
pointless_nest = proto.string(80226972, playlist_id + continuation_info)
|
||||||
|
|
||||||
return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
|
return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
|
||||||
@@ -30,7 +32,7 @@ def playlist_first_page(playlist_id, report_text="Retrieved playlist",
|
|||||||
use_mobile=False):
|
use_mobile=False):
|
||||||
# Use innertube API (pbj=1 no longer works for many playlists)
|
# Use innertube API (pbj=1 no longer works for many playlists)
|
||||||
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
||||||
url = f'https://www.youtube.com/youtubei/v1/browse?key={key}'
|
url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
|
||||||
|
|
||||||
data = {
|
data = {
|
||||||
'context': {
|
'context': {
|
||||||
@@ -41,7 +43,7 @@ def playlist_first_page(playlist_id, report_text="Retrieved playlist",
|
|||||||
'clientVersion': '2.20240327.00.00',
|
'clientVersion': '2.20240327.00.00',
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
'browseId': f'VL{playlist_id}',
|
'browseId': 'VL' + playlist_id,
|
||||||
}
|
}
|
||||||
|
|
||||||
content_type_header = (('Content-Type', 'application/json'),)
|
content_type_header = (('Content-Type', 'application/json'),)
|
||||||
@@ -58,7 +60,7 @@ def get_videos(playlist_id, page, include_shorts=True, use_mobile=False,
|
|||||||
page_size = 100
|
page_size = 100
|
||||||
|
|
||||||
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
|
||||||
url = f'https://www.youtube.com/youtubei/v1/browse?key={key}'
|
url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
|
||||||
|
|
||||||
ctoken = playlist_ctoken(playlist_id, (int(page)-1)*page_size,
|
ctoken = playlist_ctoken(playlist_id, (int(page)-1)*page_size,
|
||||||
include_shorts=include_shorts)
|
include_shorts=include_shorts)
|
||||||
@@ -97,7 +99,7 @@ def get_playlist_page():
|
|||||||
if playlist_id.startswith('RD'):
|
if playlist_id.startswith('RD'):
|
||||||
first_video_id = playlist_id[2:] # video ID after 'RD' prefix
|
first_video_id = playlist_id[2:] # video ID after 'RD' prefix
|
||||||
return flask.redirect(
|
return flask.redirect(
|
||||||
f'{util.URL_ORIGIN}/watch?v={first_video_id}&list={playlist_id}',
|
util.URL_ORIGIN + '/watch?v=' + first_video_id + '&list=' + playlist_id,
|
||||||
302
|
302
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -132,9 +134,9 @@ def get_playlist_page():
|
|||||||
if 'id' in item and not item.get('thumbnail'):
|
if 'id' in item and not item.get('thumbnail'):
|
||||||
item['thumbnail'] = f"{settings.img_prefix}https://i.ytimg.com/vi/{item['id']}/hqdefault.jpg"
|
item['thumbnail'] = f"{settings.img_prefix}https://i.ytimg.com/vi/{item['id']}/hqdefault.jpg"
|
||||||
|
|
||||||
item['url'] += f'&list={playlist_id}'
|
item['url'] += '&list=' + playlist_id
|
||||||
if item['index']:
|
if item['index']:
|
||||||
item['url'] += f'&index={item["index"]}'
|
item['url'] += '&index=' + str(item['index'])
|
||||||
|
|
||||||
video_count = yt_data_extract.deep_get(info, 'metadata', 'video_count')
|
video_count = yt_data_extract.deep_get(info, 'metadata', 'video_count')
|
||||||
if video_count is None:
|
if video_count is None:
|
||||||
|
|||||||
@@ -76,7 +76,7 @@ def read_varint(data):
|
|||||||
except IndexError:
|
except IndexError:
|
||||||
if i == 0:
|
if i == 0:
|
||||||
raise EOFError()
|
raise EOFError()
|
||||||
raise Exception(f'Unterminated varint starting at {data.tell() - i}')
|
raise Exception('Unterminated varint starting at ' + str(data.tell() - i))
|
||||||
result |= (byte & 127) << 7*i
|
result |= (byte & 127) << 7*i
|
||||||
if not byte & 128:
|
if not byte & 128:
|
||||||
break
|
break
|
||||||
@@ -118,7 +118,7 @@ def read_protobuf(data):
|
|||||||
elif wire_type == 5:
|
elif wire_type == 5:
|
||||||
value = data.read(4)
|
value = data.read(4)
|
||||||
else:
|
else:
|
||||||
raise Exception(f"Unknown wire type: {wire_type} at position {data.tell()}")
|
raise Exception("Unknown wire type: " + str(wire_type) + " at position " + str(data.tell()))
|
||||||
yield (wire_type, field_number, value)
|
yield (wire_type, field_number, value)
|
||||||
|
|
||||||
|
|
||||||
@@ -170,7 +170,8 @@ def _make_protobuf(data):
|
|||||||
elif field[0] == 2:
|
elif field[0] == 2:
|
||||||
result += string(field[1], _make_protobuf(field[2]))
|
result += string(field[1], _make_protobuf(field[2]))
|
||||||
else:
|
else:
|
||||||
raise NotImplementedError(f'Wire type {field[0]} not implemented')
|
raise NotImplementedError('Wire type ' + str(field[0])
|
||||||
|
+ ' not implemented')
|
||||||
return result
|
return result
|
||||||
return data
|
return data
|
||||||
|
|
||||||
@@ -217,4 +218,4 @@ def b64_to_bytes(data):
|
|||||||
if isinstance(data, bytes):
|
if isinstance(data, bytes):
|
||||||
data = data.decode('ascii')
|
data = data.decode('ascii')
|
||||||
data = data.replace("%3D", "=")
|
data = data.replace("%3D", "=")
|
||||||
return base64.urlsafe_b64decode(f'{data}={"=" * ((4 - len(data) % 4) % 4)}')
|
return base64.urlsafe_b64decode(data + "="*((4 - len(data) % 4) % 4))
|
||||||
|
|||||||
@@ -179,7 +179,7 @@ def read_varint(data):
|
|||||||
except IndexError:
|
except IndexError:
|
||||||
if i == 0:
|
if i == 0:
|
||||||
raise EOFError()
|
raise EOFError()
|
||||||
raise Exception(f'Unterminated varint starting at {data.tell() - i}')
|
raise Exception('Unterminated varint starting at ' + str(data.tell() - i))
|
||||||
result |= (byte & 127) << 7*i
|
result |= (byte & 127) << 7*i
|
||||||
if not byte & 128:
|
if not byte & 128:
|
||||||
break
|
break
|
||||||
@@ -235,7 +235,8 @@ def _make_protobuf(data):
|
|||||||
elif field[0] == 2:
|
elif field[0] == 2:
|
||||||
result += string(field[1], _make_protobuf(field[2]))
|
result += string(field[1], _make_protobuf(field[2]))
|
||||||
else:
|
else:
|
||||||
raise NotImplementedError(f'Wire type {field[0]} not implemented')
|
raise NotImplementedError('Wire type ' + str(field[0])
|
||||||
|
+ ' not implemented')
|
||||||
return result
|
return result
|
||||||
return data
|
return data
|
||||||
|
|
||||||
@@ -285,7 +286,7 @@ def b64_to_bytes(data):
|
|||||||
if isinstance(data, bytes):
|
if isinstance(data, bytes):
|
||||||
data = data.decode('ascii')
|
data = data.decode('ascii')
|
||||||
data = data.replace("%3D", "=")
|
data = data.replace("%3D", "=")
|
||||||
return base64.urlsafe_b64decode(f'{data}={"=" * ((4 - len(data) % 4) % 4)}')
|
return base64.urlsafe_b64decode(data + "="*((4 - len(data) % 4) % 4))
|
||||||
# --------------------------------------------------------------------
|
# --------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
@@ -343,7 +344,7 @@ fromhex = bytes.fromhex
|
|||||||
|
|
||||||
|
|
||||||
def aligned_ascii(data):
|
def aligned_ascii(data):
|
||||||
return ' '.join(f' {chr(n)}' if n in range(32, 128) else ' _' for n in data)
|
return ' '.join(' ' + chr(n) if n in range(32, 128) else ' _' for n in data)
|
||||||
|
|
||||||
|
|
||||||
def parse_protobuf(data, mutable=False, spec=()):
|
def parse_protobuf(data, mutable=False, spec=()):
|
||||||
@@ -371,7 +372,7 @@ def parse_protobuf(data, mutable=False, spec=()):
|
|||||||
elif wire_type == 5:
|
elif wire_type == 5:
|
||||||
value = data.read(4)
|
value = data.read(4)
|
||||||
else:
|
else:
|
||||||
raise Exception(f"Unknown wire type: {wire_type}, Tag: {bytes_to_hex(varint_encode(tag))}, at position {data.tell()}")
|
raise Exception("Unknown wire type: " + str(wire_type) + ", Tag: " + bytes_to_hex(varint_encode(tag)) + ", at position " + str(data.tell()))
|
||||||
if mutable:
|
if mutable:
|
||||||
yield [wire_type, field_number, value]
|
yield [wire_type, field_number, value]
|
||||||
else:
|
else:
|
||||||
@@ -452,7 +453,7 @@ def b32decode(s, casefold=False, map01=None):
|
|||||||
if map01 is not None:
|
if map01 is not None:
|
||||||
map01 = _bytes_from_decode_data(map01)
|
map01 = _bytes_from_decode_data(map01)
|
||||||
assert len(map01) == 1, repr(map01)
|
assert len(map01) == 1, repr(map01)
|
||||||
s = s.translate(bytes.maketrans(b'01', f'O{map01.decode("ascii")}'))
|
s = s.translate(bytes.maketrans(b'01', b'O' + map01))
|
||||||
if casefold:
|
if casefold:
|
||||||
s = s.upper()
|
s = s.upper()
|
||||||
# Strip off pad characters from the right. We need to count the pad
|
# Strip off pad characters from the right. We need to count the pad
|
||||||
@@ -493,7 +494,7 @@ def b32decode(s, casefold=False, map01=None):
|
|||||||
def dec32(data):
|
def dec32(data):
|
||||||
if isinstance(data, bytes):
|
if isinstance(data, bytes):
|
||||||
data = data.decode('ascii')
|
data = data.decode('ascii')
|
||||||
return b32decode(f'{data}={"=" * ((8 - len(data)%8)%8)}')
|
return b32decode(data + "="*((8 - len(data)%8)%8))
|
||||||
|
|
||||||
|
|
||||||
_patterns = [
|
_patterns = [
|
||||||
@@ -562,7 +563,9 @@ def _pp(obj, indent): # not my best work
|
|||||||
if len(obj) == 3: # (wire_type, field_number, data)
|
if len(obj) == 3: # (wire_type, field_number, data)
|
||||||
return obj.__repr__()
|
return obj.__repr__()
|
||||||
else: # (base64, [...])
|
else: # (base64, [...])
