youtube_dl/extractor/xhamster.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_str
   9 from ..utils import (
  10     clean_html,
  11     determine_ext,
  12     dict_get,
  13     extract_attributes,
  14     ExtractorError,
  15     float_or_none,
  16     int_or_none,
  17     parse_duration,
  18     str_or_none,
  19     try_get,
  20     unified_strdate,
  21     url_or_none,
  22     urljoin,
  23 )
  24
  25
  26 class XHamsterIE(InfoExtractor):
  27     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com)'
  28     _VALID_URL = r'''(?x)
  29                     https?://
  30                         (?:.+?\.)?%s/
  31                         (?:
  32                             movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
  33                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
  34                         )
  35                     ''' % _DOMAINS
  36     _TESTS = [{
  37         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  38         'md5': '34e1ab926db5dc2750fed9e1f34304bb',
  39         'info_dict': {
  40             'id': '1509445',
  41             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
  42             'ext': 'mp4',
  43             'title': 'FemaleAgent Shy beauty takes the bait',
  44             'timestamp': 1350194821,
  45             'upload_date': '20121014',
  46             'uploader': 'Ruseful2011',
  47             'uploader_id': 'ruseful2011',
  48             'duration': 893,
  49             'age_limit': 18,
  50         },
  51     }, {
  52         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  53         'info_dict': {
  54             'id': '2221348',
  55             'display_id': 'britney-spears-sexy-booty',
  56             'ext': 'mp4',
  57             'title': 'Britney Spears  Sexy Booty',
  58             'timestamp': 1379123460,
  59             'upload_date': '20130914',
  60             'uploader': 'jojo747400',
  61             'duration': 200,
  62             'age_limit': 18,
  63         },
  64         'params': {
  65             'skip_download': True,
  66         },
  67     }, {
  68         # empty seo, unavailable via new URL schema
  69         'url': 'http://xhamster.com/movies/5667973/.html',
  70         'info_dict': {
  71             'id': '5667973',
  72             'ext': 'mp4',
  73             'title': '....',
  74             'timestamp': 1454948101,
  75             'upload_date': '20160208',
  76             'uploader': 'parejafree',
  77             'uploader_id': 'parejafree',
  78             'duration': 72,
  79             'age_limit': 18,
  80         },
  81         'params': {
  82             'skip_download': True,
  83         },
  84     }, {
  85         # mobile site
  86         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  87         'only_matching': True,
  88     }, {
  89         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  90         'only_matching': True,
  91     }, {
  92         # This video is visible for marcoalfa123456's friends only
  93         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  94         'only_matching': True,
  95     }, {
  96         # new URL schema
  97         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  98         'only_matching': True,
  99     }, {
 100         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 101         'only_matching': True,
 102     }, {
 103         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 104         'only_matching': True,
 105     }, {
 106         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 107         'only_matching': True,
 108     }, {
 109         'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 110         'only_matching': True,
 111     }, {
 112         'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 113         'only_matching': True,
 114     }, {
 115         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 116         'only_matching': True,
 117     }, {
 118         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 119         'only_matching': True,
 120     }, {
 121         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
 122         'only_matching': True,
 123     }, {
 124         'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
 125         'only_matching': True,
 126     }]
 127
 128     def _real_extract(self, url):
 129         mobj = re.match(self._VALID_URL, url)
 130         video_id = mobj.group('id') or mobj.group('id_2')
 131         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 132
 133         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 134         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 135
 136         error = self._html_search_regex(
 137             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 138             webpage, 'error', default=None)
 139         if error:
 140             raise ExtractorError(error, expected=True)
 141
 142         age_limit = self._rta_search(webpage)
 143
 144         def get_height(s):
 145             return int_or_none(self._search_regex(
 146                 r'^(\d+)[pP]', s, 'height', default=None))
 147
 148         initials = self._parse_json(
 149             self._search_regex(
 150                 (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
 151                  r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
 152                 default='{}'),
 153             video_id, fatal=False)
 154         if initials:
 155             video = initials['videoModel']
 156             title = video['title']
 157             formats = []
 158             format_urls = set()
 159             format_sizes = {}
 160             sources = try_get(video, lambda x: x['sources'], dict) or {}
 161             for format_id, formats_dict in sources.items():
