Raphaël G. Git Repositories - youtubedl/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 )
  14 from ..utils import (
  15     ExtractorError,
  16     int_or_none,
  17     js_to_json,
  18     orderedSet,
  19     remove_quotes,
  20     str_to_int,
  21     url_or_none,
  22 )
  23
  24
  25 class PornHubIE(InfoExtractor):
  26     IE_DESC = 'PornHub and Thumbzilla'
  27     _VALID_URL = r'''(?x)
  28                     https?://
  29                         (?:
  30                             (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
  31                             (?:www\.)?thumbzilla\.com/video/
  32                         )
  33                         (?P<id>[\da-z]+)
  34                     '''
  35     _TESTS = [{
  36         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
  37         'md5': '1e19b41231a02eba417839222ac9d58e',
  38         'info_dict': {
  39             'id': '648719015',
  40             'ext': 'mp4',
  41             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
  42             'uploader': 'Babes',
  43             'upload_date': '20130628',
  44             'duration': 361,
  45             'view_count': int,
  46             'like_count': int,
  47             'dislike_count': int,
  48             'comment_count': int,
  49             'age_limit': 18,
  50             'tags': list,
  51             'categories': list,
  52         },
  53     }, {
  54         # non-ASCII title
  55         'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
  56         'info_dict': {
  57             'id': '1331683002',
  58             'ext': 'mp4',
  59             'title': '重庆婷婷女王足交',
  60             'uploader': 'Unknown',
  61             'upload_date': '20150213',
  62             'duration': 1753,
  63             'view_count': int,
  64             'like_count': int,
  65             'dislike_count': int,
  66             'comment_count': int,
  67             'age_limit': 18,
  68             'tags': list,
  69             'categories': list,
  70         },
  71         'params': {
  72             'skip_download': True,
  73         },
  74     }, {
  75         # subtitles
  76         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
  77         'info_dict': {
  78             'id': 'ph5af5fef7c2aa7',
  79             'ext': 'mp4',
  80             'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
  81             'uploader': 'BFFs',
  82             'duration': 622,
  83             'view_count': int,
  84             'like_count': int,
  85             'dislike_count': int,
  86             'comment_count': int,
  87             'age_limit': 18,
  88             'tags': list,
  89             'categories': list,
  90             'subtitles': {
  91                 'en': [{
  92                     "ext": 'srt'
  93                 }]
  94             },
  95         },
  96         'params': {
  97             'skip_download': True,
  98         },
  99     }, {
 100         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
 101         'only_matching': True,
 102     }, {
 103         # removed at the request of cam4.com
 104         'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
 105         'only_matching': True,
 106     }, {
 107         # removed at the request of the copyright owner
 108         'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
 109         'only_matching': True,
 110     }, {
 111         # removed by uploader
 112         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
 113         'only_matching': True,
 114     }, {
 115         # private video
 116         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
 117         'only_matching': True,
 118     }, {
 119         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
 120         'only_matching': True,
 121     }, {
 122         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
 123         'only_matching': True,
 124     }, {
 125         'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
 126         'only_matching': True,
 127     }]
 128
 129     @staticmethod
 130     def _extract_urls(webpage):
 131         return re.findall(
 132             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
 133             webpage)
 134
 135     def _extract_count(self, pattern, webpage, name):
 136         return str_to_int(self._search_regex(
 137             pattern, webpage, '%s count' % name, fatal=False))
 138
 139     def _real_extract(self, url):
 140         mobj = re.match(self._VALID_URL, url)
 141         host = mobj.group('host') or 'pornhub.com'
 142         video_id = mobj.group('id')
 143
 144         self._set_cookie(host, 'age_verified', '1')
 145
 146         def dl_webpage(platform):
 147             self._set_cookie(host, 'platform', platform)
 148             return self._download_webpage(
 149                 'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
 150                 video_id, 'Downloading %s webpage' % platform)
 151
 152         webpage = dl_webpage('pc')
 153
 154         error_msg = self._html_search_regex(
 155             r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
 156             webpage, 'error message', default=None, group='error')
 157         if error_msg:
 158             error_msg = re.sub(r'\s+', ' ', error_msg)
 159             raise ExtractorError(
 160                 'PornHub said: %s' % error_msg,
 161                 expected=True, video_id=video_id)
 162
 163         # video_title from flashvars contains whitespace instead of non-ASCII (see
 164         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
 165         # on that anymore.
