8 from .common
import InfoExtractor
9 from .openload
import PhantomJSwrapper
10 from ..compat
import compat_HTTPError
, compat_str
29 class PornHubBaseIE(InfoExtractor
):
30 _NETRC_MACHINE
= 'pornhub'
31 _PORNHUB_HOST_RE
= r
'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd\.onion)'
33 def _download_webpage_handle(self
, *args
, **kwargs
):
34 def dl(*args
, **kwargs
):
35 return super(PornHubBaseIE
, self
)._download
_webpage
_handle
(*args
, **kwargs
)
37 ret
= dl(*args
, **kwargs
)
44 if any(re
.search(p
, webpage
) for p
in (
45 r
'<body\b[^>]+\bonload=["\']go\
(\
)',
46 r'document\
.cookie\s
*=\s
*["\']RNKEY=',
47 r'document\.location\.reload\(true\)')):
48 url_or_request = args[0]
49 url = (url_or_request.get_full_url()
50 if isinstance(url_or_request, urllib.request.Request)
52 phantom = PhantomJSwrapper(self, required_version='2.0')
53 phantom.get(url, html=webpage)
54 webpage, urlh = dl(*args, **kwargs)
58 def _real_initialize(self):
59 self._logged_in = False
61 def _login(self, host):
65 site = host.split('.')[0]
67 # Both sites pornhub and pornhubpremium have separate accounts
68 # so there should be an option to provide credentials for both.
69 # At the same time some videos are available under the same video id
70 # on both sites so that we have to identify them as the same video.
71 # For that purpose we have to keep both in the same extractor
72 # but under different netrc machines.
73 username, password = self._get_login_info(netrc_machine=site)
77 login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
78 login_page = self._download_webpage(
79 login_url, None, 'Downloading %s login page' % site)
81 def is_logged(webpage):
82 return any(re.search(p, webpage) for p in (
83 r'class=["\']signOut
',
84 r'>Sign\s
+[Oo
]ut\s
*<'))
86 if is_logged(login_page):
87 self._logged_in = True
90 login_form = self._hidden_inputs(login_page)
97 response = self._download_json(
98 'https
://www
.%s/front
/authenticate
' % host, None,
99 'Logging
in to
%s' % site,
100 data=urlencode_postdata(login_form),
102 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
; charset
=UTF
-8',
103 'Referer
': login_url,
104 'X
-Requested
-With
': 'XMLHttpRequest
',
107 if response.get('success
') == '1':
108 self._logged_in = True
111 message = response.get('message
')
112 if message is not None:
113 raise ExtractorError(
114 'Unable to login
: %s' % message, expected=True)
116 raise ExtractorError('Unable to log
in')
119 class PornHubIE(PornHubBaseIE):
120 IE_DESC = 'PornHub
and Thumbzilla
'
121 _VALID_URL = r'''(?x)
126 /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
127 (?:www\.)?thumbzilla\.com/video/
130 ''' % PornHubBaseIE._PORNHUB_HOST_RE
132 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=648719015',
133 'md5
': 'a6391306d050e4547f62b3f485dd9ba9
',
137 'title
': 'Seductive Indian beauty strips down
and fingers her pink pussy
',
139 'upload_date
': '20130628',
140 'timestamp
': 1372447216,
144 'dislike_count
': int,
145 'comment_count
': int,
153 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=1331683002',
158 'upload_date
': '20150213',
159 'timestamp
': 1423804862,
163 'dislike_count
': int,
164 'comment_count
': int,
170 'skip_download
': True,
172 'skip
': 'Video has been flagged
for verification
in accordance
with our trust
and safety policy
',
175 'url
': 'https
://www
.pornhub
.com
/view_video
.php?viewkey
=ph5af5fef7c2aa7
',
177 'id': 'ph5af5fef7c2aa7
',
179 'title
': 'BFFS
- Cute Teen Girls Share Cock On the Floor
',
184 'dislike_count
': int,
185 'comment_count
': int,
196 'skip_download
': True,
198 'skip
': 'This video has been disabled
',
200 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph601dc30bae19a
',
202 'id': 'ph601dc30bae19a
',
203 'uploader
': 'Projekt Melody
',
204 'uploader_id
': 'projekt
-melody
',
205 'upload_date
': '20210205',
206 'title
': '"Welcome to My Pussy Mansion" - CB
Stream (02/03/21)',
207 'thumbnail
': r're
:https?