|
||||||
return f"({obj[0].__repr__()},\n{indent_lines(_pp(obj[1], indent), indent)}\n)"
|
return ('(' + obj[0].__repr__() + ',\n'
|
||||||
|
+ indent_lines(_pp(obj[1], indent), indent) + '\n'
|
||||||
|
+ ')')
|
||||||
elif isinstance(obj, list):
|
elif isinstance(obj, list):
|
||||||
# [wire_type, field_number, data]
|
# [wire_type, field_number, data]
|
||||||
if (len(obj) == 3
|
if (len(obj) == 3
|
||||||
@@ -574,11 +577,13 @@ def _pp(obj, indent): # not my best work
|
|||||||
elif (len(obj) == 3
|
elif (len(obj) == 3
|
||||||
and not any(isinstance(x, (list, tuple)) for x in obj[0:2])
|
and not any(isinstance(x, (list, tuple)) for x in obj[0:2])
|
||||||
):
|
):
|
||||||
return f"[{obj[0].__repr__()}, {obj[1].__repr__()},\n{indent_lines(_pp(obj[2], indent), indent)}\n]"
|
return ('[' + obj[0].__repr__() + ', ' + obj[1].__repr__() + ',\n'
|
||||||
|
+ indent_lines(_pp(obj[2], indent), indent) + '\n'
|
||||||
|
+ ']')
|
||||||
else:
|
else:
|
||||||
s = '[\n'
|
s = '[\n'
|
||||||
for x in obj:
|
for x in obj:
|
||||||
s += f"{indent_lines(_pp(x, indent), indent)},\n"
|
s += indent_lines(_pp(x, indent), indent) + ',\n'
|
||||||
s += ']'
|
s += ']'
|
||||||
return s
|
return s
|
||||||
else:
|
else:
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ import settings
|
|||||||
import json
|
import json
|
||||||
import urllib
|
import urllib
|
||||||
import base64
|
import base64
|
||||||
|
import mimetypes
|
||||||
from flask import request
|
from flask import request
|
||||||
import flask
|
import flask
|
||||||
import os
|
import os
|
||||||
@@ -51,7 +52,7 @@ def get_search_json(query, page, autocorrect, sort, filters):
|
|||||||
'X-YouTube-Client-Name': '1',
|
'X-YouTube-Client-Name': '1',
|
||||||
'X-YouTube-Client-Version': '2.20180418',
|
'X-YouTube-Client-Version': '2.20180418',
|
||||||
}
|
}
|
||||||
url += f"&pbj=1&sp={page_number_to_sp_parameter(page, autocorrect, sort, filters).replace('=', '%3D')}"
|
url += "&pbj=1&sp=" + page_number_to_sp_parameter(page, autocorrect, sort, filters).replace("=", "%3D")
|
||||||
content = util.fetch_url(url, headers=headers, report_text="Got search results", debug_name='search_results')
|
content = util.fetch_url(url, headers=headers, report_text="Got search results", debug_name='search_results')
|
||||||
info = json.loads(content)
|
info = json.loads(content)
|
||||||
return info
|
return info
|
||||||
|
|||||||
@@ -9,8 +9,6 @@
|
|||||||
--thumb-background: #222222;
|
--thumb-background: #222222;
|
||||||
--link: #00B0FF;
|
--link: #00B0FF;
|
||||||
--link-visited: #40C4FF;
|
--link-visited: #40C4FF;
|
||||||
--border-color: #333333;
|
|
||||||
--thead-background: #0a0a0b;
|
|
||||||
--border-bg: #222222;
|
--border-bg: #222222;
|
||||||
--border-bg-settings: #000000;
|
--border-bg-settings: #000000;
|
||||||
--border-bg-license: #000000;
|
--border-bg-license: #000000;
|
||||||
|
|||||||
@@ -9,8 +9,6 @@
|
|||||||
--thumb-background: #35404D;
|
--thumb-background: #35404D;
|
||||||
--link: #22AAFF;
|
--link: #22AAFF;
|
||||||
--link-visited: #7755FF;
|
--link-visited: #7755FF;
|
||||||
--border-color: #4A5568;
|
|
||||||
--thead-background: #1a2530;
|
|
||||||
--border-bg: #FFFFFF;
|
--border-bg: #FFFFFF;
|
||||||
--border-bg-settings: #FFFFFF;
|
--border-bg-settings: #FFFFFF;
|
||||||
--border-bg-license: #FFFFFF;
|
--border-bg-license: #FFFFFF;
|
||||||
|
|||||||
@@ -9,8 +9,6 @@
|
|||||||
--thumb-background: #F5F5F5;
|
--thumb-background: #F5F5F5;
|
||||||
--link: #212121;
|
--link: #212121;
|
||||||
--link-visited: #808080;
|
--link-visited: #808080;
|
||||||
--border-color: #CCCCCC;
|
|
||||||
--thead-background: #d0d0d0;
|
|
||||||
--border-bg: #212121;
|
--border-bg: #212121;
|
||||||
--border-bg-settings: #91918C;
|
--border-bg-settings: #91918C;
|
||||||
--border-bg-license: #91918C;
|
--border-bg-license: #91918C;
|
||||||
|
|||||||
@@ -307,122 +307,18 @@ figure.sc-video {
|
|||||||
padding-top: 0.5rem;
|
padding-top: 0.5rem;
|
||||||
padding-bottom: 0.5rem;
|
padding-bottom: 0.5rem;
|
||||||
}
|
}
|
||||||
.v-download {
|
.v-download { grid-area: v-download; }
|
||||||
grid-area: v-download;
|
.v-download > ul.download-dropdown-content {
|
||||||
margin-bottom: 0.5rem;
|
background: var(--secondary-background);
|
||||||
|
padding-left: 0px;
|
||||||
}
|
}
|
||||||
.v-download details {
|
.v-download > ul.download-dropdown-content > li.download-format {
|
||||||
display: block;
|
list-style: none;
|
||||||
width: 100%;
|
|
||||||
}
|
|
||||||
.v-download > summary {
|
|
||||||
cursor: pointer;
|
|
||||||
padding: 0.4rem 0;
|
padding: 0.4rem 0;
|
||||||
padding-left: 1rem;
|
padding-left: 1rem;
|
||||||
}
|
}
|
||||||
.v-download > summary.download-dropdown-label {
|
.v-download > ul.download-dropdown-content > li.download-format a.download-link {
|
||||||
cursor: pointer;
|
|
||||||
-webkit-touch-callout: none;
|
|
||||||
-webkit-user-select: none;
|
|
||||||
-khtml-user-select: none;
|
|
||||||
-moz-user-select: none;
|
|
||||||
-ms-user-select: none;
|
|
||||||
user-select: none;
|
|
||||||
padding-bottom: 6px;
|
|
||||||
padding-left: .75em;
|
|
||||||
padding-right: .75em;
|
|
||||||
padding-top: 6px;
|
|
||||||
text-align: center;
|
|
||||||
white-space: nowrap;
|
|
||||||
background-color: var(--buttom);
|
|
||||||
border: 1px solid var(--button-border);
|
|
||||||
color: var(--buttom-text);
|
|
||||||
border-radius: 5px;
|
|
||||||
margin-bottom: 0.5rem;
|
|
||||||
}
|
|
||||||
.v-download > summary.download-dropdown-label:hover {
|
|
||||||
background-color: var(--buttom-hover);
|
|
||||||
}
|
|
||||||
.v-download > .download-table-container {
|
|
||||||
background: var(--secondary-background);
|
|
||||||
max-height: 65vh;
|
|
||||||
overflow-y: auto;
|
|
||||||
border: 1px solid var(--button-border);
|
|
||||||
border-radius: 8px;
|
|
||||||
box-shadow: 0 4px 12px rgba(0,0,0,0.15);
|
|
||||||
}
|
|
||||||
.download-table {
|
|
||||||
width: 100%;
|
|
||||||
border-collapse: separate;
|
|
||||||
border-spacing: 0;
|
|
||||||
font-size: 0.875rem;
|
|
||||||
}
|
|
||||||
.download-table thead {
|
|
||||||
background: var(--thead-background);
|
|
||||||
position: sticky;
|
|
||||||
top: 0;
|
|
||||||
z-index: 1;
|
|
||||||
}
|
|
||||||
.download-table th,
|
|
||||||
.download-table td {
|
|
||||||
padding: 0.7rem 0.9rem;
|
|
||||||
text-align: left;
|
|
||||||
border-bottom: 1px solid var(--button-border);
|
|
||||||
}
|
|
||||||
.download-table th {
|
|
||||||
font-weight: 600;
|
|
||||||
font-size: 0.7rem;
|
|
||||||
text-transform: uppercase;
|
|
||||||
letter-spacing: 0.8px;
|
|
||||||
}
|
|
||||||
.download-table tbody tr {
|
|
||||||
transition: all 0.2s ease;
|
|
||||||
}
|
|
||||||
.download-table tbody tr:hover {
|
|
||||||
background: var(--primary-background);
|
|
||||||
}
|
|
||||||
.download-table a.download-link {
|
|
||||||
display: inline-block;
|
|
||||||
padding: 0.4rem 0.85rem;
|
|
||||||
background: rgba(0,0,0,0.12);
|
|
||||||
color: var(--buttom-text);
|
|
||||||
text-decoration: none;
|
text-decoration: none;
|
||||||
border-radius: 5px;
|
|
||||||
font-weight: 500;
|
|
||||||
font-size: 0.85rem;
|
|
||||||
transition: background 0.2s ease;
|
|
||||||
white-space: nowrap;
|
|
||||||
}
|
|
||||||
.download-table a.download-link:hover {
|
|
||||||
background: rgba(0,0,0,0.28);
|
|
||||||
color: var(--buttom-text);
|
|
||||||
}
|
|
||||||
.download-table tbody tr:last-child td {
|
|
||||||
border-bottom: none;
|
|
||||||
}
|
|
||||||
.download-table td[data-label="Ext"] {
|
|
||||||
font-family: monospace;
|
|
||||||
font-size: 0.8rem;
|
|
||||||
font-weight: 600;
|
|
||||||
}
|
|
||||||
.download-table td[data-label="Link"] {
|
|
||||||
white-space: nowrap;
|
|
||||||
vertical-align: middle;
|
|
||||||
}
|
|
||||||
.download-table td[data-label="Codecs"] {
|
|
||||||
max-width: 180px;
|
|
||||||
text-overflow: ellipsis;
|
|
||||||
overflow: hidden;
|
|
||||||
font-family: monospace;
|
|
||||||
font-size: 0.75rem;
|
|
||||||
}
|
|
||||||
.download-table td[data-label="Size"] {
|
|
||||||
font-family: monospace;
|
|
||||||
font-size: 0.85rem;
|
|
||||||
}
|
|
||||||
.download-table td[colspan="3"] {
|
|
||||||
font-style: italic;
|
|
||||||
opacity: 0.7;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
.v-description {
|
.v-description {
|
||||||
|
|||||||
@@ -126,7 +126,7 @@ def delete_thumbnails(to_delete):
|
|||||||
os.remove(os.path.join(thumbnails_directory, thumbnail))
|
os.remove(os.path.join(thumbnails_directory, thumbnail))
|
||||||
existing_thumbnails.remove(video_id)
|
existing_thumbnails.remove(video_id)
|
||||||
except Exception:
|
except Exception:
|
||||||
print(f'Failed to delete thumbnail: {thumbnail}')
|
print('Failed to delete thumbnail: ' + thumbnail)
|
||||||
traceback.print_exc()
|
traceback.print_exc()
|
||||||
|
|
||||||
|
|
||||||
@@ -184,7 +184,7 @@ def _get_videos(cursor, number_per_page, offset, tag=None):
|
|||||||
'time_published': exact_timestamp(db_video[3]) if db_video[4] else posix_to_dumbed_down(db_video[3]),
|
'time_published': exact_timestamp(db_video[3]) if db_video[4] else posix_to_dumbed_down(db_video[3]),
|
||||||
'author': db_video[5],
|
'author': db_video[5],
|
||||||
'author_id': db_video[6],
|
'author_id': db_video[6],
|
||||||
'author_url': f'/https://www.youtube.com/channel/{db_video[6]}',
|
'author_url': '/https://www.youtube.com/channel/' + db_video[6],
|
||||||
})
|
})
|
||||||
|
|
||||||
return videos, pseudo_number_of_videos
|
return videos, pseudo_number_of_videos
|
||||||
@@ -292,10 +292,7 @@ def youtube_timestamp_to_posix(dumb_timestamp):
|
|||||||
def posix_to_dumbed_down(posix_time):
|
def posix_to_dumbed_down(posix_time):
|
||||||
'''Inverse of youtube_timestamp_to_posix.'''
|
'''Inverse of youtube_timestamp_to_posix.'''
|
||||||
delta = int(time.time() - posix_time)
|
delta = int(time.time() - posix_time)
|
||||||
# Guard against future timestamps (clock drift) without relying on
|
assert delta >= 0
|
||||||
# `assert` (which is stripped under `python -O`).
|
|
||||||
if delta < 0:
|
|
||||||
delta = 0
|
|
||||||
|
|
||||||
if delta == 0:
|
if delta == 0:
|
||||||
return '0 seconds ago'
|
return '0 seconds ago'
|
||||||
@@ -304,9 +301,9 @@ def posix_to_dumbed_down(posix_time):
|
|||||||
if delta >= unit_time:
|
if delta >= unit_time:
|
||||||
quantifier = round(delta/unit_time)
|
quantifier = round(delta/unit_time)
|
||||||
if quantifier == 1:
|
if quantifier == 1:
|
||||||
return f'1 {unit_name} ago'
|
return '1 ' + unit_name + ' ago'
|
||||||
else:
|
else:
|
||||||
return f'{quantifier} {unit_name}s ago'
|
return str(quantifier) + ' ' + unit_name + 's ago'
|
||||||
else:
|
else:
|
||||||
raise Exception()
|
raise Exception()
|
||||||
|
|
||||||
@@ -363,7 +360,7 @@ def autocheck_dispatcher():
|
|||||||
time_until_earliest_job = earliest_job['next_check_time'] - time.time()
|
time_until_earliest_job = earliest_job['next_check_time'] - time.time()
|
||||||
|
|
||||||
if time_until_earliest_job <= -5: # should not happen unless we're running extremely slow
|
if time_until_earliest_job <= -5: # should not happen unless we're running extremely slow
|
||||||
print(f'ERROR: autocheck_dispatcher got job scheduled in the past, skipping and rescheduling: {earliest_job["channel_id"]}, {earliest_job["channel_name"]}, {earliest_job["next_check_time"]}')
|
print('ERROR: autocheck_dispatcher got job scheduled in the past, skipping and rescheduling: ' + earliest_job['channel_id'] + ', ' + earliest_job['channel_name'] + ', ' + str(earliest_job['next_check_time']))
|
||||||
next_check_time = time.time() + 3600*secrets.randbelow(60)/60
|
next_check_time = time.time() + 3600*secrets.randbelow(60)/60
|
||||||
with_open_db(_schedule_checking, earliest_job['channel_id'], next_check_time)
|
with_open_db(_schedule_checking, earliest_job['channel_id'], next_check_time)
|
||||||
autocheck_jobs[earliest_job_index]['next_check_time'] = next_check_time
|
autocheck_jobs[earliest_job_index]['next_check_time'] = next_check_time
|
||||||
@@ -451,7 +448,7 @@ def check_channels_if_necessary(channel_ids):
|
|||||||
|
|
||||||
|
|
||||||
def _get_atoma_feed(channel_id):
|
def _get_atoma_feed(channel_id):
|
||||||
url = f'https://www.youtube.com/feeds/videos.xml?channel_id={channel_id}'
|
url = 'https://www.youtube.com/feeds/videos.xml?channel_id=' + channel_id
|
||||||
try:
|
try:
|
||||||
return util.fetch_url(url).decode('utf-8')
|
return util.fetch_url(url).decode('utf-8')
|
||||||
except util.FetchError as e:
|
except util.FetchError as e:
|
||||||
@@ -485,15 +482,16 @@ def _get_channel_videos_first_page(channel_id, channel_status_name):
|
|||||||
return channel_info
|
return channel_info
|
||||||
except util.FetchError as e:
|
except util.FetchError as e:
|
||||||
if e.code == '429' and settings.route_tor:
|
if e.code == '429' and settings.route_tor:
|
||||||
error_message = (f'Error checking channel {channel_status_name}: '
|
error_message = ('Error checking channel ' + channel_status_name
|
||||||
f'YouTube blocked the request because the Tor exit node is overutilized. '
|
+ ': YouTube blocked the request because the'
|
||||||
f'Try getting a new exit node by using the New Identity button in the Tor Browser.')
|
+ ' Tor exit node is overutilized. Try getting a new exit node'
|
||||||
|
+ ' by using the New Identity button in the Tor Browser.')
