MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-27 05:35:52 +01:00
Code Issues Projects Releases Wiki Activity

[youtube] fix annotations extraction(closes #22045)

Browse Source
This commit is contained in:
Remita Amine 2019-08-09 08:16:53 +01:00
parent b3d39be239
commit 64b6a4e91e
1 changed files with 15 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
youtube_dl/extractor/youtube.py
View File

@ -1595,17 +1595,6 @@ def extract_id(cls, url):
video_id = mobj.group(2) video_id = mobj.group(2)
return video_id return video_id
def _extract_annotations(self, video_id):
return self._download_webpage(
'https://www.youtube.com/annotations_invideo', video_id,
note='Downloading annotations',
errnote='Unable to download video annotations', fatal=False,
query={
'features': 1,
'legacy': 1,
'video_id': video_id,
})
@staticmethod @staticmethod
def _extract_chapters(description, duration): def _extract_chapters(description, duration):
if not description: if not description:
@ -2277,7 +2266,21 @@ def _extract_count(count_name):
# annotations # annotations
video_annotations = None video_annotations = None
if self._downloader.params.get('writeannotations', False): if self._downloader.params.get('writeannotations', False):
video_annotations = self._extract_annotations(video_id) xsrf_token = self._search_regex(
r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
invideo_url = try_get(
player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
if xsrf_token and invideo_url:
xsrf_field_name = self._search_regex(
r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
video_webpage, 'xsrf field name',
group='xsrf_field_name', default='session_token')
video_annotations = self._download_webpage(
self._proto_relative_url(invideo_url),
video_id, note='Downloading annotations',
errnote='Unable to download video annotations', fatal=False,
data=urlencode_postdata({xsrf_field_name: xsrf_token}))
chapters = self._extract_chapters(description_original, video_duration) chapters = self._extract_chapters(description_original, video_duration)