external/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-13 02:14:20 +01:00
Code Issues Projects Releases Packages Wiki Activity

[pornhub] Add support for more paged video sources

Browse source
This commit is contained in:
Sergey M․ 2019-06-22 08:37:07 +07:00
parent 1f7a563ab0
commit 9634de178d
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 62 additions and 44 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/extractors.py
View file

@ -892,8 +892,9 @@
from .pornhd import PornHdIE from .pornhd import PornHdIE
from .pornhub import ( from .pornhub import (
PornHubIE, PornHubIE,
PornHubPlaylistIE, PornHubUserIE,
PornHubUserVideosIE, PornHubPagedVideoListIE,
PornHubUserVideosUploadIE,
) )
from .pornotube import PornotubeIE from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE from .pornovoisines import PornoVoisinesIE

101
youtube_dl/extractor/pornhub.py
View file

@ -372,23 +372,8 @@ def _real_extract(self, url):
entries, playlist_id, title, playlist.get('description')) entries, playlist_id, title, playlist.get('description'))
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.pornhub.com/playlist/4667351',
'info_dict': {
'id': '4667351',
'title': 'Nataly Hot',
},
'playlist_mincount': 2,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'only_matching': True,
}]
class PornHubUserIE(PornHubPlaylistBaseIE): class PornHubUserIE(PornHubPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))' _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph', 'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118, 'playlist_mincount': 118,
@ -400,23 +385,20 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
'playlist_mincount': 118, 'playlist_mincount': 118,
}, { }, {
'url': 'https://www.pornhub.com/users/russianveet69', 'url': 'https://www.pornhub.com/users/russianveet69',
'playlist_mincount': 0, 'only_matching': True,
}, { }, {
'url': 'https://www.pornhub.com/channels/povd', 'url': 'https://www.pornhub.com/channels/povd',
'playlist_mincount': 0, 'only_matching': True,
}, {
'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
'only_matching': True,
}] }]
@classmethod
def suitable(cls, url):
return (False
if PornHubPagedVideosIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
else super(PornHubUserIE, cls).suitable(url))
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('id') user_id = mobj.group('id')
return self.url_result( return self.url_result(
'%s/videos' % mobj.group('url'), ie=PornHubPagedVideosIE.ie_key(), '%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
video_id=user_id) video_id=user_id)
@ -424,7 +406,7 @@ 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')
user_id = mobj.group('id') item_id = mobj.group('id')
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))
@ -435,7 +417,7 @@ def _real_extract(self, url):
for page_num in (page, ) if page is not None else itertools.count(1): for page_num in (page, ) if page is not None else itertools.count(1):
try: try:
webpage = self._download_webpage( webpage = self._download_webpage(
page_url, user_id, 'Downloading page %d' % page_num, page_url, item_id, 'Downloading page %d' % page_num,
query={'page': page_num}) query={'page': page_num})
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
@ -448,18 +430,11 @@ def _real_extract(self, url):
if not self._has_more(webpage): if not self._has_more(webpage):
break break
return self.playlist_result(orderedSet(entries), user_id) return self.playlist_result(orderedSet(entries), item_id)
class PornHubPagedVideosIE(PornHubPagedPlaylistBaseIE): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
https?://
(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/
(?:
(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos|
video/search
)
'''
_TESTS = [{ _TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph/videos', 'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True, 'only_matching': True,
@ -469,20 +444,20 @@ class PornHubPagedVideosIE(PornHubPagedPlaylistBaseIE):
}, { }, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos', 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
'info_dict': { 'info_dict': {
'id': 'jenny-blighe', 'id': 'pornstar/jenny-blighe/videos',
}, },
'playlist_mincount': 149, 'playlist_mincount': 149,
}, { }, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3', 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
'info_dict': { 'info_dict': {
'id': 'jenny-blighe', 'id': 'pornstar/jenny-blighe/videos',
}, },
'playlist_mincount': 40, 'playlist_mincount': 40,
}, { }, {
# default sorting as Top Rated Videos # default sorting as Top Rated Videos
'url': 'https://www.pornhub.com/channels/povd/videos', 'url': 'https://www.pornhub.com/channels/povd/videos',
'info_dict': { 'info_dict': {
'id': 'povd', 'id': 'channels/povd/videos',
}, },
'playlist_mincount': 293, 'playlist_mincount': 293,
}, { }, {
@ -522,13 +497,55 @@ class PornHubPagedVideosIE(PornHubPagedPlaylistBaseIE):
}, { }, {
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly', 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video/search?search=123',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/categories/teen',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/categories/teen?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/hd',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/hd?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/described-video',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/described-video?page=2',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/playlist/44121572',
'info_dict': {
'id': 'playlist/44121572',
},
'playlist_mincount': 132,
}, {
'url': 'https://www.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'only_matching': True,
}] }]
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
return (False return (False
if PornHubUserVideosUploadIE.suitable(url) if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
else super(PornHubPagedVideosIE, cls).suitable(url)) else super(PornHubPagedVideoListIE, cls).suitable(url))
def _make_page_url(self, url): def _make_page_url(self, url):
return url return url