|
||||||
if e.ip:
|
if e.ip:
|
||||||
error_message += f' Exit node IP address: {e.ip}'
|
error_message += ' Exit node IP address: ' + e.ip
|
||||||
print(error_message)
|
print(error_message)
|
||||||
return None
|
return None
|
||||||
elif e.code == '502':
|
elif e.code == '502':
|
||||||
print(f'Error checking channel {channel_status_name}: {e}')
|
print('Error checking channel', channel_status_name + ':', str(e))
|
||||||
return None
|
return None
|
||||||
raise
|
raise
|
||||||
|
|
||||||
@@ -504,7 +502,7 @@ def _get_upstream_videos(channel_id):
|
|||||||
except KeyError:
|
except KeyError:
|
||||||
channel_status_name = channel_id
|
channel_status_name = channel_id
|
||||||
|
|
||||||
print(f"Checking channel: {channel_status_name}")
|
print("Checking channel: " + channel_status_name)
|
||||||
|
|
||||||
tasks = (
|
tasks = (
|
||||||
# channel page, need for video duration
|
# channel page, need for video duration
|
||||||
@@ -533,8 +531,7 @@ def _get_upstream_videos(channel_id):
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
root = defusedxml.ElementTree.fromstring(feed)
|
root = defusedxml.ElementTree.fromstring(feed)
|
||||||
if remove_bullshit(root.tag) != 'feed':
|
assert remove_bullshit(root.tag) == 'feed'
|
||||||
raise ValueError('Root element is not <feed>')
|
|
||||||
for entry in root:
|
for entry in root:
|
||||||
if (remove_bullshit(entry.tag) != 'entry'):
|
if (remove_bullshit(entry.tag) != 'entry'):
|
||||||
continue
|
continue
|
||||||
@@ -542,22 +539,22 @@ def _get_upstream_videos(channel_id):
|
|||||||
# it's yt:videoId in the xml but the yt: is turned into a namespace which is removed by remove_bullshit
|
# it's yt:videoId in the xml but the yt: is turned into a namespace which is removed by remove_bullshit
|
||||||
video_id_element = find_element(entry, 'videoId')
|
video_id_element = find_element(entry, 'videoId')
|
||||||
time_published_element = find_element(entry, 'published')
|
time_published_element = find_element(entry, 'published')
|
||||||
if video_id_element is None or time_published_element is None:
|
assert video_id_element is not None
|
||||||
raise ValueError('Missing videoId or published element')
|
assert time_published_element is not None
|
||||||
|
|
||||||
time_published = int(calendar.timegm(time.strptime(time_published_element.text, '%Y-%m-%dT%H:%M:%S+00:00')))
|
time_published = int(calendar.timegm(time.strptime(time_published_element.text, '%Y-%m-%dT%H:%M:%S+00:00')))
|
||||||
times_published[video_id_element.text] = time_published
|
times_published[video_id_element.text] = time_published
|
||||||
|
|
||||||
except ValueError:
|
except AssertionError:
|
||||||
print(f'Failed to read atoma feed for {channel_status_name}')
|
print('Failed to read atoma feed for ' + channel_status_name)
|
||||||
traceback.print_exc()
|
traceback.print_exc()
|
||||||
except defusedxml.ElementTree.ParseError:
|
except defusedxml.ElementTree.ParseError:
|
||||||
print(f'Failed to read atoma feed for {channel_status_name}')
|
print('Failed to read atoma feed for ' + channel_status_name)
|
||||||
|
|
||||||
if channel_info is None: # there was an error
|
if channel_info is None: # there was an error
|
||||||
return
|
return
|
||||||
if channel_info['error']:
|
if channel_info['error']:
|
||||||
print(f'Error checking channel {channel_status_name}: {channel_info["error"]}')
|
print('Error checking channel ' + channel_status_name + ': ' + channel_info['error'])
|
||||||
return
|
return
|
||||||
|
|
||||||
videos = channel_info['items']
|
videos = channel_info['items']
|
||||||
@@ -596,10 +593,7 @@ def _get_upstream_videos(channel_id):
|
|||||||
# Special case: none of the videos have a time published.
|
# Special case: none of the videos have a time published.
|
||||||
# In this case, make something up
|
# In this case, make something up
|
||||||
if videos and videos[0]['time_published'] is None:
|
if videos and videos[0]['time_published'] is None:
|
||||||
# Invariant: if the first video has no timestamp, earlier passes
|
assert all(v['time_published'] is None for v in videos)
|
||||||
# ensure all of them are unset. Don't rely on `assert`.
|
|
||||||
if not all(v['time_published'] is None for v in videos):
|
|
||||||
raise RuntimeError('Inconsistent time_published state')
|
|
||||||
now = time.time()
|
now = time.time()
|
||||||
for i in range(len(videos)):
|
for i in range(len(videos)):
|
||||||
# 1 month between videos
|
# 1 month between videos
|
||||||
@@ -814,8 +808,7 @@ def import_subscriptions():
|
|||||||
file = file.read().decode('utf-8')
|
file = file.read().decode('utf-8')
|
||||||
try:
|
try:
|
||||||
root = defusedxml.ElementTree.fromstring(file)
|
root = defusedxml.ElementTree.fromstring(file)
|
||||||
if root.tag != 'opml':
|
assert root.tag == 'opml'
|
||||||
raise ValueError('Root element is not <opml>')
|
|
||||||
channels = []
|
channels = []
|
||||||
for outline_element in root[0][0]:
|
for outline_element in root[0][0]:
|
||||||
if (outline_element.tag != 'outline') or ('xmlUrl' not in outline_element.attrib):
|
if (outline_element.tag != 'outline') or ('xmlUrl' not in outline_element.attrib):
|
||||||
@@ -826,7 +819,7 @@ def import_subscriptions():
|
|||||||
channel_id = channel_rss_url[channel_rss_url.find('channel_id=')+11:].strip()
|
channel_id = channel_rss_url[channel_rss_url.find('channel_id=')+11:].strip()
|
||||||
channels.append((channel_id, channel_name))
|
channels.append((channel_id, channel_name))
|
||||||
|
|
||||||
except (ValueError, IndexError, defusedxml.ElementTree.ParseError):
|
except (AssertionError, IndexError, defusedxml.ElementTree.ParseError) as e:
|
||||||
return '400 Bad Request: Unable to read opml xml file, or the file is not the expected format', 400
|
return '400 Bad Request: Unable to read opml xml file, or the file is not the expected format', 400
|
||||||
elif mime_type in ('text/csv', 'application/vnd.ms-excel'):
|
elif mime_type in ('text/csv', 'application/vnd.ms-excel'):
|
||||||
content = file.read().decode('utf-8')
|
content = file.read().decode('utf-8')
|
||||||
@@ -1022,7 +1015,7 @@ def get_subscriptions_page():
|
|||||||
tag = request.args.get('tag', None)
|
tag = request.args.get('tag', None)
|
||||||
videos, number_of_videos_in_db = _get_videos(cursor, 60, (page - 1)*60, tag)
|
videos, number_of_videos_in_db = _get_videos(cursor, 60, (page - 1)*60, tag)
|
||||||
for video in videos:
|
for video in videos:
|
||||||
video['thumbnail'] = f'{util.URL_ORIGIN}/data/subscription_thumbnails/{video["id"]}.jpg'
|
video['thumbnail'] = util.URL_ORIGIN + '/data/subscription_thumbnails/' + video['id'] + '.jpg'
|
||||||
video['type'] = 'video'
|
video['type'] = 'video'
|
||||||
video['item_size'] = 'small'
|
video['item_size'] = 'small'
|
||||||
util.add_extra_html_info(video)
|
util.add_extra_html_info(video)
|
||||||
@@ -1032,7 +1025,7 @@ def get_subscriptions_page():
|
|||||||
subscription_list = []
|
subscription_list = []
|
||||||
for channel_name, channel_id, muted in _get_subscribed_channels(cursor):
|
for channel_name, channel_id, muted in _get_subscribed_channels(cursor):
|
||||||
subscription_list.append({
|
subscription_list.append({
|
||||||
'channel_url': f'{util.URL_ORIGIN}/channel/{channel_id}',
|
'channel_url': util.URL_ORIGIN + '/channel/' + channel_id,
|
||||||
'channel_name': channel_name,
|
'channel_name': channel_name,
|
||||||
'channel_id': channel_id,
|
'channel_id': channel_id,
|
||||||
'muted': muted,
|
'muted': muted,
|
||||||
@@ -1078,20 +1071,11 @@ def post_subscriptions_page():
|
|||||||
return '', 204
|
return '', 204
|
||||||
|
|
||||||
|
|
||||||
# YouTube video IDs are exactly 11 chars from [A-Za-z0-9_-]. Enforce this
|
|
||||||
# before using the value in filesystem paths to prevent path traversal
|
|
||||||
# (CWE-22, OWASP A01:2021).
|
|
||||||
_VIDEO_ID_RE = re.compile(r'^[A-Za-z0-9_-]{11}$')
|
|
||||||
|
|
||||||
|
|
||||||
@yt_app.route('/data/subscription_thumbnails/<thumbnail>')
|
@yt_app.route('/data/subscription_thumbnails/<thumbnail>')
|
||||||
def serve_subscription_thumbnail(thumbnail):
|
def serve_subscription_thumbnail(thumbnail):
|
||||||
'''Serves thumbnail from disk if it's been saved already. If not, downloads the thumbnail, saves to disk, and serves it.'''
|
'''Serves thumbnail from disk if it's been saved already. If not, downloads the thumbnail, saves to disk, and serves it.'''
|
||||||
if not thumbnail.endswith('.jpg'):
|
assert thumbnail[-4:] == '.jpg'
|
||||||
flask.abort(400)
|
|
||||||
video_id = thumbnail[0:-4]
|
video_id = thumbnail[0:-4]
|
||||||
if not _VIDEO_ID_RE.match(video_id):
|
|
||||||
flask.abort(400)
|
|
||||||
thumbnail_path = os.path.join(thumbnails_directory, thumbnail)
|
thumbnail_path = os.path.join(thumbnails_directory, thumbnail)
|
||||||
|
|
||||||
if video_id in existing_thumbnails:
|
if video_id in existing_thumbnails:
|
||||||
@@ -1108,17 +1092,17 @@ def serve_subscription_thumbnail(thumbnail):
|
|||||||
for quality in ('hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'):
|
for quality in ('hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'):
|
||||||
url = f"https://i.ytimg.com/vi/{video_id}/{quality}"
|
url = f"https://i.ytimg.com/vi/{video_id}/{quality}"
|
||||||
try:
|
try:
|
||||||
image = util.fetch_url(url, report_text=f"Saved thumbnail: {video_id}")
|
image = util.fetch_url(url, report_text="Saved thumbnail: " + video_id)
|
||||||
break
|
break
|
||||||
except util.FetchError as e:
|
except util.FetchError as e:
|
||||||
if '404' in str(e):
|
if '404' in str(e):
|
||||||
continue
|
continue
|
||||||
print(f"Failed to download thumbnail for {video_id}: {e}")
|
print("Failed to download thumbnail for " + video_id + ": " + str(e))
|
||||||
flask.abort(500)
|
flask.abort(500)
|
||||||
except urllib.error.HTTPError as e:
|
except urllib.error.HTTPError as e:
|
||||||
if e.code == 404:
|
if e.code == 404:
|
||||||
continue
|
continue
|
||||||
print(f"Failed to download thumbnail for {video_id}: {e}")
|
print("Failed to download thumbnail for " + video_id + ": " + str(e))
|
||||||
flask.abort(e.code)
|
flask.abort(e.code)
|
||||||
|
|
||||||
if image is None:
|
if image is None:
|
||||||
|
|||||||
@@ -105,10 +105,5 @@
|
|||||||
{% if use_dash %}
|
{% if use_dash %}
|
||||||
<script src="/youtube.com/static/js/av-merge.js"></script>
|
<script src="/youtube.com/static/js/av-merge.js"></script>
|
||||||
{% endif %}
|
{% endif %}
|
||||||
|
|
||||||
<!-- Storyboard Preview Thumbnails (native players only; Plyr handles this internally) -->
|
|
||||||
{% if settings.use_video_player != 2 and settings.native_player_storyboard %}
|
|
||||||
<script src="/youtube.com/static/js/storyboard-preview.js"></script>
|
|
||||||
{% endif %}
|
|
||||||
</body>
|
</body>
|
||||||
</html>
|
</html>
|
||||||
|
|||||||
@@ -102,40 +102,22 @@
|
|||||||
{% if settings.use_video_download != 0 %}
|
{% if settings.use_video_download != 0 %}
|
||||||
<details class="v-download">
|
<details class="v-download">
|
||||||
<summary class="download-dropdown-label">{{ _('Download') }}</summary>
|
<summary class="download-dropdown-label">{{ _('Download') }}</summary>
|
||||||
<div class="download-table-container">
|
<ul class="download-dropdown-content">
|
||||||
<table class="download-table" aria-label="Download formats">
|
{% for format in download_formats %}
|
||||||
<thead>
|
<li class="download-format">
|
||||||
<tr>
|
<a class="download-link" href="{{ format['url'] }}" download="{{ title }}.{{ format['ext'] }}">
|
||||||
<th scope="col">{{ _('Ext') }}</th>
|
{{ format['ext'] }} {{ format['video_quality'] }} {{ format['audio_quality'] }} {{ format['file_size'] }} {{ format['codecs'] }}
|
||||||
<th scope="col">{{ _('Video') }}</th>
|
</a>
|
||||||
<th scope="col">{{ _('Audio') }}</th>
|
</li>
|
||||||
