_ Git - youtube-dl/blob - 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     orderedSet,
  21     remove_quotes,
  22     str_to_int,
  23     url_or_none,
  24 )
  25
  26
  27 class PornHubBaseIE(InfoExtractor):
  28     def _download_webpage_handle(self, *args, **kwargs):
  29         def dl(*args, **kwargs):
  30             return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
  31
  32         webpage, urlh = dl(*args, **kwargs)
  33
  34         if any(re.search(p, webpage) for p in (
  35                 r'<body\b[^>]+\bonload=["\']go\(\)',
  36                 r'document\.cookie\s*=\s*["\']RNKEY=',
  37                 r'document\.location\.reload\(true\)')):
  38             url_or_request = args[0]
  39             url = (url_or_request.get_full_url()
  40                    if isinstance(url_or_request, compat_urllib_request.Request)
  41                    else url_or_request)
  42             phantom = PhantomJSwrapper(self, required_version='2.0')
  43             phantom.get(url, html=webpage)
  44             webpage, urlh = dl(*args, **kwargs)
  45
  46         return webpage, urlh
  47
  48
  49 class PornHubIE(PornHubBaseIE):
  50     IE_DESC = 'PornHub and Thumbzilla'
  51     _VALID_URL = r'''(?x)
  52                     https?://
  53                         (?:
  54                             (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
  55                             (?:www\.)?thumbzilla\.com/video/
  56                         )
  57                         (?P<id>[\da-z]+)
  58                     '''
  59     _TESTS = [{
  60         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  61         'md5': '1e19b41231a02eba417839222ac9d58e',
  62         'info_dict': {
  63             'id': '648719015',
  64             'ext': 'mp4',
  65             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
  66             'uploader': 'Babes',
  67             'upload_date': '20130628',
  68             'duration': 361,
  69             'view_count': int,
  70             'like_count': int,
  71             'dislike_count': int,
  72             'comment_count': int,
  73             'age_limit': 18,
  74             'tags': list,
  75             'categories': list,
  76         },
  77     }, {
  78         # non-ASCII title
  79         'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
  80         'info_dict': {
  81             'id': '1331683002',
  82             'ext': 'mp4',
  83             'title': '重庆婷婷女王足交',
  84             'uploader': 'Unknown',
  85             'upload_date': '20150213',
  86             'duration': 1753,
  87             'view_count': int,
  88             'like_count': int,
  89             'dislike_count': int,
  90             'comment_count': int,
  91             'age_limit': 18,
  92             'tags': list,
  93             'categories': list,
  94         },
  95         'params': {
  96             'skip_download': True,
  97         },
  98     }, {
  99         # subtitles
 100         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
 101         'info_dict': {
 102             'id': 'ph5af5fef7c2aa7',
 103             'ext': 'mp4',
 104             'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
 105             'uploader': 'BFFs',
 106             'duration': 622,
 107             'view_count': int,
 108             'like_count': int,
 109             'dislike_count': int,
 110             'comment_count': int,
 111             'age_limit': 18,
 112             'tags': list,
 113             'categories': list,
 114             'subtitles': {
 115                 'en': [{
 116                     "ext": 'srt'
 117                 }]
 118             },
 119         },
 120         'params': {
 121             'skip_download': True,
 122         },
 123     }, {
 124         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
 125         'only_matching': True,
 126     }, {
 127         # removed at the request of cam4.com
 128         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
 129         'only_matching': True,
 130     }, {
 131         # removed at the request of the copyright owner
 132         'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
 133         'only_matching': True,
 134     }, {
 135         # removed by uploader
 136         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
 137         'only_matching': True,
 138     }, {
 139         # private video
 140         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
 141         'only_matching': True,
 142     }, {
 143         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
 144         'only_matching': True,
 145     }, {
 146         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
 147         'only_matching': True,
 148     }, {
 149         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
 150         'only_matching': True,
 151     }]
 152
 153     @staticmethod
 154     def _extract_urls(webpage):
 155         return re.findall(
 156             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
 157             webpage)
 158
 159     def _extract_count(self, pattern, webpage, name):
 160         return str_to_int(self._search_regex(
 161             pattern, webpage, '%s count' % name, fatal=False))
 162
 163     def _real_extract(self, url):
 164         mobj = re.match(self._VALID_URL, url)
 165         host = mobj.group('host') or 'pornhub.com'
 166         video_id = mobj.group('id')
 167
 168         self._set_cookie(host, 'age_verified', '1')
 169
 170         def dl_webpage(platform):
 171             self._set_cookie(host, 'platform', platform)
 172             return self._download_webpage(
 173                 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
 174                 video_id, 'Downloading %s webpage' % platform)
 175
 176         webpage = dl_webpage('pc')
 177
 178         error_msg = self._html_search_regex(
 179             r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
 180             webpage, 'error message', default=None, group='error')
 181         if error_msg:
 182             error_msg = re.sub(r'\s+', ' ', error_msg)
 183             raise ExtractorError(
 184                 'PornHub said: %s' % error_msg,
 185                 expected=True, video_id=video_id)
 186
 187         # video_title from flashvars contains whitespace instead of non-ASCII (see
 188         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
 189         # on that anymore.
