nhyatt/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-04-05 06:30:17 -05:00
Code Issues Projects Releases Wiki Activity

[ie/youtube] Retry on more critical requests (#12339)

Browse Source 
Authored by: coletdjnz
This commit is contained in:
coletdjnz 2025-02-19 13:39:51 +13:00 committed by GitHub
parent 5c4c2ddfaa
commit d48e612609
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 21 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
yt_dlp/extractor/youtube.py
View File

@ -857,6 +857,18 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
} }
return filter_dict(headers) return filter_dict(headers)
def _download_webpage_with_retries(self, *args, retry_fatal=False, retry_on_status=None, **kwargs):
for retry in self.RetryManager(fatal=retry_fatal):
try:
return self._download_webpage(*args, **kwargs)
except ExtractorError as e:
if isinstance(e.cause, network_exceptions):
if not isinstance(e.cause, HTTPError) or e.cause.status not in (retry_on_status or (403, 429)):
retry.error = e
continue
self._error_or_warning(e, fatal=retry_fatal)
break
def _download_ytcfg(self, client, video_id): def _download_ytcfg(self, client, video_id):
url = { url = {
'web': 'https://www.youtube.com', 'web': 'https://www.youtube.com',
@ -866,8 +878,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
}.get(client) }.get(client)
if not url: if not url:
return {} return {}
webpage = self._download_webpage( webpage = self._download_webpage_with_retries(
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config', url, video_id, note=f'Downloading {client.replace("_", " ").strip()} client config',
headers=traverse_obj(self._get_default_ytcfg(client), { headers=traverse_obj(self._get_default_ytcfg(client), {
'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}), 'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}),
})) }))
@ -3143,12 +3155,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return urljoin('https://www.youtube.com', player_url) return urljoin('https://www.youtube.com', player_url)
def _download_player_url(self, video_id, fatal=False): def _download_player_url(self, video_id, fatal=False):
res = self._download_webpage( iframe_webpage = self._download_webpage_with_retries(
'https://www.youtube.com/iframe_api', 'https://www.youtube.com/iframe_api',
note='Downloading iframe API JS', video_id=video_id, fatal=fatal) note='Downloading iframe API JS',
if res: video_id=video_id, retry_fatal=fatal)
if iframe_webpage:
player_version = self._search_regex( player_version = self._search_regex(
r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal) r'player\\?/([0-9a-fA-F]{8})\\?/', iframe_webpage, 'player version', fatal=fatal)
if player_version: if player_version:
return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js' return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
@ -4561,8 +4575,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
pp = self._configuration_arg('player_params', [None], casesense=True)[0] pp = self._configuration_arg('player_params', [None], casesense=True)[0]
if pp: if pp:
query['pp'] = pp query['pp'] = pp
webpage = self._download_webpage( webpage = self._download_webpage_with_retries(webpage_url, video_id, query=query)
webpage_url, video_id, fatal=False, query=query)
master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg() master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()