Metadata-Version: 2.1
Name: post-archiver
Version: 1.0.0
Summary: A tool to scrape YouTube community posts
Author-email: sadadYes <syaddadpunya@gmail.com>
License: MIT License
        
        Copyright (c) 2024 Sadad
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE.
        
Project-URL: Homepage, https://github.com/sadadYes/post-archiver
Project-URL: Repository, https://github.com/sadadYes/post-archiver.git
Project-URL: Documentation, https://github.com/sadadYes/post-archiver#readme
Project-URL: Bug Tracker, https://github.com/sadadYes/post-archiver/issues
Keywords: youtube,scraper,community,posts,python
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: beautifulsoup4>=4.12.0
Requires-Dist: blinker==1.7.0
Requires-Dist: selenium-wire>=5.1.0
Requires-Dist: selenium>=4.10.0
Requires-Dist: packaging>=23.0
Requires-Dist: setuptools>=67.0.0
Requires-Dist: requests>=2.31.0
Requires-Dist: urllib3>=2.1.0
Requires-Dist: pathlib>=1.0.1

# YouTube Community Post Scraper

A Python tool to scrape posts from YouTube community tabs.

## Dependencies

* Firefox browser needs to be installed
* GeckoDriver needs to be installed and in your PATH
* Python 3.7 or higher

## Features

- Scrape posts from YouTube community tabs
- Download images from posts
- Collect post comments
- Proxy support
- Progress saving
- Configurable output directory

## Installation

Download and install using pip:
```bash
pip install post-archiver
```

Alternatively, if you want to install from source:
```bash
git clone https://github.com/sadadYes/post-archiver.git
cd post-archiver
pip install -e .
```

## Usage

```
usage: post-archiver [OPTIONS] url [amount]

YouTube Community Posts Scraper

positional arguments:
  url                   YouTube channel community URL
  amount                Amount of posts to get (default: max)

options:
  -h, --help            show this help message and exit
  -c, --get-comments    Get comments from posts (default: False)
  -i, --get-images      Get images from posts (default: False)
  -d, --download-images
                        Download images (requires --get-images)
  -q IMAGE_QUALITY, --image-quality IMAGE_QUALITY
                        Image quality: sd, hd, or all (default: all)
  --proxy PROXY         Proxy file or single proxy string
  -o OUTPUT, --output OUTPUT
                        Output directory (default: current directory)
  -v, --verbose         Show basic progress information
  -t, --trace           Show detailed debug information
  --version             show program's version number and exit

Proxy format:
  Single proxy: <scheme>://<username>:<password>@<host>:<port>
  Proxy file: One proxy per line using the same format
  Supported schemes: socks5, http, https

Amount:
  Specify number of posts to scrape (default: max)
  Use 'max' or any number <= 0 to scrape all posts

Examples:
  post-archiver https://www.youtube.com/@channel/community
  post-archiver https://www.youtube.com/@channel/community 50
  post-archiver -c -i -d -q hd https://www.youtube.com/@channel/community max
  post-archiver --proxy proxies.txt https://www.youtube.com/@channel/community 100
  post-archiver --proxy socks5://username:password@host:port https://www.youtube.com/@channel/community
  post-archiver --proxy http://username:password@host:port https://www.youtube.com/@channel/community
```

## License

MIT License