<th scope="col">{{ _('Size') }}</th>
|
{% endfor %}
|
||||||
<th scope="col">{{ _('Codecs') }}</th>
|
{% for download in other_downloads %}
|
||||||
<th scope="col">{{ _('Link') }}</th>
|
<li class="download-format">
|
||||||
</tr>
|
<a href="{{ download['url'] }}" download>
|
||||||
</thead>
|
{{ download['ext'] }} {{ download['label'] }}
|
||||||
<tbody>
|
</a>
|
||||||
{% for format in download_formats %}
|
</li>
|
||||||
<tr>
|
{% endfor %}
|
||||||
<td data-label="{{ _('Ext') }}">{{ format['ext'] }}</td>
|
</ul>
|
||||||
<td data-label="{{ _('Video') }}">{{ format['video_quality'] }}</td>
|
|
||||||
<td data-label="{{ _('Audio') }}">{{ format['audio_quality'] }}</td>
|
|
||||||
<td data-label="{{ _('Size') }}">{{ format['file_size'] }}</td>
|
|
||||||
<td data-label="{{ _('Codecs') }}">{{ format['codecs'] }}</td>
|
|
||||||
<td data-label="{{ _('Link') }}"><a class="download-link" href="{{ format['url'] }}" download="{{ title }}.{{ format['ext'] }}" aria-label="{{ _('Download') }} {{ format['ext'] }} {{ format['video_quality'] }} {{ format['audio_quality'] }}">{{ _('Download') }}</a></td>
|
|
||||||
</tr>
|
|
||||||
{% endfor %}
|
|
||||||
{% for download in other_downloads %}
|
|
||||||
<tr>
|
|
||||||
<td data-label="{{ _('Ext') }}">{{ download['ext'] }}</td>
|
|
||||||
<td data-label="{{ _('Video') }}" colspan="3">{{ download['label'] }}</td>
|
|
||||||
<td data-label="{{ _('Codecs') }}">{{ download.get('codecs', 'N/A') }}</td>
|
|
||||||
<td data-label="{{ _('Link') }}"><a class="download-link" href="{{ download['url'] }}" download aria-label="{{ _('Download') }} {{ download['label'] }}">{{ _('Download') }}</a></td>
|
|
||||||
</tr>
|
|
||||||
{% endfor %}
|
|
||||||
</tbody>
|
|
||||||
</table>
|
|
||||||
</div>
|
|
||||||
</details>
|
</details>
|
||||||
{% else %}
|
{% else %}
|
||||||
<span class="v-download"></span>
|
<span class="v-download"></span>
|
||||||
@@ -322,8 +304,8 @@
|
|||||||
<!-- /plyr -->
|
<!-- /plyr -->
|
||||||
{% endif %}
|
{% endif %}
|
||||||
|
|
||||||
<!-- Storyboard Preview Thumbnails (native players only; Plyr handles this internally) -->
|
<!-- Storyboard Preview Thumbnails -->
|
||||||
{% if settings.use_video_player != 2 and settings.native_player_storyboard %}
|
{% if settings.use_video_player != 2 %}
|
||||||
<script src="/youtube.com/static/js/storyboard-preview.js"></script>
|
<script src="/youtube.com/static/js/storyboard-preview.js"></script>
|
||||||
{% endif %}
|
{% endif %}
|
||||||
|
|
||||||
|
|||||||
@@ -1,6 +1,5 @@
|
|||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
import logging
|
import logging
|
||||||
import random
|
|
||||||
import settings
|
import settings
|
||||||
import socks
|
import socks
|
||||||
import sockshandler
|
import sockshandler
|
||||||
@@ -20,10 +19,10 @@ import gevent.queue
|
|||||||
import gevent.lock
|
import gevent.lock
|
||||||
import collections
|
import collections
|
||||||
import stem
|
import stem
|
||||||
import stem.control
|
|
||||||
import traceback
|
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
import stem.control
|
||||||
|
import traceback
|
||||||
|
|
||||||
# The trouble with the requests library: It ships its own certificate bundle via certifi
|
# The trouble with the requests library: It ships its own certificate bundle via certifi
|
||||||
# instead of using the system certificate store, meaning self-signed certificates
|
# instead of using the system certificate store, meaning self-signed certificates
|
||||||
@@ -55,8 +54,8 @@ logger = logging.getLogger(__name__)
|
|||||||
# https://github.com/kennethreitz/requests/issues/2966
|
# https://github.com/kennethreitz/requests/issues/2966
|
||||||
|
|
||||||
# Until then, I will use a mix of urllib3 and urllib.
|
# Until then, I will use a mix of urllib3 and urllib.
|
||||||
import urllib3 # noqa: E402 (imported here intentionally after the long note above)
|
import urllib3
|
||||||
import urllib3.contrib.socks # noqa: E402
|
import urllib3.contrib.socks
|
||||||
|
|
||||||
URL_ORIGIN = "/https://www.youtube.com"
|
URL_ORIGIN = "/https://www.youtube.com"
|
||||||
|
|
||||||
@@ -72,7 +71,7 @@ class TorManager:
|
|||||||
def __init__(self):
|
def __init__(self):
|
||||||
self.old_tor_connection_pool = None
|
self.old_tor_connection_pool = None
|
||||||
self.tor_connection_pool = urllib3.contrib.socks.SOCKSProxyManager(
|
self.tor_connection_pool = urllib3.contrib.socks.SOCKSProxyManager(
|
||||||
f'socks5h://127.0.0.1:{settings.tor_port}/',
|
'socks5h://127.0.0.1:' + str(settings.tor_port) + '/',
|
||||||
cert_reqs='CERT_REQUIRED')
|
cert_reqs='CERT_REQUIRED')
|
||||||
self.tor_pool_refresh_time = time.monotonic()
|
self.tor_pool_refresh_time = time.monotonic()
|
||||||
settings.add_setting_changed_hook(
|
settings.add_setting_changed_hook(
|
||||||
@@ -92,7 +91,7 @@ class TorManager:
|
|||||||
self.old_tor_connection_pool = self.tor_connection_pool
|
self.old_tor_connection_pool = self.tor_connection_pool
|
||||||
|
|
||||||
self.tor_connection_pool = urllib3.contrib.socks.SOCKSProxyManager(
|
self.tor_connection_pool = urllib3.contrib.socks.SOCKSProxyManager(
|
||||||
f'socks5h://127.0.0.1:{settings.tor_port}/',
|
'socks5h://127.0.0.1:' + str(settings.tor_port) + '/',
|
||||||
cert_reqs='CERT_REQUIRED')
|
cert_reqs='CERT_REQUIRED')
|
||||||
self.tor_pool_refresh_time = time.monotonic()
|
self.tor_pool_refresh_time = time.monotonic()
|
||||||
|
|
||||||
@@ -178,6 +177,7 @@ def get_pool(use_tor):
|
|||||||
class HTTPAsymmetricCookieProcessor(urllib.request.BaseHandler):
|
class HTTPAsymmetricCookieProcessor(urllib.request.BaseHandler):
|
||||||
'''Separate cookiejars for receiving and sending'''
|
'''Separate cookiejars for receiving and sending'''
|
||||||
def __init__(self, cookiejar_send=None, cookiejar_receive=None):
|
def __init__(self, cookiejar_send=None, cookiejar_receive=None):
|
||||||
|
import http.cookiejar
|
||||||
self.cookiejar_send = cookiejar_send
|
self.cookiejar_send = cookiejar_send
|
||||||
self.cookiejar_receive = cookiejar_receive
|
self.cookiejar_receive = cookiejar_receive
|
||||||
|
|
||||||
@@ -198,9 +198,9 @@ class HTTPAsymmetricCookieProcessor(urllib.request.BaseHandler):
|
|||||||
class FetchError(Exception):
|
class FetchError(Exception):
|
||||||
def __init__(self, code, reason='', ip=None, error_message=None):
|
def __init__(self, code, reason='', ip=None, error_message=None):
|
||||||
if error_message:
|
if error_message:
|
||||||
string = f"{code} {reason}: {error_message}"
|
string = code + ' ' + reason + ': ' + error_message
|
||||||
else:
|
else:
|
||||||
string = f"HTTP error during request: {code} {reason}"
|
string = 'HTTP error during request: ' + code + ' ' + reason
|
||||||
Exception.__init__(self, string)
|
Exception.__init__(self, string)
|
||||||
self.code = code
|
self.code = code
|
||||||
self.reason = reason
|
self.reason = reason
|
||||||
@@ -208,16 +208,6 @@ class FetchError(Exception):
|
|||||||
self.error_message = error_message
|
self.error_message = error_message
|
||||||
|
|
||||||
|
|
||||||
def _noop_cleanup(response):
|
|
||||||
'''No-op cleanup used when the urllib opener owns the response.'''
|
|
||||||
return None
|
|
||||||
|
|
||||||
|
|
||||||
def _release_conn_cleanup(response):
|
|
||||||
'''Release the urllib3 pooled connection back to the pool.'''
|
|
||||||
response.release_conn()
|
|
||||||
|
|
||||||
|
|
||||||
def decode_content(content, encoding_header):
|
def decode_content(content, encoding_header):
|
||||||
encodings = encoding_header.replace(' ', '').split(',')
|
encodings = encoding_header.replace(' ', '').split(',')
|
||||||
for encoding in reversed(encodings):
|
for encoding in reversed(encodings):
|
||||||
@@ -273,7 +263,7 @@ def fetch_url_response(url, headers=(), timeout=15, data=None,
|
|||||||
opener = urllib.request.build_opener(cookie_processor)
|
opener = urllib.request.build_opener(cookie_processor)
|
||||||
|
|
||||||
response = opener.open(req, timeout=timeout)
|
response = opener.open(req, timeout=timeout)
|
||||||
cleanup_func = _noop_cleanup
|
cleanup_func = (lambda r: None)
|
||||||
|
|
||||||
else: # Use a urllib3 pool. Cookies can't be used since urllib3 doesn't have easy support for them.
|
else: # Use a urllib3 pool. Cookies can't be used since urllib3 doesn't have easy support for them.
|
||||||
# default: Retry.DEFAULT = Retry(3)
|
# default: Retry.DEFAULT = Retry(3)
|
||||||
@@ -294,18 +284,20 @@ def fetch_url_response(url, headers=(), timeout=15, data=None,
|
|||||||
exception_cause = e.__context__.__context__
|
exception_cause = e.__context__.__context__
|
||||||
if (isinstance(exception_cause, socks.ProxyConnectionError)
|
if (isinstance(exception_cause, socks.ProxyConnectionError)
|
||||||
and settings.route_tor):
|
and settings.route_tor):
|
||||||
msg = f'Failed to connect to Tor. Check that Tor is open and that your internet connection is working.\n\n{e}'
|
msg = ('Failed to connect to Tor. Check that Tor is open and '
|
||||||
|
'that your internet connection is working.\n\n'
|
||||||
|
+ str(e))
|
||||||
raise FetchError('502', reason='Bad Gateway',
|
raise FetchError('502', reason='Bad Gateway',
|
||||||
error_message=msg)
|
error_message=msg)
|
||||||
elif isinstance(e.__context__,
|
elif isinstance(e.__context__,
|
||||||
urllib3.exceptions.NewConnectionError):
|
urllib3.exceptions.NewConnectionError):
|
||||||
msg = f'Failed to establish a connection.\n\n{e}'
|
msg = 'Failed to establish a connection.\n\n' + str(e)
|
||||||
raise FetchError(
|
raise FetchError(
|
||||||
'502', reason='Bad Gateway',
|
'502', reason='Bad Gateway',
|
||||||
error_message=msg)
|
error_message=msg)
|
||||||
else:
|
else:
|
||||||
raise
|
raise
|
||||||
cleanup_func = _release_conn_cleanup
|
cleanup_func = (lambda r: r.release_conn())
|
||||||
|
|
||||||
return response, cleanup_func
|
return response, cleanup_func
|
||||||
|
|
||||||
@@ -323,6 +315,8 @@ def fetch_url(url, headers=(), timeout=15, report_text=None, data=None,
|
|||||||
|
|
||||||
Max retries: 5 attempts with exponential backoff
|
Max retries: 5 attempts with exponential backoff
|
||||||
"""
|
"""
|
||||||
|
import random
|
||||||
|
|
||||||
max_retries = 5
|
max_retries = 5
|
||||||
base_delay = 1.0 # Base delay in seconds
|
base_delay = 1.0 # Base delay in seconds
|
||||||
|
|
||||||
@@ -389,7 +383,7 @@ def fetch_url(url, headers=(), timeout=15, report_text=None, data=None,
|
|||||||
if error:
|
if error:
|
||||||
raise FetchError(
|
raise FetchError(
|
||||||
'429', reason=response.reason, ip=ip,
|
'429', reason=response.reason, ip=ip,
|
||||||
error_message=f'Automatic circuit change: {error}')
|
error_message='Automatic circuit change: ' + error)
|
||||||
continue # retry with new identity
|
continue # retry with new identity
|
||||||
|
|
||||||
# Check for client errors (400, 404) - don't retry these
|
# Check for client errors (400, 404) - don't retry these
|
||||||
@@ -407,7 +401,7 @@ def fetch_url(url, headers=(), timeout=15, report_text=None, data=None,
|
|||||||
logger.error(f'Server error {response.status} after {max_retries} retries')
|
logger.error(f'Server error {response.status} after {max_retries} retries')
|
||||||
raise FetchError(str(response.status), reason=response.reason, ip=None)
|
raise FetchError(str(response.status), reason=response.reason, ip=None)
|
||||||
|
|
||||||
# Exponential backoff for server errors. Non-crypto jitter.
|
# Exponential backoff for server errors
|
||||||
delay = (base_delay * (2 ** attempt)) + random.uniform(0, 1)
|
delay = (base_delay * (2 ** attempt)) + random.uniform(0, 1)
|
||||||
logger.warning(f'Server error ({response.status}). Waiting {delay:.1f}s before retry {attempt + 1}/{max_retries}...')
|
logger.warning(f'Server error ({response.status}). Waiting {delay:.1f}s before retry {attempt + 1}/{max_retries}...')
