yt_dlp/extractor/pornhub.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import functools
   5 import itertools
   6 import operator
   7 import re
   8
   9 from .common import InfoExtractor
  10 from ..compat import (
  11     compat_HTTPError,
  12     compat_str,
  13     compat_urllib_request,
  14 )
  15 from .openload import PhantomJSwrapper
  16 from ..utils import (
  17     clean_html,
  18     determine_ext,
  19     ExtractorError,
  20     int_or_none,
  21     merge_dicts,
  22     NO_DEFAULT,
  23     orderedSet,
  24     remove_quotes,
  25     str_to_int,
  26     update_url_query,
  27     urlencode_postdata,
  28     url_or_none,
  29 )
  30
  31
  32 class PornHubBaseIE(InfoExtractor):
  33     _NETRC_MACHINE = 'pornhub'
  34
  35     def _download_webpage_handle(self, *args, **kwargs):
  36         def dl(*args, **kwargs):
  37             return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
  38
  39         ret = dl(*args, **kwargs)
  40
  41         if not ret:
  42             return ret
  43
  44         webpage, urlh = ret
  45
  46         if any(re.search(p, webpage) for p in (
  47                 r'<body\b[^>]+\bonload=["\']go\(\)',
  48                 r'document\.cookie\s*=\s*["\']RNKEY=',
  49                 r'document\.location\.reload\(true\)')):
  50             url_or_request = args[0]
  51             url = (url_or_request.get_full_url()
  52                    if isinstance(url_or_request, compat_urllib_request.Request)
  53                    else url_or_request)
  54             phantom = PhantomJSwrapper(self, required_version='2.0')
  55             phantom.get(url, html=webpage)
  56             webpage, urlh = dl(*args, **kwargs)
  57
  58         return webpage, urlh
  59
  60     def _real_initialize(self):
  61         self._logged_in = False
  62
  63     def _login(self, host):
  64         if self._logged_in:
  65             return
  66
  67         site = host.split('.')[0]
  68
  69         # Both sites pornhub and pornhubpremium have separate accounts
  70         # so there should be an option to provide credentials for both.
  71         # At the same time some videos are available under the same video id
  72         # on both sites so that we have to identify them as the same video.
  73         # For that purpose we have to keep both in the same extractor
  74         # but under different netrc machines.
  75         username, password = self._get_login_info(netrc_machine=site)
  76         if username is None:
  77             return
  78
  79         login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
  80         login_page = self._download_webpage(
  81             login_url, None, 'Downloading %s login page' % site)
  82
  83         def is_logged(webpage):
  84             return any(re.search(p, webpage) for p in (
  85                 r'class=["\']signOut',
  86                 r'>Sign\s+[Oo]ut\s*<'))
  87
  88         if is_logged(login_page):
  89             self._logged_in = True
  90             return
  91
  92         login_form = self._hidden_inputs(login_page)
  93
  94         login_form.update({
  95             'username': username,
  96             'password': password,
  97         })
  98
  99         response = self._download_json(
 100             'https://www.%s/front/authenticate' % host, None,
 101             'Logging in to %s' % site,
 102             data=urlencode_postdata(login_form),
 103             headers={
 104                 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 105                 'Referer': login_url,
 106                 'X-Requested-With': 'XMLHttpRequest',
 107             })
 108
 109         if response.get('success') == '1':
 110             self._logged_in = True
 111             return
 112
 113         message = response.get('message')
 114         if message is not None:
 115             raise ExtractorError(
 116                 'Unable to login: %s' % message, expected=True)
 117
 118         raise ExtractorError('Unable to log in')
 119
 120
 121 class PornHubIE(PornHubBaseIE):
 122     IE_DESC = 'PornHub and Thumbzilla'
 123     _VALID_URL = r'''(?x)
 124                     https?://
 125                         (?:
 126                             (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
 127                             (?:www\.)?thumbzilla\.com/video/
 128                         )
 129                         (?P<id>[\da-z]+)
 130                     '''
 131     _TESTS = [{
 132         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
 133         'md5': 'a6391306d050e4547f62b3f485dd9ba9',
 134         'info_dict': {
 135             'id': '648719015',
 136             'ext': 'mp4',
 137             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
 138             'uploader': 'Babes',
 139             'upload_date': '20130628',
 140             'timestamp': 1372447216,
 141             'duration': 361,
 142             'view_count': int,
 143             'like_count': int,
 144             'dislike_count': int,
 145             'comment_count': int,
 146             'age_limit': 18,
 147             'tags': list,