 190         title = self._html_search_meta(
 191             'twitter:title', webpage, default=None) or self._search_regex(
 192             (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
 193              r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
 194              r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
 195             webpage, 'title', group='title')
 196
 197         video_urls = []
 198         video_urls_set = set()
 199         subtitles = {}
 200
 201         flashvars = self._parse_json(
 202             self._search_regex(
 203                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
 204             video_id)
 205         if flashvars:
 206             subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
 207             if subtitle_url:
 208                 subtitles.setdefault('en', []).append({
 209                     'url': subtitle_url,
 210                     'ext': 'srt',
 211                 })
 212             thumbnail = flashvars.get('image_url')
 213             duration = int_or_none(flashvars.get('video_duration'))
 214             media_definitions = flashvars.get('mediaDefinitions')
 215             if isinstance(media_definitions, list):
 216                 for definition in media_definitions:
 217                     if not isinstance(definition, dict):
 218                         continue
 219                     video_url = definition.get('videoUrl')
 220                     if not video_url or not isinstance(video_url, compat_str):
 221                         continue
 222                     if video_url in video_urls_set:
 223                         continue
 224                     video_urls_set.add(video_url)
 225                     video_urls.append(
 226                         (video_url, int_or_none(definition.get('quality'))))
 227         else:
 228             thumbnail, duration = [None] * 2
 229
 230         def extract_js_vars(webpage, pattern, fatal=True):
 231             assignments = self._search_regex(
 232                 pattern, webpage, 'encoded url', fatal=fatal)
 233             if not assignments:
 234                 return {}
 235
 236             assignments = assignments.split(';')
 237
 238             js_vars = {}
 239
 240             def parse_js_value(inp):
 241                 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
 242                 if '+' in inp:
 243                     inps = inp.split('+')
 244                     return functools.reduce(
 245                         operator.concat, map(parse_js_value, inps))
 246                 inp = inp.strip()
 247                 if inp in js_vars:
 248                     return js_vars[inp]
 249                 return remove_quotes(inp)
 250
 251             for assn in assignments:
 252                 assn = assn.strip()
 253                 if not assn:
 254                     continue
 255                 assn = re.sub(r'var\s+', '', assn)
 256                 vname, value = assn.split('=', 1)
 257                 js_vars[vname] = parse_js_value(value)
 258             return js_vars
 259
 260         def add_video_url(video_url):
 261             v_url = url_or_none(video_url)
 262             if not v_url:
 263                 return
 264             if v_url in video_urls_set:
 265                 return
 266             video_urls.append((v_url, None))
 267             video_urls_set.add(v_url)
 268
 269         if not video_urls:
 270             FORMAT_PREFIXES = ('media', 'quality')
 271             js_vars = extract_js_vars(
 272                 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
 273                 fatal=False)
 274             if js_vars:
 275                 for key, format_url in js_vars.items():
 276                     if any(key.startswith(p) for p in FORMAT_PREFIXES):
 277                         add_video_url(format_url)
 278
 279         if not video_urls:
 280             js_vars = extract_js_vars(
 281                 dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
 282             add_video_url(js_vars['mediastring'])
 283
 284         for mobj in re.finditer(
 285                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
 286                 webpage):
 287             video_url = mobj.group('url')
 288             if video_url not in video_urls_set:
 289                 video_urls.append((video_url, None))
 290                 video_urls_set.add(video_url)
 291
 292         upload_date = None
 293         formats = []
 294         for video_url, height in video_urls:
 295             if not upload_date:
 296                 upload_date = self._search_regex(
 297                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
 298                 if upload_date:
 299                     upload_date = upload_date.replace('/', '')
 300             ext = determine_ext(video_url)
 301             if ext == 'mpd':
 302                 formats.extend(self._extract_mpd_formats(
 303                     video_url, video_id, mpd_id='dash', fatal=False))
 304                 continue
 305             elif ext == 'm3u8':
 306                 formats.extend(self._extract_m3u8_formats(
 307                     video_url, video_id, 'mp4', entry_protocol='m3u8_native',
 308                     m3u8_id='hls', fatal=False))
 309                 continue
 310             tbr = None
 311             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
 312             if mobj:
 313                 if not height:
 314                     height = int(mobj.group('height'))
 315                 tbr = int(mobj.group('tbr'))
 316             formats.append({
 317                 'url': video_url,
 318                 'format_id': '%dp' % height if height else None,
 319                 'height': height,
 320                 'tbr': tbr,
 321             })
 322         self._sort_formats(formats)
 323
 324         video_uploader = self._html_search_regex(
 325             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
 326             webpage, 'uploader', fatal=False)
 327
 328         view_count = self._extract_count(
 329             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
 330         like_count = self._extract_count(
 331             r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
 332         dislike_count = self._extract_count(
 333             r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
 334         comment_count = self._extract_count(
 335             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 336
 337         def extract_list(meta_key):
 338             div = self._search_regex(
 339                 r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
 340                 % meta_key, webpage, meta_key, default=None)
 341             if div:
 342                 return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
 343
 344         return {
 345             'id': video_id,
 346             'uploader': video_uploader,
 347             'upload_date': upload_date,
 348             'title': title,
 349             'thumbnail': thumbnail,
 350             'duration': duration,
 351             'view_count': view_count,
 352             'like_count': like_count,
 353             'dislike_count': dislike_count,
 354             'comment_count': comment_count,
 355             'formats': formats,
 356             'age_limit': 18,
 357             'tags': extract_list('tags'),
 358             'categories': extract_list('categories'),
 359             'subtitles': subtitles,
 360         }
 361
 362
 363 class PornHubPlaylistBaseIE(PornHubBaseIE):
 364     def _extract_entries(self, webpage, host):
 365         # Only process container div with main playlist content skipping
 366         # drop-down menu that uses similar pattern for videos (see
 367         # https://github.com/ytdl-org/youtube-dl/issues/11594).
 368         container = self._search_regex(
 369             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
 370             'container', default=webpage)
 371
 372         return [
 373             self.url_result(
 374                 'http://www.%s/%s' % (host, video_url),
 375                 PornHubIE.ie_key(), video_title=title)
 376             for video_url, title in orderedSet(re.findall(
 377                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
 378                 container))
 379         ]
 380
 381     def _real_extract(self, url):
 382         mobj = re.match(self._VALID_URL, url)
 383         host = mobj.group('host')
 384         playlist_id = mobj.group('id')
 385
 386         webpage = self._download_webpage(url, playlist_id)
 387
 388         entries = self._extract_entries(webpage, host)
 389
 390         playlist = self._parse_json(
 391             self._search_regex(
 392                 r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
 393                 'playlist', default='{}'),
 394             playlist_id, fatal=False)
 395         title = playlist.get('title') or self._search_regex(
 396             r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
 397
 398         return self.playlist_result(
 399             entries, playlist_id, title, playlist.get('description'))
 400
 401
 402 class PornHubUserIE(PornHubPlaylistBaseIE):
 403     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
 404     _TESTS = [{
 405         'url': 'https://www.pornhub.com/model/zoe_ph',
 406         'playlist_mincount': 118,
 407     }, {
 408         'url': 'https://www.pornhub.com/pornstar/liz-vicious',
 409         'info_dict': {
 410             'id': 'liz-vicious',
 411         },
 412         'playlist_mincount': 118,
 413     }, {
 414         'url': 'https://www.pornhub.com/users/russianveet69',
 415         'only_matching': True,
 416     }, {
 417         'url': 'https://www.pornhub.com/channels/povd',
 418         'only_matching': True,
 419     }, {
 420         'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
 421         'only_matching': True,
 422     }]
 423
 424     def _real_extract(self, url):
 425         mobj = re.match(self._VALID_URL, url)
 426         user_id = mobj.group('id')
 427         return self.url_result(
 428             '%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
 429             video_id=user_id)
 430
 431
 432 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
 433     @staticmethod
 434     def _has_more(webpage):
 435         return re.search(
 436             r'''(?x)
 437                 <li[^>]+\bclass=["\']page_next|
 438                 <link[^>]+\brel=["\']next|
 439                 <button[^>]+\bid=["\']moreDataBtn
 440             ''', webpage) is not None
 441
 442     def _real_extract(self, url):
 443         mobj = re.match(self._VALID_URL, url)
 444         host = mobj.group('host')
 445         item_id = mobj.group('id')
 446
 447         page = int_or_none(self._search_regex(
 448             r'\bpage=(\d+)', url, 'page', default=None))
 449
 450         entries = []
