fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[youtube] Make `ytcfg.set` config extraction non-fatal 

If the markup of the page changes in the future, it might be possible that _FEED_DATA still works, but the other regex does not. SInce it is not necessary for the first page of videos, we make sure the program doesn't exit before extracting them.

TL;DR: Extract the first video page even if there are problems
This commit is contained in:
xarantolus 2020-08-24 14:29:16 +02:00
parent 299056ad52
commit 1f93faf60b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
youtube_dl/extractor/youtube.py
View File

@ -3354,7 +3354,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
def _entries(self, page): def _entries(self, page):
info = [] info = []
yt_conf = self._parse_json(self._search_regex(self._YTCFG_DATA, page, 'ytcfg.set'), None) yt_conf = self._parse_json(self._search_regex(self._YTCFG_DATA, page, 'ytcfg.set', default="null"), None, fatal=False)
search_response = self._parse_json(self._search_regex(self._FEED_DATA, page, 'ytInitialData'), None) search_response = self._parse_json(self._search_regex(self._FEED_DATA, page, 'ytInitialData'), None)
@ -3385,7 +3385,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
for video in new_info: for video in new_info:
yield self.url_result(try_get(video, lambda x: x['videoId']), YoutubeIE.ie_key(), video_title=try_get(video, lambda x: x['title']['runs'][0]['text'])) yield self.url_result(try_get(video, lambda x: x['videoId']), YoutubeIE.ie_key(), video_title=try_get(video, lambda x: x['title']['runs'][0]['text']))
if not continuation: if not continuation or not yt_conf:
break break
search_response = self._download_json( search_response = self._download_json(