etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[pornhub:uservideos] Add support for multipage videos (Closes #9006)

Browse source
This commit is contained in:
Sergey M․ 2016-03-28 00:50:46 +06:00
parent 3a23bae9cc
commit 3454139576
1 changed files with 22 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/pornhub.py
View file

@ -1,10 +1,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import itertools
import os import os
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_HTTPError,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus, compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
@ -189,16 +191,31 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
class PornHubUserVideosIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos' _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
_TESTS = [{ _TESTS = [{
'url': 'http://www.pornhub.com/users/rushandlia/videos', 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': { 'info_dict': {
'id': 'rushandlia', 'id': 'zoe_ph',
}, },
'playlist_mincount': 13, 'playlist_mincount': 171,
}, {
'url': 'http://www.pornhub.com/users/rushandlia/videos',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
user_id = self._match_id(url) user_id = self._match_id(url)
webpage = self._download_webpage(url, user_id) entries = []
for page_num in itertools.count(1):
try:
webpage = self._download_webpage(
url, user_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
page_entries = self._extract_entries(webpage)
if not page_entries:
break
entries.extend(page_entries)
return self.playlist_result(self._extract_entries(webpage), user_id) return self.playlist_result(entries, user_id)