 148             'categories': list,
 149             'cast': list,
 150         },
 151     }, {
 152         # non-ASCII title
 153         'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
 154         'info_dict': {
 155             'id': '1331683002',
 156             'ext': 'mp4',
 157             'title': '重庆婷婷女王足交',
 158             'upload_date': '20150213',
 159             'timestamp': 1423804862,
 160             'duration': 1753,
 161             'view_count': int,
 162             'like_count': int,
 163             'dislike_count': int,
 164             'comment_count': int,
 165             'age_limit': 18,
 166             'tags': list,
 167             'categories': list,
 168         },
 169         'params': {
 170             'skip_download': True,
 171         },
 172         'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
 173     }, {
 174         # subtitles
 175         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
 176         'info_dict': {
 177             'id': 'ph5af5fef7c2aa7',
 178             'ext': 'mp4',
 179             'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
 180             'uploader': 'BFFs',
 181             'duration': 622,
 182             'view_count': int,
 183             'like_count': int,
 184             'dislike_count': int,
 185             'comment_count': int,
 186             'age_limit': 18,
 187             'tags': list,
 188             'categories': list,
 189             'subtitles': {
 190                 'en': [{
 191                     "ext": 'srt'
 192                 }]
 193             },
 194         },
 195         'params': {
 196             'skip_download': True,
 197         },
 198         'skip': 'This video has been disabled',
 199     }, {
 200         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
 201         'only_matching': True,
 202     }, {
 203         # removed at the request of cam4.com
 204         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
 205         'only_matching': True,
 206     }, {
 207         # removed at the request of the copyright owner
 208         'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
 209         'only_matching': True,
 210     }, {
 211         # removed by uploader
 212         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
 213         'only_matching': True,
 214     }, {
 215         # private video
 216         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
 217         'only_matching': True,
 218     }, {
 219         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
 220         'only_matching': True,
 221     }, {
 222         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
 223         'only_matching': True,
 224     }, {
 225         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
 226         'only_matching': True,
 227     }, {
 228         'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933',
 229         'only_matching': True,
 230     }, {
 231         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
 232         'only_matching': True,
 233     }, {
 234         # Some videos are available with the same id on both premium
 235         # and non-premium sites (e.g. this and the following test)
 236         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3',
 237         'only_matching': True,
 238     }, {
 239         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3',
 240         'only_matching': True,
 241     }]
 242
 243     @staticmethod
 244     def _extract_urls(webpage):
 245         return re.findall(
 246             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
 247             webpage)
 248
 249     def _extract_count(self, pattern, webpage, name):
 250         return str_to_int(self._search_regex(
 251             pattern, webpage, '%s count' % name, fatal=False))
 252
 253     def _real_extract(self, url):
 254         mobj = re.match(self._VALID_URL, url)
 255         host = mobj.group('host') or 'pornhub.com'
 256         video_id = mobj.group('id')
 257
 258         self._login(host)
 259
 260         self._set_cookie(host, 'age_verified', '1')
 261
 262         def dl_webpage(platform):
 263             self._set_cookie(host, 'platform', platform)
 264             return self._download_webpage(
 265                 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
 266                 video_id, 'Downloading %s webpage' % platform)
 267
 268         webpage = dl_webpage('pc')
 269
 270         error_msg = self._html_search_regex(
 271             (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
 272              r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
 273             webpage, 'error message', default=None, group='error')
 274         if error_msg:
 275             error_msg = re.sub(r'\s+', ' ', error_msg)
 276             raise ExtractorError(
 277                 'PornHub said: %s' % error_msg,
 278                 expected=True, video_id=video_id)
 279
 280         # video_title from flashvars contains whitespace instead of non-ASCII (see
 281         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
 282         # on that anymore.
