mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-10 00:58:17 +02:00
[extractor/generic] Improve support for pornhub embeds (closes #11100)
This commit is contained in:
parent
e28ed498e6
commit
b52c9ef165
@ -1983,11 +1983,6 @@ def _playlist_from_matches(matches, getter=None, ie=None):
|
|||||||
if sportbox_urls:
|
if sportbox_urls:
|
||||||
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
|
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
|
||||||
|
|
||||||
# Look for embedded PornHub player
|
|
||||||
pornhub_url = PornHubIE._extract_url(webpage)
|
|
||||||
if pornhub_url:
|
|
||||||
return self.url_result(pornhub_url, 'PornHub')
|
|
||||||
|
|
||||||
# Look for embedded XHamster player
|
# Look for embedded XHamster player
|
||||||
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
|
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
|
||||||
if xhamster_urls:
|
if xhamster_urls:
|
||||||
@ -1998,6 +1993,11 @@ def _playlist_from_matches(matches, getter=None, ie=None):
|
|||||||
if tnaflix_urls:
|
if tnaflix_urls:
|
||||||
return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
|
return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
|
||||||
|
|
||||||
|
# Look for embedded PornHub player
|
||||||
|
pornhub_urls = PornHubIE._extract_urls(webpage)
|
||||||
|
if pornhub_urls:
|
||||||
|
return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
|
||||||
|
|
||||||
# Look for embedded DrTuber player
|
# Look for embedded DrTuber player
|
||||||
drtuber_urls = DrTuberIE._extract_urls(webpage)
|
drtuber_urls = DrTuberIE._extract_urls(webpage)
|
||||||
if drtuber_urls:
|
if drtuber_urls:
|
||||||
|
@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
|
|||||||
(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
|
(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
|
||||||
(?:www\.)?thumbzilla\.com/video/
|
(?:www\.)?thumbzilla\.com/video/
|
||||||
)
|
)
|
||||||
(?P<id>[0-9a-z]+)
|
(?P<id>[\da-z]+)
|
||||||
'''
|
'''
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
|
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
|
||||||
@ -96,12 +96,11 @@ class PornHubIE(InfoExtractor):
|
|||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
@classmethod
|
@staticmethod
|
||||||
def _extract_url(cls, webpage):
|
def _extract_urls(webpage):
|
||||||
mobj = re.search(
|
return re.findall(
|
||||||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
|
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
|
||||||
if mobj:
|
webpage)
|
||||||
return mobj.group('url')
|
|
||||||
|
|
||||||
def _extract_count(self, pattern, webpage, name):
|
def _extract_count(self, pattern, webpage, name):
|
||||||
return str_to_int(self._search_regex(
|
return str_to_int(self._search_regex(
|
||||||
|
Loading…
Reference in New Issue
Block a user