://.+',
210 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph557bbb6676d2d
',
211 'only_matching
': True,
213 # removed at the request of cam4.com
214 'url
': 'http
://fr
.pornhub
.com
/view_video
.php?viewkey
=ph55ca2f9760862
',
215 'only_matching
': True,
217 # removed at the request of the copyright owner
218 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=788152859',
219 'only_matching
': True,
221 # removed by uploader
222 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph572716d15a111
',
223 'only_matching
': True,
226 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph56fd731fce6b7
',
227 'only_matching
': True,
229 'url
': 'https
://www
.thumbzilla
.com
/video
/ph56c6114abd99a
/horny
-girlfriend
-sex
',
230 'only_matching
': True,
232 'url
': 'http
://www
.pornhub
.com
/video
/show?viewkey
=648719015',
233 'only_matching
': True,
235 'url
': 'https
://www
.pornhub
.net
/view_video
.php?viewkey
=203640933',
236 'only_matching
': True,
238 'url
': 'https
://www
.pornhub
.org
/view_video
.php?viewkey
=203640933',
239 'only_matching
': True,
241 'url
': 'https
://www
.pornhubpremium
.com
/view_video
.php?viewkey
=ph5e4acdae54a82
',
242 'only_matching
': True,
244 # Some videos are available with the same id on both premium
245 # and non-premium sites (e.g. this and the following test)
246 'url
': 'https
://www
.pornhub
.com
/view_video
.php?viewkey
=ph5f75b0f4b18e3
',
247 'only_matching
': True,
249 'url
': 'https
://www
.pornhubpremium
.com
/view_video
.php?viewkey
=ph5f75b0f4b18e3
',
250 'only_matching
': True,
253 'url
': 'https
://www
.pornhub
.com
/view_video
.php?viewkey
=ph5a9813bfa7156
',
254 'only_matching
': True,
256 'url
': 'http
://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd
.onion
/view_video
.php?viewkey
=ph5a9813bfa7156
',
257 'only_matching
': True,
261 def _extract_urls(webpage):
263 r'<iframe
[^
>]+?src
=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
266 def _extract_count(self, pattern, webpage, name):
267 return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
269 def _real_extract(self, url):
270 mobj = self._match_valid_url(url)
271 host = mobj.group('host') or 'pornhub.com'
272 video_id = mobj.group('id')
276 self._set_cookie(host, 'age_verified', '1')
278 def dl_webpage(platform):
279 self._set_cookie(host, 'platform', platform)
280 return self._download_webpage(
281 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
282 video_id, 'Downloading %s webpage' % platform)
284 webpage = dl_webpage('pc')
286 error_msg = self._html_search_regex(
287 (r'(?s)<div[^>]+class=(["\'])(?
:(?
!\
1).)*\b(?
:removed|userMessageSection
)\b(?
:(?
!\
1).)*\
1[^
>]*>(?P
<error
>.+?
)</div
>',
288 r'(?s
)<section
[^
>]+class=["\']noVideo["\'][^
>]*>(?P
<error
>.+?
)</section
>'),
289 webpage, 'error message
', default=None, group='error
')
291 error_msg = re.sub(r'\s
+', ' ', error_msg)
292 raise ExtractorError(
293 'PornHub said
: %s' % error_msg,
294 expected=True, video_id=video_id)
296 if any(re.search(p, webpage) for p in (
297 r'class=["\']geoBlocked["\']',
298 r'>\s
*This content
is unavailable
in your country
')):
299 self.raise_geo_restricted()
301 # video_title from flashvars contains whitespace instead of non-ASCII (see
302 # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
304 title = self._html_search_meta(
305 'twitter
:title
', webpage, default=None) or self._html_search_regex(
306 (r'(?s
)<h1
[^
>]+class=["\']title["\'][^
>]*>(?P
<title
>.+?