 283         title = self._html_search_meta(
 284             'twitter:title', webpage, default=None) or self._html_search_regex(
 285             (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>',
 286              r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1',
 287              r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
 288             webpage, 'title', group='title')
 289
 290         video_urls = []
 291         video_urls_set = set()
 292         subtitles = {}
 293
 294         flashvars = self._parse_json(
 295             self._search_regex(
 296                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
 297             video_id)
 298         if flashvars:
 299             subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
 300             if subtitle_url:
 301                 subtitles.setdefault('en', []).append({
 302                     'url': subtitle_url,
 303                     'ext': 'srt',
 304                 })
 305             thumbnail = flashvars.get('image_url')
 306             duration = int_or_none(flashvars.get('video_duration'))
 307             media_definitions = flashvars.get('mediaDefinitions')
 308             if isinstance(media_definitions, list):
 309                 for definition in media_definitions:
 310                     if not isinstance(definition, dict):
 311                         continue
 312                     video_url = definition.get('videoUrl')
 313                     if not video_url or not isinstance(video_url, compat_str):
 314                         continue
 315                     if video_url in video_urls_set:
 316                         continue
 317                     video_urls_set.add(video_url)
 318                     video_urls.append(
 319                         (video_url, int_or_none(definition.get('quality'))))
 320         else:
 321             thumbnail, duration = [None] * 2
 322
 323         def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
 324             assignments = self._search_regex(
 325                 pattern, webpage, 'encoded url', default=default)
 326             if not assignments:
 327                 return {}
 328
 329             assignments = assignments.split(';')
 330
 331             js_vars = {}
 332
 333             def parse_js_value(inp):
 334                 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
 335                 if '+' in inp:
 336                     inps = inp.split('+')
 337                     return functools.reduce(
 338                         operator.concat, map(parse_js_value, inps))
 339                 inp = inp.strip()
 340                 if inp in js_vars:
 341                     return js_vars[inp]
 342                 return remove_quotes(inp)
 343
 344             for assn in assignments:
 345                 assn = assn.strip()
 346                 if not assn:
 347                     continue
 348                 assn = re.sub(r'var\s+', '', assn)
 349                 vname, value = assn.split('=', 1)
 350                 js_vars[vname] = parse_js_value(value)
 351             return js_vars
 352
 353         def add_video_url(video_url):
 354             v_url = url_or_none(video_url)
 355             if not v_url:
 356                 return
 357             if v_url in video_urls_set:
 358                 return
 359             video_urls.append((v_url, None))
 360             video_urls_set.add(v_url)
 361
 362         def parse_quality_items(quality_items):
 363             q_items = self._parse_json(quality_items, video_id, fatal=False)
 364             if not isinstance(q_items, list):
 365                 return
 366             for item in q_items:
 367                 if isinstance(item, dict):
 368                     add_video_url(item.get('url'))
 369
 370         if not video_urls:
 371             FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
 372             js_vars = extract_js_vars(
 373                 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
 374                 default=None)
 375             if js_vars:
 376                 for key, format_url in js_vars.items():
 377                     if key.startswith(FORMAT_PREFIXES[-1]):
 378                         parse_quality_items(format_url)
 379                     elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
 380                         add_video_url(format_url)
 381             if not video_urls and re.search(
 382                     r'<[^>]+\bid=["\']lockedPlayer', webpage):
 383                 raise ExtractorError(
 384                     'Video %s is locked' % video_id, expected=True)
 385
 386         if not video_urls:
 387             js_vars = extract_js_vars(
 388                 dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
 389             add_video_url(js_vars['mediastring'])
 390
 391         for mobj in re.finditer(
 392                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
 393                 webpage):
 394             video_url = mobj.group('url')
 395             if video_url not in video_urls_set:
 396                 video_urls.append((video_url, None))
 397                 video_urls_set.add(video_url)
 398
 399         upload_date = None
 400         formats = []
 401
 402         def add_format(format_url, height=None):
 403             ext = determine_ext(format_url)
 404             if ext == 'mpd':
 405                 formats.extend(self._extract_mpd_formats(
 406                     format_url, video_id, mpd_id='dash', fatal=False))
 407                 return
 408             if ext == 'm3u8':
 409                 formats.extend(self._extract_m3u8_formats(
 410                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 411                     m3u8_id='hls', fatal=False))
 412                 return
 413             tbr = None
 414             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url)
 415             if mobj:
 416                 if not height:
 417                     height = int(mobj.group('height'))
 418                 tbr = int(mobj.group('tbr'))
 419             formats.append({
 420                 'url': format_url,
 421                 'format_id': '%dp' % height if height else None,
 422                 'height': height,
 423                 'tbr': tbr,
 424             })
 425
 426         for video_url, height in video_urls:
 427             if not upload_date:
 428                 upload_date = self._search_regex(
