artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-04-28 11:36:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

** Added contentLocation and poi fields to info.json of tiktok videos which have the field defined.

Browse Source
This commit is contained in:
makingglitches 2025-05-01 15:11:43 -04:00
parent b77e5a553a
commit 0bf675ee55
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
yt_dlp/extractor/tiktok.py
View File

@ -232,6 +232,15 @@ class TikTokBaseIE(InfoExtractor):
self.report_warning(f'{message}. {self._login_hint()}') self.report_warning(f'{message}. {self._login_hint()}')
return video_data, status return video_data, status
# this is the area the main video info is being extracted from
# in the present case data from TikTok is being extracted from
# a series of "script" tags with types application/json
# locationCreated is the tag being looked for to retrieve
# location tag from and is housed under
# __UNIVERSAL_DATA_FOR_REHYDRATION__
# again.
# tags includedin the finished video_data such as "author" seem to be
# included in this section.
if universal_data := self._get_universal_data(webpage, video_id): if universal_data := self._get_universal_data(webpage, video_id):
self.write_debug('Found universal data for rehydration') self.write_debug('Found universal data for rehydration')
status = traverse_obj(universal_data, ('webapp.video-detail', 'statusCode', {int})) or 0 status = traverse_obj(universal_data, ('webapp.video-detail', 'statusCode', {int})) or 0
@ -580,11 +589,16 @@ class TikTokBaseIE(InfoExtractor):
'uploader_id': (('authorId', 'uid', 'id'), {str_or_none}), 'uploader_id': (('authorId', 'uid', 'id'), {str_or_none}),
}), get_all=False) }), get_all=False)
streetAddress = traverse_obj(aweme_detail,('contentLocation','address'))
pointOfInterest = traverse_obj(aweme_detail,('poi'))
return { return {
'id': video_id, 'id': video_id,
'formats': None if extract_flat else self._extract_web_formats(aweme_detail), 'formats': None if extract_flat else self._extract_web_formats(aweme_detail),
'subtitles': None if extract_flat else self.extract_subtitles(aweme_detail, video_id, None), 'subtitles': None if extract_flat else self.extract_subtitles(aweme_detail, video_id, None),
'http_headers': {'Referer': webpage_url}, 'http_headers': {'Referer': webpage_url},
'contentLocation':streetAddress,
'pointOfInterest':pointOfInterest,
**author_info, **author_info,
'channel_url': format_field(author_info, 'channel_id', self._UPLOADER_URL_FORMAT, default=None), 'channel_url': format_field(author_info, 'channel_id', self._UPLOADER_URL_FORMAT, default=None),
'uploader_url': format_field( 'uploader_url': format_field(