|
||||||
time.sleep(delay)
|
time.sleep(delay)
|
||||||
@@ -438,7 +432,7 @@ def fetch_url(url, headers=(), timeout=15, report_text=None, data=None,
|
|||||||
else:
|
else:
|
||||||
raise
|
raise
|
||||||
|
|
||||||
# Wait and retry. Non-crypto jitter.
|
# Wait and retry
|
||||||
delay = (base_delay * (2 ** attempt)) + random.uniform(0, 1)
|
delay = (base_delay * (2 ** attempt)) + random.uniform(0, 1)
|
||||||
logger.warning(f'Connection error. Waiting {delay:.1f}s before retry {attempt + 1}/{max_retries}...')
|
logger.warning(f'Connection error. Waiting {delay:.1f}s before retry {attempt + 1}/{max_retries}...')
|
||||||
time.sleep(delay)
|
time.sleep(delay)
|
||||||
@@ -465,7 +459,10 @@ def head(url, use_tor=False, report_text=None, max_redirects=10):
|
|||||||
headers = {'User-Agent': 'Python-urllib'}
|
headers = {'User-Agent': 'Python-urllib'}
|
||||||
response = pool.request('HEAD', url, headers=headers, retries=retries)
|
response = pool.request('HEAD', url, headers=headers, retries=retries)
|
||||||
if report_text:
|
if report_text:
|
||||||
print(f'{report_text} Latency: {round(time.monotonic() - start_time, 3)}')
|
print(
|
||||||
|
report_text,
|
||||||
|
' Latency:',
|
||||||
|
round(time.monotonic() - start_time, 3))
|
||||||
return response
|
return response
|
||||||
|
|
||||||
mobile_user_agent = 'Mozilla/5.0 (Linux; Android 7.0; Redmi Note 4 Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Mobile Safari/537.36'
|
mobile_user_agent = 'Mozilla/5.0 (Linux; Android 7.0; Redmi Note 4 Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Mobile Safari/537.36'
|
||||||
@@ -535,30 +532,30 @@ class RateLimitedQueue(gevent.queue.Queue):
|
|||||||
|
|
||||||
|
|
||||||
def download_thumbnail(save_directory, video_id):
|
def download_thumbnail(save_directory, video_id):
|
||||||
save_location = os.path.join(save_directory, video_id + '.jpg')
|
save_location = os.path.join(save_directory, video_id + ".jpg")
|
||||||
for quality in ('hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'):
|
for quality in ('hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'):
|
||||||
url = f'https://i.ytimg.com/vi/{video_id}/{quality}'
|
url = f"https://i.ytimg.com/vi/{video_id}/{quality}"
|
||||||
try:
|
try:
|
||||||
thumbnail = fetch_url(url, report_text=f'Saved thumbnail: {video_id}')
|
thumbnail = fetch_url(url, report_text="Saved thumbnail: " + video_id)
|
||||||
except FetchError as e:
|
except FetchError as e:
|
||||||
if '404' in str(e):
|
if '404' in str(e):
|
||||||
continue
|
continue
|
||||||
print(f'Failed to download thumbnail for {video_id}: {e}')
|
print("Failed to download thumbnail for " + video_id + ": " + str(e))
|
||||||
return False
|
return False
|
||||||
except urllib.error.HTTPError as e:
|
except urllib.error.HTTPError as e:
|
||||||
if e.code == 404:
|
if e.code == 404:
|
||||||
continue
|
continue
|
||||||
print(f'Failed to download thumbnail for {video_id}: {e}')
|
print("Failed to download thumbnail for " + video_id + ": " + str(e))
|
||||||
return False
|
return False
|
||||||
try:
|
try:
|
||||||
with open(save_location, 'wb') as f:
|
f = open(save_location, 'wb')
|
||||||
f.write(thumbnail)
|
|
||||||
except FileNotFoundError:
|
except FileNotFoundError:
|
||||||
os.makedirs(save_directory, exist_ok=True)
|
os.makedirs(save_directory, exist_ok=True)
|
||||||
with open(save_location, 'wb') as f:
|
f = open(save_location, 'wb')
|
||||||
f.write(thumbnail)
|
f.write(thumbnail)
|
||||||
|
f.close()
|
||||||
return True
|
return True
|
||||||
print(f'No thumbnail available for {video_id}')
|
print("No thumbnail available for " + video_id)
|
||||||
return False
|
return False
|
||||||
|
|
||||||
|
|
||||||
@@ -693,7 +690,7 @@ def prefix_urls(item):
|
|||||||
|
|
||||||
def add_extra_html_info(item):
|
def add_extra_html_info(item):
|
||||||
if item['type'] == 'video':
|
if item['type'] == 'video':
|
||||||
item['url'] = f'{URL_ORIGIN}/watch?v={item["id"]}' if item.get('id') else None
|
item['url'] = (URL_ORIGIN + '/watch?v=' + item['id']) if item.get('id') else None
|
||||||
|
|
||||||
video_info = {}
|
video_info = {}
|
||||||
for key in ('id', 'title', 'author', 'duration', 'author_id'):
|
for key in ('id', 'title', 'author', 'duration', 'author_id'):
|
||||||
@@ -716,7 +713,7 @@ def add_extra_html_info(item):
|
|||||||
item['url'] = concat_or_none(URL_ORIGIN, "/channel/", item['id'])
|
item['url'] = concat_or_none(URL_ORIGIN, "/channel/", item['id'])
|
||||||
|
|
||||||
if item.get('author_id') and 'author_url' not in item:
|
if item.get('author_id') and 'author_url' not in item:
|
||||||
item['author_url'] = f'{URL_ORIGIN}/channel/{item["author_id"]}'
|
item['author_url'] = URL_ORIGIN + '/channel/' + item['author_id']
|
||||||
|
|
||||||
|
|
||||||
def check_gevent_exceptions(*tasks):
|
def check_gevent_exceptions(*tasks):
|
||||||
@@ -962,7 +959,7 @@ def call_youtube_api(client, api, data):
|
|||||||
user_agent = context['client'].get('userAgent') or mobile_user_agent
|
user_agent = context['client'].get('userAgent') or mobile_user_agent
|
||||||
visitor_data = get_visitor_data()
|
visitor_data = get_visitor_data()
|
||||||
|
|
||||||
url = f'https://{host}/youtubei/v1/{api}?key={key}'
|
url = 'https://' + host + '/youtubei/v1/' + api + '?key=' + key
|
||||||
if visitor_data:
|
if visitor_data:
|
||||||
context['client'].update({'visitorData': visitor_data})
|
context['client'].update({'visitorData': visitor_data})
|
||||||
data['context'] = context
|
data['context'] = context
|
||||||
@@ -973,8 +970,8 @@ def call_youtube_api(client, api, data):
|
|||||||
headers = ( *headers, ('X-Goog-Visitor-Id', visitor_data ))
|
headers = ( *headers, ('X-Goog-Visitor-Id', visitor_data ))
|
||||||
response = fetch_url(
|
response = fetch_url(
|
||||||
url, data=data, headers=headers,
|
url, data=data, headers=headers,
|
||||||
debug_name=f'youtubei_{api}_{client}',
|
debug_name='youtubei_' + api + '_' + client,
|
||||||
report_text=f'Fetched {client} youtubei {api}'
|
report_text='Fetched ' + client + ' youtubei ' + api
|
||||||
).decode('utf-8')
|
).decode('utf-8')
|
||||||
return response
|
return response
|
||||||
|
|
||||||
|
|||||||
@@ -1,3 +1,3 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
__version__ = 'v0.5.0'
|
__version__ = 'v0.4.5'
|
||||||
|
|||||||
182
youtube/watch.py
182
youtube/watch.py
@@ -1,26 +1,27 @@
|
|||||||
import json
|
|
||||||
import logging
|
|
||||||
import math
|
|
||||||
import os
|
|
||||||
import re
|
|
||||||
import traceback
|
|
||||||
import urllib
|
|
||||||
from math import ceil
|
|
||||||
from types import SimpleNamespace
|
|
||||||
from urllib.parse import parse_qs, urlencode
|
|
||||||
|
|
||||||
import flask
|
|
||||||
import gevent
|
|
||||||
import urllib3.exceptions
|
|
||||||
from flask import request
|
|
||||||
|
|
||||||
import youtube
|
import youtube
|
||||||
from youtube import yt_app
|
from youtube import yt_app
|
||||||
from youtube import util, comments, local_playlist, yt_data_extract
|
from youtube import util, comments, local_playlist, yt_data_extract
|
||||||
|
from youtube.util import time_utc_isoformat
|
||||||
import settings
|
import settings
|
||||||
|
|
||||||
|
from flask import request
|
||||||
|
import flask
|
||||||
|
import logging
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
import json
|
||||||
|
import gevent
|
||||||
|
import os
|
||||||
|
import math
|
||||||
|
import traceback
|
||||||
|
import urllib
|
||||||
|
import re
|
||||||
|
import urllib3.exceptions
|
||||||
|
from urllib.parse import parse_qs, urlencode
|
||||||
|
from types import SimpleNamespace
|
||||||
|
from math import ceil
|
||||||
|
|
||||||
|
|
||||||
try:
|
try:
|
||||||
with open(os.path.join(settings.data_dir, 'decrypt_function_cache.json'), 'r') as f:
|
with open(os.path.join(settings.data_dir, 'decrypt_function_cache.json'), 'r') as f:
|
||||||
@@ -53,7 +54,7 @@ def get_video_sources(info, target_resolution):
|
|||||||
if fmt['acodec'] and fmt['vcodec']:
|
if fmt['acodec'] and fmt['vcodec']:
|
||||||
if fmt.get('audio_track_is_default', True) is False:
|
if fmt.get('audio_track_is_default', True) is False:
|
||||||
continue
|
continue
|
||||||
source = {'type': f"video/{fmt['ext']}",
|
source = {'type': 'video/' + fmt['ext'],
|
||||||
'quality_string': short_video_quality_string(fmt)}
|
'quality_string': short_video_quality_string(fmt)}
|
||||||
source['quality_string'] += ' (integrated)'
|
source['quality_string'] += ' (integrated)'
|
||||||
source.update(fmt)
|
source.update(fmt)
|
||||||
@@ -61,19 +62,17 @@ def get_video_sources(info, target_resolution):
|
|||||||
continue
|
continue
|
||||||
if not (fmt['init_range'] and fmt['index_range']):
|
if not (fmt['init_range'] and fmt['index_range']):
|
||||||
# Allow HLS-backed audio tracks (served locally, no init/index needed)
|
# Allow HLS-backed audio tracks (served locally, no init/index needed)
|
||||||
url_value = fmt.get('url', '')
|
if not fmt.get('url', '').startswith('http://127.') and not '/ytl-api/' in fmt.get('url', ''):
|
||||||
if (not url_value.startswith('http://127.')
|
|
||||||
and '/ytl-api/' not in url_value):
|
|
||||||
continue
|
continue
|
||||||
# Mark as HLS for frontend
|
# Mark as HLS for frontend
|
||||||
fmt['is_hls'] = True
|
fmt['is_hls'] = True
|
||||||
if fmt['acodec'] and not fmt['vcodec'] and (fmt['audio_bitrate'] or fmt['bitrate']):
|
if fmt['acodec'] and not fmt['vcodec'] and (fmt['audio_bitrate'] or fmt['bitrate']):
|
||||||
if fmt['bitrate']:
|
if fmt['bitrate']:
|
||||||
fmt['audio_bitrate'] = int(fmt['bitrate']/1000)
|
fmt['audio_bitrate'] = int(fmt['bitrate']/1000)
|
||||||
source = {'type': f"audio/{fmt['ext']}",
|
source = {'type': 'audio/' + fmt['ext'],
|
||||||
'quality_string': audio_quality_string(fmt)}
|
'quality_string': audio_quality_string(fmt)}
|
||||||
source.update(fmt)
|
source.update(fmt)
|
||||||
source['mime_codec'] = f"{source['type']}; codecs=\"{source['acodec']}\""
|
source['mime_codec'] = source['type'] + '; codecs="' + source['acodec'] + '"'
|
||||||
tid = fmt.get('audio_track_id') or 'default'
|
tid = fmt.get('audio_track_id') or 'default'
|
||||||
if tid not in audio_by_track:
|
if tid not in audio_by_track:
|
||||||
audio_by_track[tid] = {
|
audio_by_track[tid] = {
|
||||||
@@ -85,11 +84,11 @@ def get_video_sources(info, target_resolution):
|
|||||||
elif all(fmt[attr] for attr in ('vcodec', 'quality', 'width', 'fps', 'file_size')):
|
elif all(fmt[attr] for attr in ('vcodec', 'quality', 'width', 'fps', 'file_size')):
|
||||||
if codec_name(fmt['vcodec']) == 'unknown':
|
if codec_name(fmt['vcodec']) == 'unknown':
|
||||||
continue
|
continue
|
||||||
source = {'type': f"video/{fmt['ext']}",
|
source = {'type': 'video/' + fmt['ext'],
|
||||||
'quality_string': short_video_quality_string(fmt)}
|
'quality_string': short_video_quality_string(fmt)}
|
||||||
source.update(fmt)
|
source.update(fmt)
|
||||||
source['mime_codec'] = f"{source['type']}; codecs=\"{source['vcodec']}\""
|
source['mime_codec'] = source['type'] + '; codecs="' + source['vcodec'] + '"'
|
||||||
quality = f"{fmt['quality']}p{fmt['fps']}"
|
quality = str(fmt['quality']) + 'p' + str(fmt['fps'])
|
||||||
video_only_sources.setdefault(quality, []).append(source)
|
video_only_sources.setdefault(quality, []).append(source)
|
||||||
|
|
||||||
audio_tracks = []
|
audio_tracks = []
|
||||||
@@ -141,7 +140,7 @@ def get_video_sources(info, target_resolution):
|
|||||||
|
|
||||||
def video_rank(src):
|
def video_rank(src):
|
||||||
''' Sort by settings preference. Use file size as tiebreaker '''
|
''' Sort by settings preference. Use file size as tiebreaker '''
|
||||||
setting_name = f'codec_rank_{codec_name(src["vcodec"])}'
|
setting_name = 'codec_rank_' + codec_name(src['vcodec'])
|
||||||
return (settings.current_settings_dict[setting_name],
|
return (settings.current_settings_dict[setting_name],
|
||||||
src['file_size'])
|
src['file_size'])
|
||||||
pair_info['videos'].sort(key=video_rank)
|
pair_info['videos'].sort(key=video_rank)
|
||||||
@@ -183,7 +182,7 @@ def make_caption_src(info, lang, auto=False, trans_lang=None):
|
|||||||
if auto:
|
if auto:
|
||||||
label += ' (Automatic)'
|
label += ' (Automatic)'
|
||||||
if trans_lang:
|
if trans_lang:
|
||||||
label += f' -> {trans_lang}'
|
label += ' -> ' + trans_lang
|
||||||
|
|
||||||
# Try to use Android caption URL directly (no PO Token needed)
|
# Try to use Android caption URL directly (no PO Token needed)
|
||||||
caption_url = None
|
caption_url = None
|
||||||
@@ -204,7 +203,7 @@ def make_caption_src(info, lang, auto=False, trans_lang=None):
|
|||||||
else:
|
else:
|
||||||
caption_url += '&fmt=vtt'
|
caption_url += '&fmt=vtt'
|
||||||
if trans_lang:
|
if trans_lang:
|
||||||
caption_url += f'&tlang={trans_lang}'
|
caption_url += '&tlang=' + trans_lang
|
||||||
url = util.prefix_url(caption_url)
|
url = util.prefix_url(caption_url)
|
||||||
else:
|
else:
|
||||||
# Fallback to old method
|
# Fallback to old method
|
||||||
@@ -223,7 +222,7 @@ def lang_in(lang, sequence):
|
|||||||
if lang is None:
|
if lang is None:
|
||||||
return False
|
return False
|
||||||
lang = lang[0:2]
|
lang = lang[0:2]
|
||||||
return lang in (item[0:2] for item in sequence)
|
return lang in (l[0:2] for l in sequence)
|
||||||
|
|
||||||
|
|
||||||
def lang_eq(lang1, lang2):
|
def lang_eq(lang1, lang2):
|
||||||
@@ -239,9 +238,9 @@ def equiv_lang_in(lang, sequence):
|
|||||||
e.g. if lang is en, extracts en-GB from sequence.