 162                 if not isinstance(formats_dict, dict):
 163                     continue
 164                 download_sources = try_get(sources, lambda x: x['download'], dict) or {}
 165                 for quality, format_dict in download_sources.items():
 166                     if not isinstance(format_dict, dict):
 167                         continue
 168                     format_sizes[quality] = float_or_none(format_dict.get('size'))
 169                 for quality, format_item in formats_dict.items():
 170                     if format_id == 'download':
 171                         # Download link takes some time to be generated,
 172                         # skipping for now
 173                         continue
 174                     format_url = format_item
 175                     format_url = url_or_none(format_url)
 176                     if not format_url or format_url in format_urls:
 177                         continue
 178                     format_urls.add(format_url)
 179                     formats.append({
 180                         'format_id': '%s-%s' % (format_id, quality),
 181                         'url': format_url,
 182                         'ext': determine_ext(format_url, 'mp4'),
 183                         'height': get_height(quality),
 184                         'filesize': format_sizes.get(quality),
 185                         'http_headers': {
 186                             'Referer': urlh.geturl(),
 187                         },
 188                     })
 189             xplayer_sources = try_get(
 190                 initials, lambda x: x['xplayerSettings']['sources'], dict)
 191             if xplayer_sources:
 192                 hls_sources = xplayer_sources.get('hls')
 193                 if isinstance(hls_sources, dict):
 194                     for hls_format_key in ('url', 'fallback'):
 195                         hls_url = hls_sources.get(hls_format_key)
 196                         if not hls_url:
 197                             continue
 198                         hls_url = urljoin(url, hls_url)
 199                         if not hls_url or hls_url in format_urls:
 200                             continue
 201                         format_urls.add(hls_url)
 202                         formats.extend(self._extract_m3u8_formats(
 203                             hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 204                             m3u8_id='hls', fatal=False))
 205                 standard_sources = xplayer_sources.get('standard')
 206                 if isinstance(standard_sources, dict):
 207                     for format_id, formats_list in standard_sources.items():
 208                         if not isinstance(formats_list, list):
 209                             continue
 210                         for standard_format in formats_list:
 211                             if not isinstance(standard_format, dict):
 212                                 continue
 213                             for standard_format_key in ('url', 'fallback'):
 214                                 standard_url = standard_format.get(standard_format_key)
 215                                 if not standard_url:
 216                                     continue
 217                                 standard_url = urljoin(url, standard_url)
 218                                 if not standard_url or standard_url in format_urls:
 219                                     continue
 220                                 format_urls.add(standard_url)
 221                                 ext = determine_ext(standard_url, 'mp4')
 222                                 if ext == 'm3u8':
 223                                     formats.extend(self._extract_m3u8_formats(
 224                                         standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
 225                                         m3u8_id='hls', fatal=False))
 226                                     continue
 227                                 quality = (str_or_none(standard_format.get('quality'))
 228                                            or str_or_none(standard_format.get('label'))
 229                                            or '')
 230                                 formats.append({
 231                                     'format_id': '%s-%s' % (format_id, quality),
 232                                     'url': standard_url,
 233                                     'ext': ext,
 234                                     'height': get_height(quality),
 235                                     'filesize': format_sizes.get(quality),
 236                                     'http_headers': {
 237                                         'Referer': standard_url,
 238                                     },
 239                                 })
 240             self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 241
 242             categories_list = video.get('categories')
 243             if isinstance(categories_list, list):
 244                 categories = []
 245                 for c in categories_list:
 246                     if not isinstance(c, dict):
 247                         continue
 248                     c_name = c.get('name')
 249                     if isinstance(c_name, compat_str):
 250                         categories.append(c_name)
 251             else:
 252                 categories = None
 253
 254             uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
 255             return {
 256                 'id': video_id,
 257                 'display_id': display_id,
 258                 'title': title,
 259                 'description': video.get('description'),
 260                 'timestamp': int_or_none(video.get('created')),
