diff --git a/src/auto_archiver/archivers/generic_archiver/__manifest__.py b/src/auto_archiver/archivers/generic_archiver/__manifest__.py new file mode 100644 index 0000000..67c75f2 --- /dev/null +++ b/src/auto_archiver/archivers/generic_archiver/__manifest__.py @@ -0,0 +1,32 @@ +{ + 'name': 'Generic Archiver', + 'version': '0.1.0', + 'author': 'Bellingcat', + 'type': ['archiver'], + 'requires_setup': False, + 'depends': ['core'], + 'external_dependencies': { + 'python': ['yt_dlp', 'requests', 'loguru', 'slugify'], + }, + 'description': """ +This is the generic archiver used by auto-archiver, which uses `yt-dlp` under the hood. + +This module is responsible for downloading and processing media content from platforms +supported by `yt-dlp`, such as YouTube, Facebook, and others. It provides functionality +for retrieving videos, subtitles, comments, and other metadata, and it integrates with +the broader archiving framework. + +### Features +- Supports downloading videos and playlists. +- Retrieves metadata like titles, descriptions, upload dates, and durations. +- Downloads subtitles and comments when enabled. +- Configurable options for handling live streams, proxies, and more. + +### Dropins +- For websites supported by `yt-dlp` that also contain posts in addition to videos + (e.g. Facebook, Twitter, Bluesky), dropins can be created to extract post data and create + metadata objects. Some dropins are included in this generic_archiver by default, but +custom dropins can be created to handle additional websites and passed to the archiver +via the command line using the `--dropins` option (TODO!). +""" +} \ No newline at end of file diff --git a/src/auto_archiver/archivers/generic_archiver/generic_archiver.py b/src/auto_archiver/archivers/generic_archiver/generic_archiver.py index 729d6ef..bf423e0 100644 --- a/src/auto_archiver/archivers/generic_archiver/generic_archiver.py +++ b/src/auto_archiver/archivers/generic_archiver/generic_archiver.py @@ -1,27 +1,3 @@ -""" -This is the generic archiver used by auto-archiver, which uses `yt-dlp` under the hood. - -This module is responsible for downloading and processing media content from platforms -supported by `yt-dlp`, such as YouTube, Facebook, and others. It provides functionality -for retrieving videos, subtitles, comments, and other metadata, and it integrates with -the broader archiving framework. - -### Features -- Supports downloading videos and playlists. -- Retrieves metadata like titles, descriptions, upload dates, and durations. -- Downloads subtitles and comments when enabled. -- Configurable options for handling live streams, proxies, and more. - -### Dropins -- For websites supported by `yt-dlp` that also contain posts in addition to videos - (e.g. Facebook, Twitter, Bluesky), dropins can be created to extract post data and create - metadata objects. Some dropins are included in this generic_archiver by default, but -custom dropins can be created to handle additional websites and passed to the archiver -via the command line using the `--dropins` option (TODO!). - -""" - - import datetime, os, yt_dlp, pysubs2 import importlib from typing import Type