|
e.g. if lang is en, extracts en-GB from sequence.
|
||||||
Necessary because if only a specific variant like en-GB is available, can't ask YouTube for simply en. Need to get the available variant.'''
|
Necessary because if only a specific variant like en-GB is available, can't ask YouTube for simply en. Need to get the available variant.'''
|
||||||
lang = lang[0:2]
|
lang = lang[0:2]
|
||||||
for item in sequence:
|
for l in sequence:
|
||||||
if item[0:2] == lang:
|
if l[0:2] == lang:
|
||||||
return item
|
return l
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
|
||||||
@@ -311,15 +310,7 @@ def get_subtitle_sources(info):
|
|||||||
sources[-1]['on'] = True
|
sources[-1]['on'] = True
|
||||||
|
|
||||||
if len(sources) == 0:
|
if len(sources) == 0:
|
||||||
# Invariant: with no caption sources there should be no languages
|
assert len(info['automatic_caption_languages']) == 0 and len(info['manual_caption_languages']) == 0
|
||||||
# either. Don't rely on `assert` which is stripped under `python -O`.
|
|
||||||
if (len(info['automatic_caption_languages']) != 0
|
|
||||||
or len(info['manual_caption_languages']) != 0):
|
|
||||||
logger.warning(
|
|
||||||
'Unexpected state: no subtitle sources but %d auto / %d manual languages',
|
|
||||||
len(info['automatic_caption_languages']),
|
|
||||||
len(info['manual_caption_languages']),
|
|
||||||
)
|
|
||||||
|
|
||||||
return sources
|
return sources
|
||||||
|
|
||||||
@@ -357,10 +348,10 @@ def decrypt_signatures(info, video_id):
|
|||||||
|
|
||||||
player_name = info['player_name']
|
player_name = info['player_name']
|
||||||
if player_name in decrypt_cache:
|
if player_name in decrypt_cache:
|
||||||
print(f'Using cached decryption function for: {player_name}')
|
print('Using cached decryption function for: ' + player_name)
|
||||||
info['decryption_function'] = decrypt_cache[player_name]
|
info['decryption_function'] = decrypt_cache[player_name]
|
||||||
else:
|
else:
|
||||||
base_js = util.fetch_url(info['base_js'], debug_name='base.js', report_text=f'Fetched player {player_name}')
|
base_js = util.fetch_url(info['base_js'], debug_name='base.js', report_text='Fetched player ' + player_name)
|
||||||
base_js = base_js.decode('utf-8')
|
base_js = base_js.decode('utf-8')
|
||||||
err = yt_data_extract.extract_decryption_function(info, base_js)
|
err = yt_data_extract.extract_decryption_function(info, base_js)
|
||||||
if err:
|
if err:
|
||||||
@@ -387,11 +378,11 @@ def fetch_player_response(client, video_id):
|
|||||||
def fetch_watch_page_info(video_id, playlist_id, index):
|
def fetch_watch_page_info(video_id, playlist_id, index):
|
||||||
# bpctr=9999999999 will bypass are-you-sure dialogs for controversial
|
# bpctr=9999999999 will bypass are-you-sure dialogs for controversial
|
||||||
# videos
|
# videos
|
||||||
url = f'https://m.youtube.com/embed/{video_id}?bpctr=9999999999'
|
url = 'https://m.youtube.com/embed/' + video_id + '?bpctr=9999999999'
|
||||||
if playlist_id:
|
if playlist_id:
|
||||||
url += f'&list={playlist_id}'
|
url += '&list=' + playlist_id
|
||||||
if index:
|
if index:
|
||||||
url += f'&index={index}'
|
url += '&index=' + index
|
||||||
|
|
||||||
headers = (
|
headers = (
|
||||||
('Accept', '*/*'),
|
('Accept', '*/*'),
|
||||||
@@ -493,7 +484,7 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
|
|||||||
# Register HLS audio tracks for proxy access
|
# Register HLS audio tracks for proxy access
|
||||||
added = 0
|
added = 0
|
||||||
for lang, track in info['hls_audio_tracks'].items():
|
for lang, track in info['hls_audio_tracks'].items():
|
||||||
ck = f"{video_id}_{lang}"
|
ck = video_id + '_' + lang
|
||||||
from youtube.hls_cache import register_track
|
from youtube.hls_cache import register_track
|
||||||
register_track(ck, track['hls_url'],
|
register_track(ck, track['hls_url'],
|
||||||
video_id=video_id, track_id=lang)
|
video_id=video_id, track_id=lang)
|
||||||
@@ -502,7 +493,7 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
|
|||||||
'audio_track_id': lang,
|
'audio_track_id': lang,
|
||||||
'audio_track_name': track['name'],
|
'audio_track_name': track['name'],
|
||||||
'audio_track_is_default': track['is_default'],
|
'audio_track_is_default': track['is_default'],
|
||||||
'itag': f'hls_{lang}',
|
'itag': 'hls_' + lang,
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'audio_bitrate': 128,
|
'audio_bitrate': 128,
|
||||||
'bitrate': 128000,
|
'bitrate': 128000,
|
||||||
@@ -516,7 +507,7 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
|
|||||||
'fps': None,
|
'fps': None,
|
||||||
'init_range': {'start': 0, 'end': 0},
|
'init_range': {'start': 0, 'end': 0},
|
||||||
'index_range': {'start': 0, 'end': 0},
|
'index_range': {'start': 0, 'end': 0},
|
||||||
'url': f'/ytl-api/audio-track?id={urllib.parse.quote(ck)}',
|
'url': '/ytl-api/audio-track?id=' + urllib.parse.quote(ck),
|
||||||
's': None,
|
's': None,
|
||||||
'sp': None,
|
'sp': None,
|
||||||
'quality': None,
|
'quality': None,
|
||||||
@@ -538,11 +529,11 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
|
|||||||
|
|
||||||
# Register HLS manifest for proxying
|
# Register HLS manifest for proxying
|
||||||
if info['hls_manifest_url']:
|
if info['hls_manifest_url']:
|
||||||
ck = f"{video_id}_video"
|
ck = video_id + '_video'
|
||||||
from youtube.hls_cache import register_track
|
from youtube.hls_cache import register_track
|
||||||
register_track(ck, info['hls_manifest_url'], video_id=video_id, track_id='video')
|
register_track(ck, info['hls_manifest_url'], video_id=video_id, track_id='video')
|
||||||
# Use proxy URL instead of direct Google Video URL
|
# Use proxy URL instead of direct Google Video URL
|
||||||
info['hls_manifest_url'] = f'/ytl-api/hls-manifest?id={urllib.parse.quote(ck)}'
|
info['hls_manifest_url'] = '/ytl-api/hls-manifest?id=' + urllib.parse.quote(ck)
|
||||||
|
|
||||||
# Fallback to 'ios' if no valid URLs are found
|
# Fallback to 'ios' if no valid URLs are found
|
||||||
if not info.get('formats') or info.get('player_urls_missing'):
|
if not info.get('formats') or info.get('player_urls_missing'):
|
||||||
@@ -566,7 +557,7 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
|
|||||||
if info.get('formats'):
|
if info.get('formats'):
|
||||||
decryption_error = decrypt_signatures(info, video_id)
|
decryption_error = decrypt_signatures(info, video_id)
|
||||||
if decryption_error:
|
if decryption_error:
|
||||||
info['playability_error'] = f'Error decrypting url signatures: {decryption_error}'
|
info['playability_error'] = 'Error decrypting url signatures: ' + decryption_error
|
||||||
|
|
||||||
# check if urls ready (non-live format) in former livestream
|
# check if urls ready (non-live format) in former livestream
|
||||||
# urls not ready if all of them have no filesize
|
# urls not ready if all of them have no filesize
|
||||||
@@ -623,9 +614,9 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
|
|||||||
|
|
||||||
def video_quality_string(format):
|
def video_quality_string(format):
|
||||||
if format['vcodec']:
|
if format['vcodec']:
|
||||||
result = f"{format['width'] or '?'}x{format['height'] or '?'}"
|
result = str(format['width'] or '?') + 'x' + str(format['height'] or '?')
|
||||||
if format['fps']:
|
if format['fps']:
|
||||||
result += f" {format['fps']}fps"
|
result += ' ' + str(format['fps']) + 'fps'
|
||||||
return result
|
return result
|
||||||
elif format['acodec']:
|
elif format['acodec']:
|
||||||
return 'audio only'
|
return 'audio only'
|
||||||
@@ -634,7 +625,7 @@ def video_quality_string(format):
|
|||||||
|
|
||||||
|
|
||||||
def short_video_quality_string(fmt):
|
def short_video_quality_string(fmt):
|
||||||
result = f"{fmt['quality'] or '?'}p"
|
result = str(fmt['quality'] or '?') + 'p'
|
||||||
if fmt['fps']:
|
if fmt['fps']:
|
||||||
result += str(fmt['fps'])
|
result += str(fmt['fps'])
|
||||||
if fmt['vcodec'].startswith('av01'):
|
if fmt['vcodec'].startswith('av01'):
|
||||||
@@ -642,18 +633,18 @@ def short_video_quality_string(fmt):
|
|||||||
elif fmt['vcodec'].startswith('avc'):
|
elif fmt['vcodec'].startswith('avc'):
|
||||||
result += ' h264'
|
result += ' h264'
|
||||||
else:
|
else:
|
||||||
result += f" {fmt['vcodec']}"
|
result += ' ' + fmt['vcodec']
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
def audio_quality_string(fmt):
|
def audio_quality_string(fmt):
|
||||||
if fmt['acodec']:
|
if fmt['acodec']:
|
||||||
if fmt['audio_bitrate']:
|
if fmt['audio_bitrate']:
|
||||||
result = f"{fmt['audio_bitrate']}k"
|
result = '%d' % fmt['audio_bitrate'] + 'k'
|
||||||
else:
|
else:
|
||||||
result = '?k'
|
result = '?k'
|
||||||
if fmt['audio_sample_rate']:
|
if fmt['audio_sample_rate']:
|
||||||
result += f" {'%.3G' % (fmt['audio_sample_rate']/1000)}kHz"
|
result += ' ' + '%.3G' % (fmt['audio_sample_rate']/1000) + 'kHz'
|
||||||
return result
|
return result
|
||||||
elif fmt['vcodec']:
|
elif fmt['vcodec']:
|
||||||
return 'video only'
|
return 'video only'
|
||||||
@@ -678,6 +669,7 @@ def format_bytes(bytes):
|
|||||||
@yt_app.route('/ytl-api/audio-track-proxy')
|
@yt_app.route('/ytl-api/audio-track-proxy')
|
||||||
def audio_track_proxy():
|
def audio_track_proxy():
|
||||||
"""Proxy for DASH audio tracks to avoid throttling."""
|
"""Proxy for DASH audio tracks to avoid throttling."""
|
||||||
|
cache_key = request.args.get('id', '')
|
||||||
audio_url = request.args.get('url', '')
|
audio_url = request.args.get('url', '')
|
||||||
|
|
||||||
if not audio_url:
|
if not audio_url:
|
||||||
@@ -700,7 +692,7 @@ def audio_track_proxy():
|
|||||||
@yt_app.route('/ytl-api/audio-track')
|
@yt_app.route('/ytl-api/audio-track')
|
||||||
def get_audio_track():
|
def get_audio_track():
|
||||||
"""Proxy HLS audio/video: playlist or individual segment."""
