mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-12-25 02:07:44 +00:00
[pornhub] Implement lazy playlist extraction
This commit is contained in:
parent
2adc0c51cd
commit
89c5a7d5aa
1 changed files with 11 additions and 10 deletions
|
@ -547,13 +547,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
|
|||
<button[^>]+\bid=["\']moreDataBtn
|
||||
''', webpage) is not None
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
item_id = mobj.group('id')
|
||||
|
||||
self._login(host)
|
||||
|
||||
def _entries(self, url, host, item_id):
|
||||
page = self._extract_page(url)
|
||||
|
||||
VIDEOS = '/videos'
|
||||
|
@ -566,7 +560,6 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
|
|||
def is_404(e):
|
||||
return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
|
||||
|
||||
entries = []
|
||||
base_url = url
|
||||
has_page = page is not None
|
||||
first_page = page if has_page else 1
|
||||
|
@ -590,11 +583,19 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
|
|||
page_entries = self._extract_entries(webpage, host)
|
||||
if not page_entries:
|
||||
break
|
||||
entries.extend(page_entries)
|
||||
for e in page_entries:
|
||||
yield e
|
||||
if not self._has_more(webpage):
|
||||
break
|
||||
|
||||
return self.playlist_result(orderedSet(entries), item_id)
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
item_id = mobj.group('id')
|
||||
|
||||
self._login(host)
|
||||
|
||||
return self.playlist_result(self._entries(url, host, item_id), item_id)
|
||||
|
||||
|
||||
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
|
||||
|
|
Loading…
Reference in a new issue