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