youtube_dl/extractor/xhamster.py

   1 from __future__ import unicode_literals
   2
   3 import itertools
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     clean_html,
  10     determine_ext,
  11     dict_get,
  12     extract_attributes,
  13     ExtractorError,
  14     float_or_none,
  15     int_or_none,
  16     parse_duration,
  17     str_or_none,
  18     try_get,
  19     unified_strdate,
  20     url_or_none,
  21     urljoin,
  22 )
  23
  24
  25 class XHamsterIE(InfoExtractor):
  26     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
  27     _VALID_URL = r'''(?x)
  28                     https?://
  29                         (?:.+?\.)?%s/
  30                         (?:
  31                             movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
  32                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
  33                         )
  34                     ''' % _DOMAINS
  35     _TESTS = [{
  36         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  37         'md5': '98b4687efb1ffd331c4197854dc09e8f',
  38         'info_dict': {
  39             'id': '1509445',
  40             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
  41             'ext': 'mp4',
  42             'title': 'FemaleAgent Shy beauty takes the bait',
  43             'timestamp': 1350194821,
  44             'upload_date': '20121014',
  45             'uploader': 'Ruseful2011',
  46             'duration': 893,
  47             'age_limit': 18,
  48         },
  49     }, {
  50         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  51         'info_dict': {
  52             'id': '2221348',
  53             'display_id': 'britney-spears-sexy-booty',
  54             'ext': 'mp4',
  55             'title': 'Britney Spears  Sexy Booty',
  56             'timestamp': 1379123460,
  57             'upload_date': '20130914',
  58             'uploader': 'jojo747400',
  59             'duration': 200,
  60             'age_limit': 18,
  61         },
  62         'params': {
  63             'skip_download': True,
  64         },
  65     }, {
  66         # empty seo, unavailable via new URL schema
  67         'url': 'http://xhamster.com/movies/5667973/.html',
  68         'info_dict': {
  69             'id': '5667973',
  70             'ext': 'mp4',
  71             'title': '....',
  72             'timestamp': 1454948101,
  73             'upload_date': '20160208',
  74             'uploader': 'parejafree',
  75             'duration': 72,
  76             'age_limit': 18,
  77         },
  78         'params': {
  79             'skip_download': True,
  80         },
  81     }, {
  82         # mobile site
  83         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  84         'only_matching': True,
  85     }, {
  86         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  87         'only_matching': True,
  88     }, {
  89         # This video is visible for marcoalfa123456's friends only
  90         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  91         'only_matching': True,
  92     }, {
  93         # new URL schema
  94         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  95         'only_matching': True,
  96     }, {
  97         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  98         'only_matching': True,
  99     }, {
 100         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 101         'only_matching': True,
 102     }, {
 103         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 104         'only_matching': True,
 105     }, {
 106         'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 107         'only_matching': True,
 108     }, {
 109         'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 110         'only_matching': True,
 111     }, {
 112         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 113         'only_matching': True,
 114     }, {
 115         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 116         'only_matching': True,
 117     }, {
 118         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
 119         'only_matching': True,
 120     }]
 121
 122     def _real_extract(self, url):
 123         mobj = re.match(self._VALID_URL, url)
 124         video_id = mobj.group('id') or mobj.group('id_2')
 125         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 126
 127         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 128         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 129
 130         error = self._html_search_regex(
 131             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 132             webpage, 'error', default=None)
 133         if error:
 134             raise ExtractorError(error, expected=True)
 135
 136         age_limit = self._rta_search(webpage)
 137
 138         def get_height(s):
 139             return int_or_none(self._search_regex(
 140                 r'^(\d+)[pP]', s, 'height', default=None))
 141
 142         initials = self._parse_json(
 143             self._search_regex(
 144                 (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
 145                  r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
 146                 default='{}'),
 147             video_id, fatal=False)
 148         if initials:
 149             video = initials['videoModel']
 150             title = video['title']
 151             formats = []
 152             format_urls = set()
 153             format_sizes = {}
 154             sources = try_get(video, lambda x: x['sources'], dict) or {}
 155             for format_id, formats_dict in sources.items():
 156                 if not isinstance(formats_dict, dict):
 157                     continue
 158                 download_sources = try_get(sources, lambda x: x['download'], dict) or {}
 159                 for quality, format_dict in download_sources.items():
 160                     if not isinstance(format_dict, dict):
 161                         continue
 162                     format_sizes[quality] = float_or_none(format_dict.get('size'))
 163                 for quality, format_item in formats_dict.items():
 164                     if format_id == 'download':
 165                         # Download link takes some time to be generated,
 166                         # skipping for now
 167                         continue
 168                     format_url = format_item
 169                     format_url = url_or_none(format_url)
 170                     if not format_url or format_url in format_urls:
 171                         continue
 172                     format_urls.add(format_url)
 173                     formats.append({
 174                         'format_id': '%s-%s' % (format_id, quality),
 175                         'url': format_url,
 176                         'ext': determine_ext(format_url, 'mp4'),
 177                         'height': get_height(quality),
 178                         'filesize': format_sizes.get(quality),
 179                         'http_headers': {
 180                             'Referer': urlh.geturl(),
 181                         },
 182                     })
 183             xplayer_sources = try_get(
 184                 initials, lambda x: x['xplayerSettings']['sources'], dict)
 185             if xplayer_sources:
 186                 hls_sources = xplayer_sources.get('hls')
 187                 if isinstance(hls_sources, dict):
 188                     for hls_format_key in ('url', 'fallback'):
 189                         hls_url = hls_sources.get(hls_format_key)
 190                         if not hls_url:
 191                             continue
 192                         hls_url = urljoin(url, hls_url)
 193                         if not hls_url or hls_url in format_urls:
 194                             continue
 195                         format_urls.add(hls_url)
 196                         formats.extend(self._extract_m3u8_formats(
 197                             hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 198                             m3u8_id='hls', fatal=False))
 199                 standard_sources = xplayer_sources.get('standard')
 200                 if isinstance(standard_sources, dict):
 201                     for format_id, formats_list in standard_sources.items():
 202                         if not isinstance(formats_list, list):
 203                             continue
 204                         for standard_format in formats_list:
 205                             if not isinstance(standard_format, dict):
 206                                 continue
 207                             for standard_format_key in ('url', 'fallback'):
 208                                 standard_url = standard_format.get(standard_format_key)
 209                                 if not standard_url:
 210                                     continue
 211                                 standard_url = urljoin(url, standard_url)
 212                                 if not standard_url or standard_url in format_urls:
 213                                     continue
 214                                 format_urls.add(standard_url)
 215                                 ext = determine_ext(standard_url, 'mp4')
 216                                 if ext == 'm3u8':
 217                                     formats.extend(self._extract_m3u8_formats(
 218                                         standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
 219                                         m3u8_id='hls', fatal=False))
 220                                     continue
 221                                 quality = (str_or_none(standard_format.get('quality'))
 222                                            or str_or_none(standard_format.get('label'))
 223                                            or '')
 224                                 formats.append({
 225                                     'format_id': '%s-%s' % (format_id, quality),
 226                                     'url': standard_url,
 227                                     'ext': ext,
 228                                     'height': get_height(quality),
 229                                     'filesize': format_sizes.get(quality),
 230                                     'http_headers': {
 231                                         'Referer': standard_url,
 232                                     },
 233                                 })
 234             self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 235
 236             categories_list = video.get('categories')
 237             if isinstance(categories_list, list):
 238                 categories = []
 239                 for c in categories_list:
 240                     if not isinstance(c, dict):
 241                         continue
 242                     c_name = c.get('name')
 243                     if isinstance(c_name, compat_str):
 244                         categories.append(c_name)
 245             else:
 246                 categories = None
 247
 248             return {
 249                 'id': video_id,
 250                 'display_id': display_id,
 251                 'title': title,
 252                 'description': video.get('description'),
 253                 'timestamp': int_or_none(video.get('created')),
 254                 'uploader': try_get(
 255                     video, lambda x: x['author']['name'], compat_str),
 256                 'thumbnail': video.get('thumbURL'),
 257                 'duration': int_or_none(video.get('duration')),
 258                 'view_count': int_or_none(video.get('views')),
 259                 'like_count': int_or_none(try_get(
 260                     video, lambda x: x['rating']['likes'], int)),
 261                 'dislike_count': int_or_none(try_get(
 262                     video, lambda x: x['rating']['dislikes'], int)),
 263                 'comment_count': int_or_none(video.get('views')),
 264                 'age_limit': age_limit,
 265                 'categories': categories,
 266                 'formats': formats,
 267             }
 268
 269         # Old layout fallback
 270
 271         title = self._html_search_regex(
 272             [r'<h1[^>]*>([^<]+)</h1>',
 273              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 274              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 275             webpage, 'title')
 276
 277         formats = []
 278         format_urls = set()
 279
 280         sources = self._parse_json(
 281             self._search_regex(
 282                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 283                 default='{}'),
 284             video_id, fatal=False)
 285         for format_id, format_url in sources.items():
 286             format_url = url_or_none(format_url)
 287             if not format_url:
 288                 continue
 289             if format_url in format_urls:
 290                 continue
 291             format_urls.add(format_url)
 292             formats.append({