 166         title = self._html_search_meta(
 167             'twitter:title', webpage, default=None) or self._search_regex(
 168             (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
 169              r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
 170              r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
 171             webpage, 'title', group='title')
 172
 173         video_urls = []
 174         video_urls_set = set()
 175         subtitles = {}
 176
 177         flashvars = self._parse_json(
 178             self._search_regex(
 179                 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
 180             video_id)
 181         if flashvars:
 182             subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
 183             if subtitle_url:
 184                 subtitles.setdefault('en', []).append({
 185                     'url': subtitle_url,
 186                     'ext': 'srt',
 187                 })
 188             thumbnail = flashvars.get('image_url')
 189             duration = int_or_none(flashvars.get('video_duration'))
 190             media_definitions = flashvars.get('mediaDefinitions')
 191             if isinstance(media_definitions, list):
 192                 for definition in media_definitions:
 193                     if not isinstance(definition, dict):
 194                         continue
 195                     video_url = definition.get('videoUrl')
 196                     if not video_url or not isinstance(video_url, compat_str):
 197                         continue
 198                     if video_url in video_urls_set:
 199                         continue
 200                     video_urls_set.add(video_url)
 201                     video_urls.append(
 202                         (video_url, int_or_none(definition.get('quality'))))
 203         else:
 204             thumbnail, duration = [None] * 2
 205
 206         if not video_urls:
 207             tv_webpage = dl_webpage('tv')
 208
 209             assignments = self._search_regex(
 210                 r'(var.+?mediastring.+?)</script>', tv_webpage,
 211                 'encoded url').split(';')
 212
 213             js_vars = {}
 214
 215             def parse_js_value(inp):
 216                 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
 217                 if '+' in inp:
 218                     inps = inp.split('+')
 219                     return functools.reduce(
 220                         operator.concat, map(parse_js_value, inps))
 221                 inp = inp.strip()
 222                 if inp in js_vars:
 223                     return js_vars[inp]
 224                 return remove_quotes(inp)
 225
 226             for assn in assignments:
 227                 assn = assn.strip()
 228                 if not assn:
 229                     continue
 230                 assn = re.sub(r'var\s+', '', assn)
 231                 vname, value = assn.split('=', 1)
 232                 js_vars[vname] = parse_js_value(value)
 233
 234             video_url = js_vars['mediastring']
 235             if video_url not in video_urls_set:
 236                 video_urls.append((video_url, None))
 237                 video_urls_set.add(video_url)
 238
 239         for mobj in re.finditer(
 240                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
 241                 webpage):
 242             video_url = mobj.group('url')
 243             if video_url not in video_urls_set:
 244                 video_urls.append((video_url, None))
 245                 video_urls_set.add(video_url)
 246
 247         upload_date = None
 248         formats = []
 249         for video_url, height in video_urls:
 250             if not upload_date:
 251                 upload_date = self._search_regex(
 252                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
 253                 if upload_date:
 254                     upload_date = upload_date.replace('/', '')
 255             tbr = None
 256             mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
 257             if mobj:
 258                 if not height:
 259                     height = int(mobj.group('height'))
 260                 tbr = int(mobj.group('tbr'))
 261             formats.append({
 262                 'url': video_url,
 263                 'format_id': '%dp' % height if height else None,
 264                 'height': height,
 265                 'tbr': tbr,
 266             })
 267         self._sort_formats(formats)
 268
 269         video_uploader = self._html_search_regex(
 270             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
 271             webpage, 'uploader', fatal=False)
 272
 273         view_count = self._extract_count(
 274             r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
 275         like_count = self._extract_count(
 276             r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
 277         dislike_count = self._extract_count(
 278             r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
 279         comment_count = self._extract_count(
 280             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 281
 282         page_params = self._parse_json(self._search_regex(
 283             r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
 284             webpage, 'page parameters', group='data', default='{}'),
 285             video_id, transform_source=js_to_json, fatal=False)
 286         tags = categories = None
 287         if page_params:
 288             tags = page_params.get('tags', '').split(',')
 289             categories = page_params.get('categories', '').split(',')
 290
 291         return {
 292             'id': video_id,
 293             'uploader': video_uploader,
 294             'upload_date': upload_date,
 295             'title': title,
 296             'thumbnail': thumbnail,
 297             'duration': duration,
 298             'view_count': view_count,
 299             'like_count': like_count,
 300             'dislike_count': dislike_count,
 301             'comment_count': comment_count,
 302             'formats': formats,
 303             'age_limit': 18,
 304             'tags': tags,
 305             'categories': categories,
 306             'subtitles': subtitles,
 307         }
 308
 309
 310 class PornHubPlaylistBaseIE(InfoExtractor):
 311     def _extract_entries(self, webpage, host):
 312         # Only process container div with main playlist content skipping
 313         # drop-down menu that uses similar pattern for videos (see
 314         # https://github.com/rg3/youtube-dl/issues/11594).
