bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-12 13:18:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Get parsing of manifest and combining with config file working

Browse Source
This commit is contained in:
Patrick Robertson
2025-01-21 20:03:10 +01:00
parent 241b35002c
commit 4830f99300
4 changed files with 121 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/auto_archiver/modules/generic_extractor/__manifest__.py
View File

@@ -29,5 +29,18 @@ the broader archiving framework.
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!).
"""
""",
'config': {
"facebook_cookie": {"default": None, "help": "optional facebook cookie to have more access to content, from browser, looks like 'cookie: datr= xxxx'"},
"subtitles": {"default": True, "help": "download subtitles if available"},
"comments": {"default": False, "help": "download all comments if available, may lead to large metadata"},
"livestreams": {"default": False, "help": "if set, will download live streams, otherwise will skip them; see --max-filesize for more control"},
"live_from_start": {"default": False, "help": "if set, will download live streams from their earliest available moment, otherwise starts now."},
"proxy": {"default": "", "help": "http/socks (https seems to not work atm) proxy to use for the webdriver, eg https://proxy-user:password@proxy-ip:port"},
"end_means_success": {"default": True, "help": "if True, any archived content will mean a 'success', if False this archiver will not return a 'success' stage; this is useful for cases when the yt-dlp will archive a video but ignore other types of content like images or text only pages that the subsequent archivers can retrieve."},
'allow_playlist': {"default": False, "help": "If True will also download playlists, set to False if the expectation is to download a single video."},
"max_downloads": {"default": "inf", "help": "Use to limit the number of videos to download when a channel or long page is being extracted. 'inf' means no limit."},
"cookies_from_browser": {"default": None, "help": "optional browser for ytdl to extract cookies from, can be one of: brave, chrome, chromium, edge, firefox, opera, safari, vivaldi, whale"},
"cookie_file": {"default": None, "help": "optional cookie file to use for Youtube, see instructions here on how to export from your browser: https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp"},
}
}