 293                 'format_id': format_id,
 294                 'url': format_url,
 295                 'height': get_height(format_id),
 296             })
 297
 298         video_url = self._search_regex(
 299             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 300              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 301              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 302             webpage, 'video url', group='mp4', default=None)
 303         if video_url and video_url not in format_urls:
 304             formats.append({
 305                 'url': video_url,
 306             })
 307
 308         self._sort_formats(formats)
 309
 310         # Only a few videos have an description
 311         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 312         description = mobj.group(1) if mobj else None
 313
 314         upload_date = unified_strdate(self._search_regex(
 315             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 316             webpage, 'upload date', fatal=False))
 317
 318         uploader = self._html_search_regex(
 319             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 320             webpage, 'uploader', default='anonymous')
 321
 322         thumbnail = self._search_regex(
 323             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 324              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 325             webpage, 'thumbnail', fatal=False, group='thumbnail')
 326
 327         duration = parse_duration(self._search_regex(
 328             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 329              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 330             'duration', fatal=False))
 331
 332         view_count = int_or_none(self._search_regex(
 333             r'content=["\']User(?:View|Play)s:(\d+)',
 334             webpage, 'view count', fatal=False))
 335
 336         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 337         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 338
 339         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 340         comment_count = mobj.group('commentcount') if mobj else 0
 341
 342         categories_html = self._search_regex(
 343             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 344             'categories', default=None)
 345         categories = [clean_html(category) for category in re.findall(
 346             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 347
 348         return {
 349             'id': video_id,
 350             'display_id': display_id,
 351             'title': title,
 352             'description': description,
 353             'upload_date': upload_date,
 354             'uploader': uploader,
 355             'thumbnail': thumbnail,
 356             'duration': duration,
 357             'view_count': view_count,
 358             'like_count': int_or_none(like_count),
 359             'dislike_count': int_or_none(dislike_count),
 360             'comment_count': int_or_none(comment_count),
 361             'age_limit': age_limit,
 362             'categories': categories,
 363             'formats': formats,
 364         }
 365
 366
 367 class XHamsterEmbedIE(InfoExtractor):
 368     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
 369     _TEST = {
 370         'url': 'http://xhamster.com/xembed.php?video=3328539',
 371         'info_dict': {
 372             'id': '3328539',
 373             'ext': 'mp4',
 374             'title': 'Pen Masturbation',
 375             'timestamp': 1406581861,
 376             'upload_date': '20140728',
 377             'uploader': 'ManyakisArt',
 378             'duration': 5,
 379             'age_limit': 18,
 380         }
 381     }
 382
 383     @staticmethod
 384     def _extract_urls(webpage):
 385         return [url for _, url in re.findall(
 386             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 387             webpage)]
 388
 389     def _real_extract(self, url):
 390         video_id = self._match_id(url)
 391
 392         webpage = self._download_webpage(url, video_id)
 393
 394         video_url = self._search_regex(
 395             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 396             webpage, 'xhamster url', default=None)
 397
 398         if not video_url:
 399             vars = self._parse_json(
 400                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 401                 video_id)
 402             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 403
 404         return self.url_result(video_url, 'XHamster')
 405
 406
 407 class XHamsterUserIE(InfoExtractor):
 408     _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
 409     _TESTS = [{
 410         # Paginated user profile
 411         'url': 'https://xhamster.com/users/netvideogirls/videos',
 412         'info_dict': {
 413             'id': 'netvideogirls',
 414         },
 415         'playlist_mincount': 267,
 416     }, {
 417         # Non-paginated user profile
 418         'url': 'https://xhamster.com/users/firatkaan/videos',
 419         'info_dict': {
 420             'id': 'firatkaan',
 421         },
 422         'playlist_mincount': 1,
 423     }]
 424
 425     def _entries(self, user_id):
 426         next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
 427         for pagenum in itertools.count(1):
 428             page = self._download_webpage(
 429                 next_page_url, user_id, 'Downloading page %s' % pagenum)
 430             for video_tag in re.findall(
 431                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
 432                     page):
 433                 video = extract_attributes(video_tag)
 434                 video_url = url_or_none(video.get('href'))
 435                 if not video_url or not XHamsterIE.suitable(video_url):
 436                     continue
 437                 video_id = XHamsterIE._match_id(video_url)
 438                 yield self.url_result(
 439                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
 440             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
 441             if not mobj:
 442                 break
 443             next_page = extract_attributes(mobj.group(0))
 444             next_page_url = url_or_none(next_page.get('href'))
 445             if not next_page_url:
 446                 break
 447
 448     def _real_extract(self, url):
 449         user_id = self._match_id(url)
 450         return self.playlist_result(self._entries(user_id), user_id)