|
"""Proxy HLS audio/video: playlist or individual segment."""
|
||||||
from youtube.hls_cache import get_hls_url
|
from youtube.hls_cache import get_hls_url, _tracks
|
||||||
|
|
||||||
cache_key = request.args.get('id', '')
|
cache_key = request.args.get('id', '')
|
||||||
seg_url = request.args.get('seg', '')
|
seg_url = request.args.get('seg', '')
|
||||||
@@ -737,9 +729,9 @@ def get_audio_track():
|
|||||||
seg = line if line.startswith('http') else urljoin(playlist_base, line)
|
seg = line if line.startswith('http') else urljoin(playlist_base, line)
|
||||||
# Always use &seg= parameter, never &url= for segments
|
# Always use &seg= parameter, never &url= for segments
|
||||||
playlist_lines.append(
|
playlist_lines.append(
|
||||||
f'{base_url}/ytl-api/audio-track?id='
|
base_url + '/ytl-api/audio-track?id='
|
||||||
f'{urllib.parse.quote(cache_key)}'
|
+ urllib.parse.quote(cache_key)
|
||||||
f'&seg={urllib.parse.quote(seg, safe="")}'
|
+ '&seg=' + urllib.parse.quote(seg, safe='')
|
||||||
)
|
)
|
||||||
|
|
||||||
playlist = '\n'.join(playlist_lines)
|
playlist = '\n'.join(playlist_lines)
|
||||||
@@ -797,7 +789,9 @@ def get_audio_track():
|
|||||||
return url
|
return url
|
||||||
if not url.startswith('http://') and not url.startswith('https://'):
|
if not url.startswith('http://') and not url.startswith('https://'):
|
||||||
url = urljoin(playlist_base, url)
|
url = urljoin(playlist_base, url)
|
||||||
return f'{base_url}/ytl-api/audio-track?id={urllib.parse.quote(cache_key)}&seg={urllib.parse.quote(url, safe="")}'
|
return (base_url + '/ytl-api/audio-track?id='
|
||||||
|
+ urllib.parse.quote(cache_key)
|
||||||
|
+ '&seg=' + urllib.parse.quote(url, safe=''))
|
||||||
|
|
||||||
playlist_lines = []
|
playlist_lines = []
|
||||||
for line in playlist.split('\n'):
|
for line in playlist.split('\n'):
|
||||||
@@ -810,7 +804,7 @@ def get_audio_track():
|
|||||||
if line.startswith('#') and 'URI=' in line:
|
if line.startswith('#') and 'URI=' in line:
|
||||||
def rewrite_uri_attr(match):
|
def rewrite_uri_attr(match):
|
||||||
uri = match.group(1)
|
uri = match.group(1)
|
||||||
return f'URI="{proxy_url(uri)}"'
|
return 'URI="' + proxy_url(uri) + '"'
|
||||||
line = _re.sub(r'URI="([^"]+)"', rewrite_uri_attr, line)
|
line = _re.sub(r'URI="([^"]+)"', rewrite_uri_attr, line)
|
||||||
playlist_lines.append(line)
|
playlist_lines.append(line)
|
||||||
elif line.startswith('#'):
|
elif line.startswith('#'):
|
||||||
@@ -881,7 +875,9 @@ def get_audio_track():
|
|||||||
if segment_url.startswith('/ytl-api/audio-track'):
|
if segment_url.startswith('/ytl-api/audio-track'):
|
||||||
return segment_url
|
return segment_url
|
||||||
base_url = request.url_root.rstrip('/')
|
base_url = request.url_root.rstrip('/')
|
||||||
return f'{base_url}/ytl-api/audio-track?id={urllib.parse.quote(cache_key)}&seg={urllib.parse.quote(segment_url)}'
|
return (base_url + '/ytl-api/audio-track?id='
|
||||||
|
+ urllib.parse.quote(cache_key)
|
||||||
|
+ '&seg=' + urllib.parse.quote(segment_url))
|
||||||
|
|
||||||
playlist_lines = []
|
playlist_lines = []
|
||||||
for line in playlist.split('\n'):
|
for line in playlist.split('\n'):
|
||||||
@@ -920,7 +916,7 @@ def get_hls_manifest():
|
|||||||
flask.abort(404, 'HLS manifest not found')
|
flask.abort(404, 'HLS manifest not found')
|
||||||
|
|
||||||
try:
|
try:
|
||||||
print('[hls-manifest] Fetching HLS manifest...')
|
print(f'[hls-manifest] Fetching HLS manifest...')
|
||||||
manifest = util.fetch_url(hls_url,
|
manifest = util.fetch_url(hls_url,
|
||||||
headers=(('User-Agent', 'Mozilla/5.0'),),
|
headers=(('User-Agent', 'Mozilla/5.0'),),
|
||||||
debug_name='hls_manifest').decode('utf-8')
|
debug_name='hls_manifest').decode('utf-8')
|
||||||
@@ -945,10 +941,14 @@ def get_hls_manifest():
|
|||||||
|
|
||||||
if is_audio_track:
|
if is_audio_track:
|
||||||
# Audio track playlist - proxy through audio-track endpoint
|
# Audio track playlist - proxy through audio-track endpoint
|
||||||
return f'{base_url}/ytl-api/audio-track?id={urllib.parse.quote(cache_key)}&url={urllib.parse.quote(url, safe="")}'
|
return (base_url + '/ytl-api/audio-track?id='
|
||||||
|
+ urllib.parse.quote(cache_key)
|
||||||
|
+ '&url=' + urllib.parse.quote(url, safe=''))
|
||||||
else:
|
else:
|
||||||
# Video segment or variant playlist - proxy through audio-track endpoint
|
# Video segment or variant playlist - proxy through audio-track endpoint
|
||||||
return f'{base_url}/ytl-api/audio-track?id={urllib.parse.quote(cache_key)}&seg={urllib.parse.quote(url, safe="")}'
|
return (base_url + '/ytl-api/audio-track?id='
|
||||||
|
+ urllib.parse.quote(cache_key)
|
||||||
|
+ '&seg=' + urllib.parse.quote(url, safe=''))
|
||||||
|
|
||||||
# Parse and rewrite the manifest
|
# Parse and rewrite the manifest
|
||||||
manifest_lines = []
|
manifest_lines = []
|
||||||
@@ -966,7 +966,7 @@ def get_hls_manifest():
|
|||||||
nonlocal rewritten_count
|
nonlocal rewritten_count
|
||||||
uri = match.group(1)
|
uri = match.group(1)
|
||||||
rewritten_count += 1
|
rewritten_count += 1
|
||||||
return f'URI="{rewrite_url(uri, is_audio_track=True)}"'
|
return 'URI="' + rewrite_url(uri, is_audio_track=True) + '"'
|
||||||
line = _re.sub(r'URI="([^"]+)"', rewrite_media_uri, line)
|
line = _re.sub(r'URI="([^"]+)"', rewrite_media_uri, line)
|
||||||
manifest_lines.append(line)
|
manifest_lines.append(line)
|
||||||
elif line.startswith('#'):
|
elif line.startswith('#'):
|
||||||
@@ -1018,8 +1018,7 @@ def get_storyboard_vtt():
|
|||||||
for i, board in enumerate(boards):
|
for i, board in enumerate(boards):
|
||||||
*t, _, sigh = board.split("#")
|
*t, _, sigh = board.split("#")
|
||||||
width, height, count, width_cnt, height_cnt, interval = map(int, t)
|
width, height, count, width_cnt, height_cnt, interval = map(int, t)
|
||||||
if height != wanted_height:
|
if height != wanted_height: continue
|
||||||
continue
|
|
||||||
q['sigh'] = [sigh]
|
q['sigh'] = [sigh]
|
||||||
url = f"{base_url}?{urlencode(q, doseq=True)}"
|
url = f"{base_url}?{urlencode(q, doseq=True)}"
|
||||||
storyboard = SimpleNamespace(
|
storyboard = SimpleNamespace(
|
||||||
@@ -1045,7 +1044,7 @@ def get_storyboard_vtt():
|
|||||||
ts = 0 # current timestamp
|
ts = 0 # current timestamp
|
||||||
|
|
||||||
for i in range(storyboard.storyboard_count):
|
for i in range(storyboard.storyboard_count):
|
||||||
url = f'/{storyboard.url.replace("$M", str(i))}'
|
url = '/' + storyboard.url.replace("$M", str(i))
|
||||||
interval = storyboard.interval
|
interval = storyboard.interval
|
||||||
w, h = storyboard.width, storyboard.height
|
w, h = storyboard.width, storyboard.height
|
||||||
w_cnt, h_cnt = storyboard.width_cnt, storyboard.height_cnt
|
w_cnt, h_cnt = storyboard.width_cnt, storyboard.height_cnt
|
||||||
@@ -1070,7 +1069,7 @@ def get_watch_page(video_id=None):
|
|||||||
if not video_id:
|
if not video_id:
|
||||||
return flask.render_template('error.html', error_message='Missing video id'), 404
|
return flask.render_template('error.html', error_message='Missing video id'), 404
|
||||||
if len(video_id) < 11:
|
if len(video_id) < 11:
|
||||||
return flask.render_template('error.html', error_message=f'Incomplete video id (too short): {video_id}'), 404
|
return flask.render_template('error.html', error_message='Incomplete video id (too short): ' + video_id), 404
|
||||||
|
|
||||||
time_start_str = request.args.get('t', '0s')
|
time_start_str = request.args.get('t', '0s')
|
||||||
time_start = 0
|
time_start = 0
|
||||||
@@ -1133,9 +1132,9 @@ def get_watch_page(video_id=None):
|
|||||||
util.prefix_urls(item)
|
util.prefix_urls(item)
|
||||||
util.add_extra_html_info(item)
|
util.add_extra_html_info(item)
|
||||||
if playlist_id:
|
if playlist_id:
|
||||||
item['url'] += f'&list={playlist_id}'
|
item['url'] += '&list=' + playlist_id
|
||||||
if item['index']:
|
if item['index']:
|
||||||
item['url'] += f'&index={item["index"]}'
|
item['url'] += '&index=' + str(item['index'])
|
||||||
info['playlist']['author_url'] = util.prefix_url(
|
info['playlist']['author_url'] = util.prefix_url(
|
||||||
info['playlist']['author_url'])
|
info['playlist']['author_url'])
|
||||||
if settings.img_prefix:
|
if settings.img_prefix:
|
||||||
@@ -1151,16 +1150,16 @@ def get_watch_page(video_id=None):
|
|||||||
filename = title
|
filename = title
|
||||||
ext = fmt.get('ext')
|
ext = fmt.get('ext')
|
||||||
if ext:
|
if ext:
|
||||||
filename += f'.{ext}'
|
filename += '.' + ext
|
||||||
fmt['url'] = fmt['url'].replace(
|
fmt['url'] = fmt['url'].replace(
|
||||||
'/videoplayback',
|
'/videoplayback',
|
||||||
f'/videoplayback/name/{filename}')
|
'/videoplayback/name/' + filename)
|
||||||
|
|
||||||
download_formats = []
|
download_formats = []
|
||||||
|
|
||||||
for format in (info['formats'] + info['hls_formats']):
|
for format in (info['formats'] + info['hls_formats']):
|
||||||
if format['acodec'] and format['vcodec']:
|
if format['acodec'] and format['vcodec']:
|
||||||
codecs_string = f"{format['acodec']}, {format['vcodec']}"
|
codecs_string = format['acodec'] + ', ' + format['vcodec']
|
||||||
else:
|
else:
|
||||||
codecs_string = format['acodec'] or format['vcodec'] or '?'
|
codecs_string = format['acodec'] or format['vcodec'] or '?'
|
||||||
download_formats.append({
|
download_formats.append({
|
||||||
@@ -1183,6 +1182,7 @@ def get_watch_page(video_id=None):
|
|||||||
uni_sources = video_sources['uni_sources']
|
uni_sources = video_sources['uni_sources']
|
||||||
pair_sources = video_sources['pair_sources']
|
pair_sources = video_sources['pair_sources']
|
||||||
pair_idx = video_sources['pair_idx']
|
pair_idx = video_sources['pair_idx']
|
||||||
|
audio_track_sources = video_sources['audio_track_sources']
|
||||||
|
|
||||||
# Build audio tracks list from HLS
|
# Build audio tracks list from HLS
|
||||||
audio_tracks = []
|
audio_tracks = []
|
||||||
@@ -1239,9 +1239,12 @@ def get_watch_page(video_id=None):
|
|||||||
for source in subtitle_sources:
|
for source in subtitle_sources:
|
||||||
best_caption_parse = urllib.parse.urlparse(
|
best_caption_parse = urllib.parse.urlparse(
|
||||||
source['url'].lstrip('/'))
|
source['url'].lstrip('/'))
|
||||||
transcript_url = f'{util.URL_ORIGIN}/watch/transcript{best_caption_parse.path}?{best_caption_parse.query}'
|
transcript_url = (util.URL_ORIGIN
|
||||||
|
+ '/watch/transcript'
|
||||||
|
+ best_caption_parse.path
|
||||||
|
+ '?' + best_caption_parse.query)
|
||||||
other_downloads.append({
|
other_downloads.append({
|
||||||
'label': f'Video Transcript: {source["label"]}',
|
'label': 'Video Transcript: ' + source['label'],
|
||||||
'ext': 'txt',
|
'ext': 'txt',
|
||||||
'url': transcript_url
|
'url': transcript_url
|
||||||
})
|
})
|
||||||
@@ -1252,7 +1255,7 @@ def get_watch_page(video_id=None):
|
|||||||
template_name = 'watch.html'
|
template_name = 'watch.html'
|
||||||
return flask.render_template(template_name,
|
return flask.render_template(template_name,
|
||||||
header_playlist_names = local_playlist.get_playlist_names(),
|
header_playlist_names = local_playlist.get_playlist_names(),
|
||||||
uploader_channel_url = f'/{info["author_url"]}' if info['author_url'] else '',
|
uploader_channel_url = ('/' + info['author_url']) if info['author_url'] else '',
|
||||||
time_published = info['time_published'],
|
time_published = info['time_published'],
|
||||||
view_count = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("view_count", None)),
|
view_count = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("view_count", None)),
|
||||||
like_count = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("like_count", None)),
|
like_count = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("like_count", None)),
|
||||||
@@ -1294,10 +1297,10 @@ def get_watch_page(video_id=None):
|
|||||||
ip_address = info['ip_address'] if settings.route_tor else None,
|
ip_address = info['ip_address'] if settings.route_tor else None,
|
||||||
invidious_used = info['invidious_used'],
|
invidious_used = info['invidious_used'],
|
||||||
invidious_reload_button = info['invidious_reload_button'],
|
invidious_reload_button = info['invidious_reload_button'],
|
||||||
video_url = f'{util.URL_ORIGIN}/watch?v={video_id}',
|
video_url = util.URL_ORIGIN + '/watch?v=' + video_id,
|
||||||
video_id = video_id,
|
video_id = video_id,
|
||||||
storyboard_url = (f'{util.URL_ORIGIN}/ytl-api/storyboard.vtt?'
