bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-13 05:38:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Further tweaks based on __manifest__.py files

Browse Source 
Loading configs now works
This commit is contained in:
Patrick Robertson
2025-01-22 13:11:43 +01:00
parent 7b3a1468cd
commit 54995ad6ab
7 changed files with 214 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/auto_archiver/modules/generic_extractor/__manifest__.py
View File

@@ -30,7 +30,7 @@ the broader archiving framework.
custom dropins can be created to handle additional websites and passed to the archiver
via the command line using the `--dropins` option (TODO!).
""",
'config': {
'configs': {
"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"},
@@ -40,7 +40,7 @@ via the command line using the `--dropins` option (TODO!).
"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"},
"cookies_from_browser": {"default": None, 'type': 'str', "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"},
}
}

2
src/auto_archiver/modules/twitter_api_archiver/__manifest__.py
View File

@@ -13,7 +13,7 @@
},
"configs": {
"bearer_token": {"default": None, "help": "[deprecated: see bearer_tokens] twitter API bearer_token which is enough for archiving, if not provided you will need consumer_key, consumer_secret, access_token, access_secret"},
"bearer_tokens": {"default": [], "help": " a list of twitter API bearer_token which is enough for archiving, if not provided you will need consumer_key, consumer_secret, access_token, access_secret, if provided you can still add those for better rate limits. CSV of bearer tokens if provided via the command line", "cli_set": lambda cli_val, cur_val: list(set(cli_val.split(",")))},
"bearer_tokens": {"default": [], "help": " a list of twitter API bearer_token which is enough for archiving, if not provided you will need consumer_key, consumer_secret, access_token, access_secret, if provided you can still add those for better rate limits. CSV of bearer tokens if provided via the command line"},
"consumer_key": {"default": None, "help": "twitter API consumer_key"},
"consumer_secret": {"default": None, "help": "twitter API consumer_secret"},
"access_token": {"default": None, "help": "twitter API access_token"},