 429                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
 430                 if upload_date:
 431                     upload_date = upload_date.replace('/', '')
 432             if '/video/get_media' in video_url:
 433                 medias = self._download_json(video_url, video_id, fatal=False)
 434                 if isinstance(medias, list):
 435                     for media in medias:
 436                         if not isinstance(media, dict):
 437                             continue
 438                         video_url = url_or_none(media.get('videoUrl'))
 439                         if not video_url:
 440                             continue
 441                         height = int_or_none(media.get('quality'))
 442                         add_format(video_url, height)
 443                 continue
 444             add_format(video_url)
 445         self._sort_formats(formats)
 446
 447         video_uploader = self._html_search_regex(
 448             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
 449             webpage, 'uploader', default=None)
 450
 451         def extract_vote_count(kind, name):
 452             return self._extract_count(
 453                 (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
 454                  r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
 455                 webpage, name)
 456
 457         view_count = self._extract_count(
 458             r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
 459         like_count = extract_vote_count('Up', 'like')
 460         dislike_count = extract_vote_count('Down', 'dislike')
 461         comment_count = self._extract_count(
 462             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 463
 464         def extract_list(meta_key):
 465             div = self._search_regex(
 466                 r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
 467                 % meta_key, webpage, meta_key, default=None)
 468             if div:
 469                 return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
 470
 471         info = self._search_json_ld(webpage, video_id, default={})
 472         # description provided in JSON-LD is irrelevant
 473         info['description'] = None
 474
 475         return merge_dicts({
 476             'id': video_id,
 477             'uploader': video_uploader,
 478             'upload_date': upload_date,
 479             'title': title,
 480             'thumbnail': thumbnail,
 481             'duration': duration,
 482             'view_count': view_count,
 483             'like_count': like_count,
 484             'dislike_count': dislike_count,
 485             'comment_count': comment_count,
 486             'formats': formats,
 487             'age_limit': 18,
 488             'tags': extract_list('tags'),
 489             'categories': extract_list('categories'),
 490             'cast': extract_list('pornstars'),
 491             'subtitles': subtitles,
 492         }, info)
 493
 494
 495 class PornHubPlaylistBaseIE(PornHubBaseIE):
 496     def _extract_page(self, url):
 497         return int_or_none(self._search_regex(
 498             r'\bpage=(\d+)', url, 'page', default=None))
 499
 500     def _extract_entries(self, webpage, host):
 501         # Only process container div with main playlist content skipping
 502         # drop-down menu that uses similar pattern for videos (see
 503         # https://github.com/ytdl-org/youtube-dl/issues/11594).
 504         container = self._search_regex(
 505             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
 506             'container', default=webpage)
 507
 508         return [
 509             self.url_result(
 510                 'http://www.%s/%s' % (host, video_url),
 511                 PornHubIE.ie_key(), video_title=title)
 512             for video_url, title in orderedSet(re.findall(
 513                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
 514                 container))
 515         ]
 516
 517
 518 class PornHubUserIE(PornHubPlaylistBaseIE):
 519     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
 520     _TESTS = [{
 521         'url': 'https://www.pornhub.com/model/zoe_ph',
 522         'playlist_mincount': 118,
 523     }, {
 524         'url': 'https://www.pornhub.com/pornstar/liz-vicious',
 525         'info_dict': {
 526             'id': 'liz-vicious',
 527         },
 528         'playlist_mincount': 118,
 529     }, {
 530         'url': 'https://www.pornhub.com/users/russianveet69',
 531         'only_matching': True,
 532     }, {
 533         'url': 'https://www.pornhub.com/channels/povd',
 534         'only_matching': True,
 535     }, {
 536         'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
 537         'only_matching': True,
 538     }, {
 539         # Unavailable via /videos page, but available with direct pagination
 540         # on pornstar page (see [1]), requires premium
 541         # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
 542         'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
 543         'only_matching': True,
 544     }, {
 545         # Same as before, multi page
 546         'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
 547         'only_matching': True,
 548     }]
 549
 550     def _real_extract(self, url):
 551         mobj = re.match(self._VALID_URL, url)
 552         user_id = mobj.group('id')
 553         videos_url = '%s/videos' % mobj.group('url')
 554         page = self._extract_page(url)
 555         if page:
 556             videos_url = update_url_query(videos_url, {'page': page})
 557         return self.url_result(
 558             videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
 559
 560
 561 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
 562     @staticmethod
 563     def _has_more(webpage):
 564         return re.search(
 565             r'''(?x)
 566                 <li[^>]+\bclass=["\']page_next|
 567                 <link[^>]+\brel=["\']next|
 568                 <button[^>]+\bid=["\']moreDataBtn
 569             ''', webpage) is not None
 570
 571     def _entries(self, url, host, item_id):
 572         page = self._extract_page(url)
 573
 574         VIDEOS = '/videos'
 575
 576         def download_page(base_url, num, fallback=False):
 577             note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
 578             return self._download_webpage(
 579                 base_url, item_id, note, query={'page': num})