)</h1
>',
307 r'<div
[^
>]+data
-video
-title
=(["\'])(?P<title>(?:(?!\1).)+)\1',
308 r'shareTitle["\']\s
*[=:]\s
*(["\'])(?P<title>(?:(?!\1).)+)\1'),
309 webpage, 'title', group='title')
312 video_urls_set = set()
315 flashvars = self._parse_json(
317 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
320 subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
322 subtitles.setdefault('en', []).append({
326 thumbnail = flashvars.get('image_url')
327 duration = int_or_none(flashvars.get('video_duration'))
328 media_definitions = flashvars.get('mediaDefinitions')
329 if isinstance(media_definitions, list):
330 for definition in media_definitions:
331 if not isinstance(definition, dict):
333 video_url = definition.get('videoUrl')
334 if not video_url or not isinstance(video_url, compat_str):
336 if video_url in video_urls_set:
338 video_urls_set.add(video_url)
340 (video_url, int_or_none(definition.get('quality'))))
342 thumbnail, duration = [None] * 2
344 def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
345 assignments = self._search_regex(
346 pattern, webpage, 'encoded url', default=default)
350 assignments = assignments.split(';')
354 def parse_js_value(inp):
355 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
357 inps = inp.split('+')
358 return functools.reduce(
359 operator.concat, map(parse_js_value, inps))
363 return remove_quotes(inp)
365 for assn in assignments:
369 assn = re.sub(r'var\s+', '', assn)
370 vname, value = assn.split('=', 1)
371 js_vars[vname] = parse_js_value(value)
374 def add_video_url(video_url):
375 v_url = url_or_none(video_url)
378 if v_url in video_urls_set:
380 video_urls.append((v_url, None))
381 video_urls_set.add(v_url)
383 def parse_quality_items(quality_items):
384 q_items = self._parse_json(quality_items, video_id, fatal=False)
385 if not isinstance(q_items, list):
388 if isinstance(item, dict):
389 add_video_url(item.get('url'))
392 FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
393 js_vars = extract_js_vars(
394 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
397 for key, format_url in js_vars.items():
398 if key.startswith(FORMAT_PREFIXES[-1]):
399 parse_quality_items(format_url)
400 elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
401 add_video_url(format_url)
402 if not video_urls and re.search(
403 r'<[^>]+\bid=["\']lockedPlayer
', webpage):
404 raise ExtractorError(
405 'Video
%s is locked
' % video_id, expected=True)
408 js_vars = extract_js_vars(
409 dl_webpage('tv
'), r'(var
.+?mediastring
.+?
)</script
>')
410 add_video_url(js_vars['mediastring
'])
412 for mobj in re.finditer(
413 r'<a
[^
>]+\bclass
=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1',
415 video_url = mobj.group('url
')
416 if video_url not in video_urls_set:
417 video_urls.append((video_url, None))
418 video_urls_set.add(video_url)
423 def add_format(format_url, height=None):
424 ext = determine_ext(format_url)
426 formats.extend(self._extract_mpd_formats(
427 format_url, video_id, mpd_id='dash
', fatal=False))
430 formats.extend(self._extract_m3u8_formats(
431 format_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
432 m3u8_id='hls
', fatal=False))
435 height = int_or_none(self._search_regex(
436 r'(?P
<height
>\d
+)[pP
]?_\d
+[kK
]', format_url, 'height
',
440 'format_id
': format_field(height, None, '%dp
'),
444 for video_url, height in video_urls:
446 upload_date = self._search_regex(
447 r'/(\d{6}
/\d{2}
)/', video_url, 'upload data
', default=None)
449 upload_date = upload_date.replace('/', '')
450 if '/video
/get_media
' in video_url:
451 medias = self._download_json(video_url, video_id, fatal=False)
452 if isinstance(medias, list):
454 if not isinstance(media, dict):
456 video_url = url_or_none(media.get('videoUrl
'))
459 height = int_or_none(media.get('quality
'))
460 add_format(video_url, height)
462 add_format(video_url)
464 # field_preference is unnecessary here, but kept for code-similarity with youtube-dl
466 formats, field_preference=('height
', 'width
', 'fps
', 'format_id
'))
468 model_profile = self._search_json(
469 r'var\s
+MODEL_PROFILE\s
*=', webpage, 'model profile
', video_id, fatal=False)
470 video_uploader = self._html_search_regex(
471 r'(?s
)From
: 
;.+?
<(?
:a
\b[^
>]+\bhref
=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username
)[^
>]+>(.+?