 315         container = self._search_regex(
 316             r'(?s)(<div[^>]+class=["\']container.+)', webpage,
 317             'container', default=webpage)
 318
 319         return [
 320             self.url_result(
 321                 'http://www.%s/%s' % (host, video_url),
 322                 PornHubIE.ie_key(), video_title=title)
 323             for video_url, title in orderedSet(re.findall(
 324                 r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
 325                 container))
 326         ]
 327
 328     def _real_extract(self, url):
 329         mobj = re.match(self._VALID_URL, url)
 330         host = mobj.group('host')
 331         playlist_id = mobj.group('id')
 332
 333         webpage = self._download_webpage(url, playlist_id)
 334
 335         entries = self._extract_entries(webpage, host)
 336
 337         playlist = self._parse_json(
 338             self._search_regex(
 339                 r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
 340                 'playlist', default='{}'),
 341             playlist_id, fatal=False)
 342         title = playlist.get('title') or self._search_regex(
 343             r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
 344
 345         return self.playlist_result(
 346             entries, playlist_id, title, playlist.get('description'))
 347
 348
 349 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
 350     _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
 351     _TESTS = [{
 352         'url': 'http://www.pornhub.com/playlist/4667351',
 353         'info_dict': {
 354             'id': '4667351',
 355             'title': 'Nataly Hot',
 356         },
 357         'playlist_mincount': 2,
 358     }, {
 359         'url': 'https://de.pornhub.com/playlist/4667351',
 360         'only_matching': True,
 361     }]
 362
 363
 364 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
 365     _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
 366     _TESTS = [{
 367         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 368         'info_dict': {
 369             'id': 'zoe_ph',
 370         },
 371         'playlist_mincount': 171,
 372     }, {
 373         'url': 'http://www.pornhub.com/users/rushandlia/videos',
 374         'only_matching': True,
 375     }, {
 376         # default sorting as Top Rated Videos
 377         'url': 'https://www.pornhub.com/channels/povd/videos',
 378         'info_dict': {
 379             'id': 'povd',
 380         },
 381         'playlist_mincount': 293,
 382     }, {
 383         # Top Rated Videos
 384         'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
 385         'only_matching': True,
 386     }, {
 387         # Most Recent Videos
 388         'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
 389         'only_matching': True,
 390     }, {
 391         # Most Viewed Videos
 392         'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
 393         'only_matching': True,
 394     }, {
 395         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
 396         'only_matching': True,
 397     }, {
 398         'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
 399         'only_matching': True,
 400     }, {
 401         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
 402         'only_matching': True,
 403     }]
 404
 405     def _real_extract(self, url):
 406         mobj = re.match(self._VALID_URL, url)
 407         host = mobj.group('host')
 408         user_id = mobj.group('id')
 409
 410         entries = []
 411         for page_num in itertools.count(1):
 412             try:
 413                 webpage = self._download_webpage(
 414                     url, user_id, 'Downloading page %d' % page_num,
 415                     query={'page': page_num})
 416             except ExtractorError as e:
 417                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
 418                     break
 419                 raise
 420             page_entries = self._extract_entries(webpage, host)
 421             if not page_entries:
 422                 break
 423             entries.extend(page_entries)
 424
 425         return self.playlist_result(entries, user_id)