Compare commits

..

2 Commits

Author SHA1 Message Date
Simon Sawicki
cc8d844152
[ie/xhamster:user] Support creator urls (#8232)
Authored by: Grub4K
2023-10-03 11:33:40 +02:00
coletdjnz
eb5bdbfa70
[ie/youtube] Raise a warning for Incomplete Data instead of an error (#8238)
Closes https://github.com/yt-dlp/yt-dlp/issues/8206

Adds `raise_incomplete_data` extractor arg to revert this behaviour and raise an error.

Authored by: coletdjnz
Co-authored-by: Simon Sawicki <contact@grub4k.xyz>
2023-10-03 06:42:30 +00:00
3 changed files with 32 additions and 12 deletions

View File

@ -1809,6 +1809,7 @@ The following extractors use this feature:
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
* `innertube_key`: Innertube API key to use for all API requests
* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
#### youtubetab (YouTube playlists, channels, feeds, etc.)
* `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details)

View File

@ -407,7 +407,7 @@ class XHamsterEmbedIE(InfoExtractor):
class XHamsterUserIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
_VALID_URL = rf'https?://(?:[^/?#]+\.)?{XHamsterIE._DOMAINS}/(?:(?P<user>users)|creators)/(?P<id>[^/?#&]+)'
_TESTS = [{
# Paginated user profile
'url': 'https://xhamster.com/users/netvideogirls/videos',
@ -422,6 +422,12 @@ class XHamsterUserIE(InfoExtractor):
'id': 'firatkaan',
},
'playlist_mincount': 1,
}, {
'url': 'https://xhamster.com/creators/squirt-orgasm-69',
'info_dict': {
'id': 'squirt-orgasm-69',
},
'playlist_mincount': 150,
}, {
'url': 'https://xhday.com/users/mobhunter',
'only_matching': True,
@ -430,8 +436,9 @@ class XHamsterUserIE(InfoExtractor):
'only_matching': True,
}]
def _entries(self, user_id):
next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
def _entries(self, user_id, is_user):
prefix, suffix = ('users', 'videos') if is_user else ('creators', 'exclusive')
next_page_url = f'https://xhamster.com/{prefix}/{user_id}/{suffix}/1'
for pagenum in itertools.count(1):
page = self._download_webpage(
next_page_url, user_id, 'Downloading page %s' % pagenum)
@ -454,5 +461,5 @@ class XHamsterUserIE(InfoExtractor):
break
def _real_extract(self, url):
user_id = self._match_id(url)
return self.playlist_result(self._entries(user_id), user_id)
user, user_id = self._match_valid_url(url).group('user', 'id')
return self.playlist_result(self._entries(user_id, bool(user)), user_id)

View File

@ -941,7 +941,13 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
default_client='web'):
for retry in self.RetryManager():
raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE))
# Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal.
icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete))
icd_rm = next(icd_retries)
main_retries = iter(self.RetryManager())
main_rm = next(main_retries)
for _ in range(main_rm.retries + icd_rm.retries + 1):
try:
response = self._call_api(
ep=ep, fatal=True, headers=headers,
@ -953,7 +959,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
if not isinstance(e.cause, network_exceptions):
return self._error_or_warning(e, fatal=fatal)
elif not isinstance(e.cause, HTTPError):
retry.error = e
main_rm.error = e
next(main_retries)
continue
first_bytes = e.cause.response.read(512)
@ -965,27 +972,32 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
if yt_error:
self._report_alerts([('ERROR', yt_error)], fatal=False)
# Downloading page may result in intermittent 5xx HTTP error
# Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
# Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
# We also want to catch all other network exceptions since errors in later pages can be troublesome
# See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
if e.cause.status not in (403, 429):
retry.error = e
main_rm.error = e
next(main_retries)
continue
return self._error_or_warning(e, fatal=fatal)
try:
self._extract_and_report_alerts(response, only_once=True)
except ExtractorError as e:
# YouTube servers may return errors we want to retry on in a 200 OK response
# YouTube's servers may return errors we want to retry on in a 200 OK response
# See: https://github.com/yt-dlp/yt-dlp/issues/839
if 'unknown error' in e.msg.lower():
retry.error = e
main_rm.error = e
next(main_retries)
continue
return self._error_or_warning(e, fatal=fatal)
# Youtube sometimes sends incomplete data
# See: https://github.com/ytdl-org/youtube-dl/issues/28194
if not traverse_obj(response, *variadic(check_get_keys)):
retry.error = ExtractorError('Incomplete data received', expected=True)
icd_rm.error = ExtractorError('Incomplete data received', expected=True)
should_retry = next(icd_retries, None)
if not should_retry:
return None
continue
return response