)<',
472 webpage, 'uploader
', default=None) or model_profile.get('username
')
474 def extract_vote_count(kind, name):
475 return self._extract_count(
476 (r'<span
[^
>]+\bclass
="votes%s"[^
>]*>([\d
,\
.]+)</span
>' % kind,
477 r'<span
[^
>]+\bclass
=["\']votes%s["\'][^
>]*\bdata
-rating
=["\'](\d+)' % kind),
480 view_count = self._extract_count(
481 r'<span class="count
">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
482 like_count = extract_vote_count('Up', 'like')
483 dislike_count = extract_vote_count('Down', 'dislike')
484 comment_count = self._extract_count(
485 r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
487 def extract_list(meta_key):
488 div = self._search_regex(
489 r'(?s)<div[^>]+\bclass=["\'].*?
\b%sWrapper
[^
>]*>(.+?
)</div
>'
490 % meta_key, webpage, meta_key, default=None)
492 return [clean_html(x).strip() for x in re.findall(r'(?s
)<a
[^
>]+\bhref
=[^
>]+>.+?
</a
>', div)]
494 info = self._search_json_ld(webpage, video_id, default={})
495 # description provided in JSON-LD is irrelevant
496 info['description
'] = None
500 'uploader
': video_uploader,
501 'uploader_id
': remove_start(model_profile.get('modelProfileLink
'), '/model
/'),
502 'upload_date
': upload_date,
504 'thumbnail
': thumbnail,
505 'duration
': duration,
506 'view_count
': view_count,
507 'like_count
': like_count,
508 'dislike_count
': dislike_count,
509 'comment_count
': comment_count,
512 'tags
': extract_list('tags
'),
513 'categories
': extract_list('categories
'),
514 'cast
': extract_list('pornstars
'),
515 'subtitles
': subtitles,
519 class PornHubPlaylistBaseIE(PornHubBaseIE):
520 def _extract_page(self, url):
521 return int_or_none(self._search_regex(
522 r'\bpage
=(\d
+)', url, 'page
', default=None))
524 def _extract_entries(self, webpage, host):
525 # Only process container div with main playlist content skipping
526 # drop-down menu that uses similar pattern for videos (see
527 # https://github.com/ytdl-org/youtube-dl/issues/11594).
528 container = self._search_regex(
529 r'(?s
)(<div
[^
>]+class=["\']container.+)', webpage,
530 'container', default=webpage)
534 'http://www.%s/%s' % (host, video_url),
535 PornHubIE.ie_key(), video_title=title)
536 for video_url, title in orderedSet(re.findall(
537 r'href="/?
(view_video\
.php
\?.*\bviewkey
=[\da
-z
]+[^
"]*)"[^
>]*\s
+title
="([^"]+)"',
542 class PornHubUserIE(PornHubPlaylistBaseIE):
543 _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
545 'url': 'https://www.pornhub.com/model/zoe_ph',
546 'playlist_mincount': 118,
548 'url': 'https://www.pornhub.com/pornstar/liz-vicious',
552 'playlist_mincount': 118,
554 'url': 'https://www.pornhub.com/users/russianveet69',
555 'only_matching': True,
557 'url': 'https://www.pornhub.com/channels/povd',
558 'only_matching': True,
560 'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
561 'only_matching': True,
563 # Unavailable via /videos page, but available with direct pagination
564 # on pornstar page (see [1]), requires premium
565 # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
566 'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
567 'only_matching': True,
569 # Same as before, multi page
570 'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
571 'only_matching': True,
573 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph',
574 'only_matching': True,
577 def _real_extract(self, url):
578 mobj = self._match_valid_url(url)
579 user_id = mobj.group('id')
580 videos_url = '%s/videos' % mobj.group('url')
581 page = self._extract_page(url)
583 videos_url = update_url_query(videos_url, {'page': page})
584 return self.url_result(
585 videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
588 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
590 def _has_more(webpage):
593 <li[^>]+\bclass=["\']page_next|
594 <link
[^
>]+\brel
=["\']next|
595 <button[^>]+\bid=["\']moreDataBtn
596 ''', webpage) is not None
598 def _entries(self, url, host, item_id):
599 page = self._extract_page(url)
603 def download_page(base_url, num, fallback=False):
604 note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
605 return self._download_webpage(
606 base_url, item_id, note, query={'page': num})
609 return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
612 has_page = page is not None
613 first_page = page if has_page else 1
614 for page_num in (first_page, ) if has_page else itertools.count(first_page):
617 webpage = download_page(base_url, page_num)
618 except ExtractorError as e:
619 # Some sources may not be available via /videos page,
620 # trying to fallback to main page pagination (see [1])
621 # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
622 if is_404(e) and page_num == first_page and VIDEOS in base_url:
623 base_url = base_url.replace(VIDEOS, '')
624 webpage = download_page(base_url, page_num, fallback=True)
627 except ExtractorError as e:
628 if is_404(e) and page_num != first_page:
631 page_entries = self._extract_entries(webpage, host)
634 for e in page_entries:
636 if not self._has_more(webpage):
639 def _real_extract(self, url):
640 mobj = self._match_valid_url(url)
641 host = mobj.group('host')
642 item_id = mobj.group('id')
646 return self.playlist_result(self._entries(url, host, item_id), item_id)
649 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
650 _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
652 'url': 'https://www.pornhub.com/model/zoe_ph/videos',
653 'only_matching': True,
655 'url': 'http://www.pornhub.com/users/rushandlia/videos',
656 'only_matching': True,
658 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
660 'id': 'pornstar/jenny-blighe/videos',
662 'playlist_mincount': 149,
664 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
666 'id': 'pornstar/jenny-blighe/videos',
668 'playlist_mincount': 40,
670 # default sorting as Top Rated Videos
671 'url': 'https://www.pornhub.com/channels/povd/videos',
673 'id': 'channels/povd/videos',
675 'playlist_mincount': 293,
678 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
679 'only_matching': True,
682 'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
683 'only_matching': True,
686 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
687 'only_matching': True,
689 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
690 'only_matching': True,
693 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
694 'only_matching': True,
697 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
698 'only_matching': True,
701 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
702 'only_matching': True,
705 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
706 'only_matching': True,
708 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
709 'only_matching': True,
711 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
712 'only_matching': True,
714 'url': 'https://www.pornhub.com/video',
715 'only_matching': True,
717 'url': 'https://www.pornhub.com/video?page=3',
718 'only_matching': True,
720 'url': 'https://www.pornhub.com/video/search?search=123',
721 'only_matching': True,
723 'url': 'https://www.pornhub.com/categories/teen',
724 'only_matching': True,
726 'url': 'https://www.pornhub.com/categories/teen?page=3',
727 'only_matching': True,
729 'url': 'https://www.pornhub.com/hd',
730 'only_matching': True,
732 'url': 'https://www.pornhub.com/hd?page=3',
733 'only_matching': True,
735 'url': 'https://www.pornhub.com/described-video',
736 'only_matching': True,
738 'url': 'https://www.pornhub.com/described-video?page=2',
739 'only_matching': True,
741 'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
742 'only_matching': True,
744 'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph/videos',
745 'only_matching': True,
749 def suitable(cls, url):
751 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
752 else super(PornHubPagedVideoListIE, cls).suitable(url))
755 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
756 _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE
758 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
760 'id': 'jenny-blighe',
762 'playlist_mincount': 129,
764 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
765 'only_matching': True,
767 'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/pornstar/jenny-blighe/videos/upload',
768 'only_matching': True,
772 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
773 _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
775 'url': 'https://www.pornhub.com/playlist/44121572',
779 'playlist_count': 77,
781 'url': 'https://www.pornhub.com/playlist/4667351',
782 'only_matching': True,
784 'url': 'https://de.pornhub.com/playlist/4667351',
785 'only_matching': True,
787 'url': 'https://de.pornhub.com/playlist/4667351?page=2',
788 'only_matching': True,
791 def _entries(self, url, host, item_id):
792 webpage = self._download_webpage(url, item_id, 'Downloading page 1')
793 playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id')
794 video_count = int_or_none(
795 self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count'))
796 token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token')
797 page_count = math.ceil((video_count - 36) / 40.) + 1
798 page_entries = self._extract_entries(webpage, host)
800 def download_page(page_num):
801 note = 'Downloading page {}'.format(page_num)
802 page_url = 'https://www.{}/playlist/viewChunked'.format(host)
803 return self._download_webpage(page_url, item_id, note, query={
809 for page_num in range(1, page_count + 1):
811 webpage = download_page(page_num)
812 page_entries = self._extract_entries(webpage, host)
815 for e in page_entries:
818 def _real_extract(self, url):
819 mobj = self._match_valid_url(url)
820 host = mobj.group('host')
821 item_id = mobj.group('id')
825 return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id)