 580
 581         def is_404(e):
 582             return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
 583
 584         base_url = url
 585         has_page = page is not None
 586         first_page = page if has_page else 1
 587         for page_num in (first_page, ) if has_page else itertools.count(first_page):
 588             try:
 589                 try:
 590                     webpage = download_page(base_url, page_num)
 591                 except ExtractorError as e:
 592                     # Some sources may not be available via /videos page,
 593                     # trying to fallback to main page pagination (see [1])
 594                     # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
 595                     if is_404(e) and page_num == first_page and VIDEOS in base_url:
 596                         base_url = base_url.replace(VIDEOS, '')
 597                         webpage = download_page(base_url, page_num, fallback=True)
 598                     else:
 599                         raise
 600             except ExtractorError as e:
 601                 if is_404(e) and page_num != first_page:
 602                     break
 603                 raise
 604             page_entries = self._extract_entries(webpage, host)
 605             if not page_entries:
 606                 break
 607             for e in page_entries:
 608                 yield e
 609             if not self._has_more(webpage):
 610                 break
 611
 612     def _real_extract(self, url):
 613         mobj = re.match(self._VALID_URL, url)
 614         host = mobj.group('host')
 615         item_id = mobj.group('id')
 616
 617         self._login(host)
 618
 619         return self.playlist_result(self._entries(url, host, item_id), item_id)
 620
 621
 622 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
 623     _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
 624     _TESTS = [{
 625         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
 626         'only_matching': True,
 627     }, {
 628         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 629         'only_matching': True,
 630     }, {
 631         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
 632         'info_dict': {
 633             'id': 'pornstar/jenny-blighe/videos',
 634         },
 635         'playlist_mincount': 149,
 636     }, {
 637         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
 638         'info_dict': {
 639             'id': 'pornstar/jenny-blighe/videos',
 640         },
 641         'playlist_mincount': 40,
 642     }, {
 643         # default sorting as Top Rated Videos
 644         'url': 'https://www.pornhub.com/channels/povd/videos',
 645         'info_dict': {
 646             'id': 'channels/povd/videos',
 647         },
 648         'playlist_mincount': 293,
 649     }, {
 650         # Top Rated Videos
 651         'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
 652         'only_matching': True,
 653     }, {
 654         # Most Recent Videos
 655         'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
 656         'only_matching': True,
 657     }, {
 658         # Most Viewed Videos
 659         'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
 660         'only_matching': True,
 661     }, {
 662         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 663         'only_matching': True,
 664     }, {
 665         # Most Viewed Videos
 666         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
 667         'only_matching': True,
 668     }, {
 669         # Top Rated Videos
 670         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
 671         'only_matching': True,
 672     }, {
 673         # Longest Videos
 674         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
 675         'only_matching': True,
 676     }, {
 677         # Newest Videos
 678         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
 679         'only_matching': True,
 680     }, {
 681         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
 682         'only_matching': True,
 683     }, {
 684         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
 685         'only_matching': True,
 686     }, {
 687         'url': 'https://www.pornhub.com/video',
 688         'only_matching': True,
 689     }, {
 690         'url': 'https://www.pornhub.com/video?page=3',
 691         'only_matching': True,
 692     }, {
 693         'url': 'https://www.pornhub.com/video/search?search=123',
 694         'only_matching': True,
 695     }, {
 696         'url': 'https://www.pornhub.com/categories/teen',
 697         'only_matching': True,
 698     }, {
 699         'url': 'https://www.pornhub.com/categories/teen?page=3',
 700         'only_matching': True,
 701     }, {
 702         'url': 'https://www.pornhub.com/hd',
 703         'only_matching': True,
 704     }, {
 705         'url': 'https://www.pornhub.com/hd?page=3',
 706         'only_matching': True,
 707     }, {
 708         'url': 'https://www.pornhub.com/described-video',
 709         'only_matching': True,
 710     }, {
 711         'url': 'https://www.pornhub.com/described-video?page=2',
 712         'only_matching': True,
 713     }, {
 714         'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
 715         'only_matching': True,
 716     }, {
 717         'url': 'https://www.pornhub.com/playlist/44121572',
 718         'info_dict': {
 719             'id': 'playlist/44121572',
 720         },
 721         'playlist_mincount': 132,
 722     }, {
 723         'url': 'https://www.pornhub.com/playlist/4667351',
 724         'only_matching': True,
 725     }, {
 726         'url': 'https://de.pornhub.com/playlist/4667351',
 727         'only_matching': True,
 728     }]
 729
 730     @classmethod
 731     def suitable(cls, url):
 732         return (False
 733                 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
 734                 else super(PornHubPagedVideoListIE, cls).suitable(url))
 735
 736
 737 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
 738     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
 739     _TESTS = [{
 740         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
 741         'info_dict': {
 742             'id': 'jenny-blighe',
 743         },
 744         'playlist_mincount': 129,
 745     }, {
 746         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
 747         'only_matching': True,
 748     }]