mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-10 00:58:17 +02:00
[pornhub:playlistbase] Skip videos from drop-down menu for all playlists (closes #12819, closes #13902)
This commit is contained in:
parent
b3c6515365
commit
475bcb225f
@ -227,20 +227,6 @@ def parse_js_value(inp):
|
|||||||
|
|
||||||
class PornHubPlaylistBaseIE(InfoExtractor):
|
class PornHubPlaylistBaseIE(InfoExtractor):
|
||||||
def _extract_entries(self, webpage):
|
def _extract_entries(self, webpage):
|
||||||
return [
|
|
||||||
self.url_result(
|
|
||||||
'http://www.pornhub.com/%s' % video_url,
|
|
||||||
PornHubIE.ie_key(), video_title=title)
|
|
||||||
for video_url, title in orderedSet(re.findall(
|
|
||||||
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
|
|
||||||
webpage))
|
|
||||||
]
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
playlist_id = self._match_id(url)
|
|
||||||
|
|
||||||
webpage = self._download_webpage(url, playlist_id)
|
|
||||||
|
|
||||||
# Only process container div with main playlist content skipping
|
# Only process container div with main playlist content skipping
|
||||||
# drop-down menu that uses similar pattern for videos (see
|
# drop-down menu that uses similar pattern for videos (see
|
||||||
# https://github.com/rg3/youtube-dl/issues/11594).
|
# https://github.com/rg3/youtube-dl/issues/11594).
|
||||||
@ -248,7 +234,21 @@ def _real_extract(self, url):
|
|||||||
r'(?s)(<div[^>]+class=["\']container.+)', webpage,
|
r'(?s)(<div[^>]+class=["\']container.+)', webpage,
|
||||||
'container', default=webpage)
|
'container', default=webpage)
|
||||||
|
|
||||||
entries = self._extract_entries(container)
|
return [
|
||||||
|
self.url_result(
|
||||||
|
'http://www.pornhub.com/%s' % video_url,
|
||||||
|
PornHubIE.ie_key(), video_title=title)
|
||||||
|
for video_url, title in orderedSet(re.findall(
|
||||||
|
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
|
||||||
|
container))
|
||||||
|
]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
playlist_id = self._match_id(url)
|
||||||
|
|
||||||
|
webpage = self._download_webpage(url, playlist_id)
|
||||||
|
|
||||||
|
entries = self._extract_entries(webpage)
|
||||||
|
|
||||||
playlist = self._parse_json(
|
playlist = self._parse_json(
|
||||||
self._search_regex(
|
self._search_regex(
|
||||||
|
Loading…
Reference in New Issue
Block a user