github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[youtube] Fall back to embed webpage when content is blocked on main (Fixes #4717)

Browse source
This commit is contained in:
Philipp Hagemeister 2015-01-30 04:43:50 +01:00
parent e2a08185c6
commit 6449cd807e
1 changed files with 15 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/youtube.py
View file

@ -28,6 +28,7 @@
get_element_by_attribute, get_element_by_attribute,
get_element_by_id, get_element_by_id,
int_or_none, int_or_none,
js_to_json,
OnDemandPagedList, OnDemandPagedList,
orderedSet, orderedSet,
unescapeHTML, unescapeHTML,
@ -809,6 +810,7 @@ def _real_extract(self, url):
player_url = None player_url = None
# Get video info # Get video info
embed_webpage = None
if re.search(r'player-age-gate-content">', video_webpage) is not None: if re.search(r'player-age-gate-content">', video_webpage) is not None:
age_gate = True age_gate = True
# We simulate the access to the video from www.youtube.com/v/{video_id} # We simulate the access to the video from www.youtube.com/v/{video_id}
@ -1016,10 +1018,21 @@ def _map_to_format_list(urlmap):
url += '&signature=' + url_data['sig'][0] url += '&signature=' + url_data['sig'][0]
elif 's' in url_data: elif 's' in url_data:
encrypted_sig = url_data['s'][0] encrypted_sig = url_data['s'][0]
ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
jsplayer_url_json = self._search_regex( jsplayer_url_json = self._search_regex(
r'"assets":.+?"js":\s*("[^"]+")', ASSETS_RE,
embed_webpage if age_gate else video_webpage, 'JS player URL') embed_webpage if age_gate else video_webpage,
'JS player URL (1)', default=None)
if not jsplayer_url_json and not age_gate:
# We need the embed website after all
if embed_webpage is None:
embed_url = proto + '://www.youtube.com/embed/%s' % video_id
embed_webpage = self._download_webpage(
embed_url, video_id, 'Downloading embed webpage')
jsplayer_url_json = self._search_regex(
ASSETS_RE, embed_webpage, 'JS player URL')
player_url = json.loads(jsplayer_url_json) player_url = json.loads(jsplayer_url_json)
if player_url is None: if player_url is None:
player_url_json = self._search_regex( player_url_json = self._search_regex(