 451         for page_num in (page, ) if page is not None else itertools.count(1):
 452             try:
 453                 webpage = self._download_webpage(
 454                     url, item_id, 'Downloading page %d' % page_num,
 455                     query={'page': page_num})
 456             except ExtractorError as e:
 457                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
 458                     break
 459                 raise
 460             page_entries = self._extract_entries(webpage, host)
 461             if not page_entries:
 462                 break
 463             entries.extend(page_entries)
 464             if not self._has_more(webpage):
 465                 break
 466
 467         return self.playlist_result(orderedSet(entries), item_id)
 468
 469
 470 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
 471     _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
 472     _TESTS = [{
 473         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
 474         'only_matching': True,
 475     }, {
 476         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 477         'only_matching': True,
 478     }, {
 479         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
 480         'info_dict': {
 481             'id': 'pornstar/jenny-blighe/videos',
 482         },
 483         'playlist_mincount': 149,
 484     }, {
 485         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
 486         'info_dict': {
 487             'id': 'pornstar/jenny-blighe/videos',
 488         },
 489         'playlist_mincount': 40,
 490     }, {
 491         # default sorting as Top Rated Videos
 492         'url': 'https://www.pornhub.com/channels/povd/videos',
 493         'info_dict': {
 494             'id': 'channels/povd/videos',
 495         },
 496         'playlist_mincount': 293,
 497     }, {
 498         # Top Rated Videos
 499         'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
 500         'only_matching': True,
 501     }, {
 502         # Most Recent Videos
 503         'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
 504         'only_matching': True,
 505     }, {
 506         # Most Viewed Videos
 507         'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
 508         'only_matching': True,
 509     }, {
 510         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 511         'only_matching': True,
 512     }, {
 513         # Most Viewed Videos
 514         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
 515         'only_matching': True,
 516     }, {
 517         # Top Rated Videos
 518         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
 519         'only_matching': True,
 520     }, {
 521         # Longest Videos
 522         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
 523         'only_matching': True,
 524     }, {
 525         # Newest Videos
 526         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
 527         'only_matching': True,
 528     }, {
 529         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
 530         'only_matching': True,
 531     }, {
 532         'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
 533         'only_matching': True,
 534     }, {
 535         'url': 'https://www.pornhub.com/video',
 536         'only_matching': True,
 537     }, {
 538         'url': 'https://www.pornhub.com/video?page=3',
 539         'only_matching': True,
 540     }, {
 541         'url': 'https://www.pornhub.com/video/search?search=123',
 542         'only_matching': True,
 543     }, {
 544         'url': 'https://www.pornhub.com/categories/teen',
 545         'only_matching': True,
 546     }, {
 547         'url': 'https://www.pornhub.com/categories/teen?page=3',
 548         'only_matching': True,
 549     }, {
 550         'url': 'https://www.pornhub.com/hd',
 551         'only_matching': True,
 552     }, {
 553         'url': 'https://www.pornhub.com/hd?page=3',
 554         'only_matching': True,
 555     }, {
 556         'url': 'https://www.pornhub.com/described-video',
 557         'only_matching': True,
 558     }, {
 559         'url': 'https://www.pornhub.com/described-video?page=2',
 560         'only_matching': True,
 561     }, {
 562         'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
 563         'only_matching': True,
 564     }, {
 565         'url': 'https://www.pornhub.com/playlist/44121572',
 566         'info_dict': {
 567             'id': 'playlist/44121572',
 568         },
 569         'playlist_mincount': 132,
 570     }, {
 571         'url': 'https://www.pornhub.com/playlist/4667351',
 572         'only_matching': True,
 573     }, {
 574         'url': 'https://de.pornhub.com/playlist/4667351',
 575         'only_matching': True,
 576     }]
 577
 578     @classmethod
 579     def suitable(cls, url):
 580         return (False
 581                 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
 582                 else super(PornHubPagedVideoListIE, cls).suitable(url))
 583
 584
 585 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
 586     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
 587     _TESTS = [{
 588         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
 589         'info_dict': {
 590             'id': 'jenny-blighe',
 591         },
 592         'playlist_mincount': 129,
 593     }, {
 594         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
 595         'only_matching': True,
 596     }]