|
storyboard_url = (util.URL_ORIGIN + '/ytl-api/storyboard.vtt?' +
|
||||||
f'{urlencode([("spec_url", info["storyboard_spec_url"])])}'
|
urlencode([('spec_url', info['storyboard_spec_url'])])
|
||||||
if info['storyboard_spec_url'] else None),
|
if info['storyboard_spec_url'] else None),
|
||||||
|
|
||||||
js_data = {
|
js_data = {
|
||||||
@@ -1324,7 +1327,7 @@ def get_watch_page(video_id=None):
|
|||||||
|
|
||||||
@yt_app.route('/api/<path:dummy>')
|
@yt_app.route('/api/<path:dummy>')
|
||||||
def get_captions(dummy):
|
def get_captions(dummy):
|
||||||
url = f'https://www.youtube.com{request.full_path}'
|
url = 'https://www.youtube.com' + request.full_path
|
||||||
try:
|
try:
|
||||||
result = util.fetch_url(url, headers=util.mobile_ua)
|
result = util.fetch_url(url, headers=util.mobile_ua)
|
||||||
result = result.replace(b"align:start position:0%", b"")
|
result = result.replace(b"align:start position:0%", b"")
|
||||||
@@ -1339,9 +1342,12 @@ inner_timestamp_removal_reg = re.compile(r'<[^>]+>')
|
|||||||
@yt_app.route('/watch/transcript/<path:caption_path>')
|
@yt_app.route('/watch/transcript/<path:caption_path>')
|
||||||
def get_transcript(caption_path):
|
def get_transcript(caption_path):
|
||||||
try:
|
try:
|
||||||
captions = util.fetch_url(f'https://www.youtube.com/{caption_path}?{request.environ["QUERY_STRING"]}').decode('utf-8')
|
captions = util.fetch_url('https://www.youtube.com/'
|
||||||
|
+ caption_path
|
||||||
|
+ '?' + request.environ['QUERY_STRING']).decode('utf-8')
|
||||||
except util.FetchError as e:
|
except util.FetchError as e:
|
||||||
msg = f'Error retrieving captions: {e}\n\nThe caption url may have expired.'
|
msg = ('Error retrieving captions: ' + str(e) + '\n\n'
|
||||||
|
+ 'The caption url may have expired.')
|
||||||
print(msg)
|
print(msg)
|
||||||
return flask.Response(
|
return flask.Response(
|
||||||
msg,
|
msg,
|
||||||
@@ -1389,7 +1395,7 @@ def get_transcript(caption_path):
|
|||||||
result = ''
|
result = ''
|
||||||
for seg in segments:
|
for seg in segments:
|
||||||
if seg['text'] != ' ':
|
if seg['text'] != ' ':
|
||||||
result += f"{seg['begin']} {seg['text']}\r\n"
|
result += seg['begin'] + ' ' + seg['text'] + '\r\n'
|
||||||
|
|
||||||
return flask.Response(result.encode('utf-8'),
|
return flask.Response(result.encode('utf-8'),
|
||||||
mimetype='text/plain;charset=UTF-8')
|
mimetype='text/plain;charset=UTF-8')
|
||||||
|
|||||||
@@ -212,7 +212,7 @@ def extract_date(date_text):
|
|||||||
month, day, year = parts[-3:]
|
month, day, year = parts[-3:]
|
||||||
month = MONTH_ABBREVIATIONS.get(month[0:3]) # slicing in case they start writing out the full month name
|
month = MONTH_ABBREVIATIONS.get(month[0:3]) # slicing in case they start writing out the full month name
|
||||||
if month and (re.fullmatch(r'\d\d?', day) is not None) and (re.fullmatch(r'\d{4}', year) is not None):
|
if month and (re.fullmatch(r'\d\d?', day) is not None) and (re.fullmatch(r'\d{4}', year) is not None):
|
||||||
return f'{year}-{month}-{day}'
|
return year + '-' + month + '-' + day
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def check_missing_keys(object, *key_sequences):
|
def check_missing_keys(object, *key_sequences):
|
||||||
@@ -222,7 +222,7 @@ def check_missing_keys(object, *key_sequences):
|
|||||||
for key in key_sequence:
|
for key in key_sequence:
|
||||||
_object = _object[key]
|
_object = _object[key]
|
||||||
except (KeyError, IndexError, TypeError):
|
except (KeyError, IndexError, TypeError):
|
||||||
return f'Could not find {key}'
|
return 'Could not find ' + key
|
||||||
|
|
||||||
return None
|
return None
|
||||||
|
|
||||||
@@ -467,7 +467,7 @@ def extract_item_info(item, additional_info={}):
|
|||||||
['shortBylineText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId'],
|
['shortBylineText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId'],
|
||||||
['ownerText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId']
|
['ownerText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId']
|
||||||
))
|
))
|
||||||
info['author_url'] = f'https://www.youtube.com/channel/{info["author_id"]}' if info['author_id'] else None
|
info['author_url'] = ('https://www.youtube.com/channel/' + info['author_id']) if info['author_id'] else None
|
||||||
info['description'] = extract_formatted_text(multi_deep_get(
|
info['description'] = extract_formatted_text(multi_deep_get(
|
||||||
item,
|
item,
|
||||||
['descriptionText'], ['descriptionSnippet'],
|
['descriptionText'], ['descriptionSnippet'],
|
||||||
|
|||||||
@@ -305,7 +305,7 @@ def extract_playlist_metadata(polymer_json):
|
|||||||
metadata['description'] = desc
|
metadata['description'] = desc
|
||||||
|
|
||||||
if metadata['author_id']:
|
if metadata['author_id']:
|
||||||
metadata['author_url'] = f'https://www.youtube.com/channel/{metadata["author_id"]}'
|
metadata['author_url'] = 'https://www.youtube.com/channel/' + metadata['author_id']
|
||||||
|
|
||||||
if metadata['first_video_id'] is None:
|
if metadata['first_video_id'] is None:
|
||||||
metadata['thumbnail'] = None
|
metadata['thumbnail'] = None
|
||||||
|
|||||||
@@ -650,9 +650,9 @@ def _extract_playability_error(info, player_response, error_prefix=''):
|
|||||||
)
|
)
|
||||||
|
|
||||||
if playability_status not in (None, 'OK'):
|
if playability_status not in (None, 'OK'):
|
||||||
info['playability_error'] = f'{error_prefix}{playability_reason}'
|
info['playability_error'] = error_prefix + playability_reason
|
||||||
elif not info['playability_error']: # do not override
|
elif not info['playability_error']: # do not override
|
||||||
info['playability_error'] = f'{error_prefix}Unknown playability error'
|
info['playability_error'] = error_prefix + 'Unknown playability error'
|
||||||
|
|
||||||
SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
||||||
def extract_watch_info(polymer_json):
|
def extract_watch_info(polymer_json):
|
||||||
@@ -726,7 +726,7 @@ def extract_watch_info(polymer_json):
|
|||||||
# Store the full URL from the player response (includes valid tokens)
|
# Store the full URL from the player response (includes valid tokens)
|
||||||
if base_url:
|
if base_url:
|
||||||
normalized = normalize_url(base_url) if base_url.startswith('/') or not base_url.startswith('http') else base_url
|
normalized = normalize_url(base_url) if base_url.startswith('/') or not base_url.startswith('http') else base_url
|
||||||
info['_caption_track_urls'][f'{lang_code}_{"asr" if caption_track.get("kind") == "asr" else ""}'] = normalized
|
info['_caption_track_urls'][lang_code + ('_asr' if caption_track.get('kind') == 'asr' else '')] = normalized
|
||||||
lang_name = deep_get(urllib.parse.parse_qs(urllib.parse.urlparse(base_url).query), 'name', 0)
|
lang_name = deep_get(urllib.parse.parse_qs(urllib.parse.urlparse(base_url).query), 'name', 0)
|
||||||
if lang_name:
|
if lang_name:
|
||||||
info['_manual_caption_language_names'][lang_code] = lang_name
|
info['_manual_caption_language_names'][lang_code] = lang_name
|
||||||
@@ -806,7 +806,7 @@ def extract_watch_info(polymer_json):
|
|||||||
info['allowed_countries'] = mf.get('availableCountries', [])
|
info['allowed_countries'] = mf.get('availableCountries', [])
|
||||||
|
|
||||||
# other stuff
|
# other stuff
|
||||||
info['author_url'] = f'https://www.youtube.com/channel/{info["author_id"]}' if info['author_id'] else None
|
info['author_url'] = 'https://www.youtube.com/channel/' + info['author_id'] if info['author_id'] else None
|
||||||
info['storyboard_spec_url'] = deep_get(player_response, 'storyboards', 'playerStoryboardSpecRenderer', 'spec')
|
info['storyboard_spec_url'] = deep_get(player_response, 'storyboards', 'playerStoryboardSpecRenderer', 'spec')
|
||||||
|
|
||||||
return info
|
return info
|
||||||
@@ -912,12 +912,12 @@ def get_caption_url(info, language, format, automatic=False, translation_languag
|
|||||||
url = info['_captions_base_url']
|
url = info['_captions_base_url']
|
||||||
if not url:
|
if not url:
|
||||||
return None
|
return None
|
||||||
url += f'&lang={language}'
|
url += '&lang=' + language
|
||||||
url += f'&fmt={format}'
|
url += '&fmt=' + format
|
||||||
if automatic:
|
if automatic:
|
||||||
url += '&kind=asr'
|
url += '&kind=asr'
|
||||||
elif language in info['_manual_caption_language_names']:
|
elif language in info['_manual_caption_language_names']:
|
||||||
url += f'&name={urllib.parse.quote(info["_manual_caption_language_names"][language], safe="")}'
|
url += '&name=' + urllib.parse.quote(info['_manual_caption_language_names'][language], safe='')
|
||||||
|
|
||||||
if translation_language:
|
if translation_language:
|
||||||
url += '&tlang=' + translation_language
|
url += '&tlang=' + translation_language
|
||||||
@@ -964,7 +964,7 @@ def extract_decryption_function(info, base_js):
|
|||||||
return 'Could not find var_name'
|
return 'Could not find var_name'
|
||||||
|
|
||||||
var_name = var_with_operation_match.group(1)
|
var_name = var_with_operation_match.group(1)
|
||||||
var_body_match = re.search(rf'var {re.escape(var_name)}=\{{(.*?)\}};', base_js, flags=re.DOTALL)
|
var_body_match = re.search(r'var ' + re.escape(var_name) + r'=\{(.*?)\};', base_js, flags=re.DOTALL)
|
||||||
if var_body_match is None:
|
if var_body_match is None:
|
||||||
return 'Could not find var_body'
|
return 'Could not find var_body'
|
||||||
|
|
||||||
@@ -988,7 +988,7 @@ def extract_decryption_function(info, base_js):
|
|||||||
elif op_body.startswith('var c=a[0]'):
|
elif op_body.startswith('var c=a[0]'):
|
||||||
operation_definitions[op_name] = 2
|
operation_definitions[op_name] = 2
|
||||||
else:
|
else:
|
||||||
return f'Unknown op_body: {op_body}'
|
return 'Unknown op_body: ' + op_body
|
||||||
|
|
||||||
decryption_function = []
|
decryption_function = []
|
||||||
for op_with_arg in function_body:
|
for op_with_arg in function_body:
|
||||||
@@ -997,7 +997,7 @@ def extract_decryption_function(info, base_js):
|
|||||||
return 'Could not parse operation with arg'
|
return 'Could not parse operation with arg'
|
||||||
op_name = match.group(2).strip('[].')
|
op_name = match.group(2).strip('[].')
|
||||||
if op_name not in operation_definitions:
|
if op_name not in operation_definitions:
|
||||||
return f'Unknown op_name: {op_name}'
|
return 'Unknown op_name: ' + str(op_name)
|
||||||
op_argument = match.group(3)
|
op_argument = match.group(3)
|
||||||
decryption_function.append([operation_definitions[op_name], int(op_argument)])
|
decryption_function.append([operation_definitions[op_name], int(op_argument)])
|
||||||
|
|
||||||
@@ -1028,5 +1028,5 @@ def decrypt_signatures(info):
|
|||||||
_operation_2(a, argument)
|
_operation_2(a, argument)
|
||||||
|
|
||||||
signature = ''.join(a)
|
signature = ''.join(a)
|
||||||
format['url'] += f'&{format["sp"]}={signature}'
|
format['url'] += '&' + format['sp'] + '=' + signature
|
||||||
return False
|
return False
|
||||||
|
|||||||
Reference in New Issue
Block a user