Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-09 22:27:45 +08:00
Code Issues Releases Wiki Activity

Update pornhub.py

Browse Source 
Issue with title not being populated when download a playlist, so added title extraction for user playlists in PornHubPagedPlaylistBaseIE class.
This commit is contained in:
projx 2019-09-02 23:09:14 +01:00 committed by GitHub
parent bff90fc518
commit 8d6c3a0f15
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 19 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/pornhub.py
View File

@ -403,11 +403,17 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
host = mobj.group('host') host = mobj.group('host')
item_id = mobj.group('id') item_id = mobj.group('id')
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
playlist_id = mobj.group('id')
title = ""
page = int_or_none(self._search_regex( page = int_or_none(self._search_regex(
r'\bpage=(\d+)', url, 'page', default=None)) r'\bpage=(\d+)', url, 'page', default=None))
@ -423,14 +429,25 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break break
raise raise
page_entries = self._extract_entries(webpage, host) page_entries = self._extract_entries(webpage, host)
if title == "":
playlist = self._parse_json(
self._search_regex(
r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
'playlist', default='{}'),
playlist_id, fatal=False)
title = playlist.get('title') or self._search_regex(
r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
if not page_entries: if not page_entries:
break break
entries.extend(page_entries) entries.extend(page_entries)
if not self._has_more(webpage): if not self._has_more(webpage):
break break
return self.playlist_result(orderedSet(entries), item_id) return self.playlist_result(orderedSet(entries), item_id, title)
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):