 261                 'uploader': try_get(
 262                     video, lambda x: x['author']['name'], compat_str),
 263                 'uploader_url': uploader_url,
 264                 'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
 265                 'thumbnail': video.get('thumbURL'),
 266                 'duration': int_or_none(video.get('duration')),
 267                 'view_count': int_or_none(video.get('views')),
 268                 'like_count': int_or_none(try_get(
 269                     video, lambda x: x['rating']['likes'], int)),
 270                 'dislike_count': int_or_none(try_get(
 271                     video, lambda x: x['rating']['dislikes'], int)),
 272                 'comment_count': int_or_none(video.get('views')),
 273                 'age_limit': age_limit if age_limit is not None else 18,
 274                 'categories': categories,
 275                 'formats': formats,
 276             }
 277
 278         # Old layout fallback
 279
 280         title = self._html_search_regex(
 281             [r'<h1[^>]*>([^<]+)</h1>',
 282              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 283              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 284             webpage, 'title')
 285
 286         formats = []
 287         format_urls = set()
 288
 289         sources = self._parse_json(
 290             self._search_regex(
 291                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 292                 default='{}'),
 293             video_id, fatal=False)
 294         for format_id, format_url in sources.items():
 295             format_url = url_or_none(format_url)
 296             if not format_url:
 297                 continue
 298             if format_url in format_urls:
 299                 continue
 300             format_urls.add(format_url)
 301             formats.append({
 302                 'format_id': format_id,
 303                 'url': format_url,
 304                 'height': get_height(format_id),
 305             })
 306
 307         video_url = self._search_regex(
 308             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 309              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 310              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 311             webpage, 'video url', group='mp4', default=None)
 312         if video_url and video_url not in format_urls:
 313             formats.append({
 314                 'url': video_url,
 315             })
 316
 317         self._sort_formats(formats)
 318
 319         # Only a few videos have an description
 320         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 321         description = mobj.group(1) if mobj else None
 322
 323         upload_date = unified_strdate(self._search_regex(
 324             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 325             webpage, 'upload date', fatal=False))
 326
 327         uploader = self._html_search_regex(
 328             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 329             webpage, 'uploader', default='anonymous')
 330
 331         thumbnail = self._search_regex(
 332             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 333              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 334             webpage, 'thumbnail', fatal=False, group='thumbnail')
 335
 336         duration = parse_duration(self._search_regex(
 337             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 338              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 339             'duration', fatal=False))
 340
 341         view_count = int_or_none(self._search_regex(
 342             r'content=["\']User(?:View|Play)s:(\d+)',
 343             webpage, 'view count', fatal=False))
 344
 345         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 346         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 347
 348         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 349         comment_count = mobj.group('commentcount') if mobj else 0
 350
 351         categories_html = self._search_regex(
 352             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 353             'categories', default=None)
 354         categories = [clean_html(category) for category in re.findall(
 355             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 356
 357         return {
 358             'id': video_id,
 359             'display_id': display_id,
 360             'title': title,
 361             'description': description,
 362             'upload_date': upload_date,
 363             'uploader': uploader,
 364             'uploader_id': uploader.lower() if uploader else None,
 365             'thumbnail': thumbnail,
 366             'duration': duration,
 367             'view_count': view_count,
 368             'like_count': int_or_none(like_count),
 369             'dislike_count': int_or_none(dislike_count),
 370             'comment_count': int_or_none(comment_count),
 371             'age_limit': age_limit,
 372             'categories': categories,
 373             'formats': formats,
 374         }
 375
 376
 377 class XHamsterEmbedIE(InfoExtractor):
 378     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
 379     _TEST = {
 380         'url': 'http://xhamster.com/xembed.php?video=3328539',
 381         'info_dict': {
 382             'id': '3328539',
 383             'ext': 'mp4',
 384             'title': 'Pen Masturbation',
 385             'timestamp': 1406581861,
 386             'upload_date': '20140728',
 387             'uploader': 'ManyakisArt',
 388             'duration': 5,
 389             'age_limit': 18,
 390         }
 391     }
 392
 393     @staticmethod
 394     def _extract_urls(webpage):
 395         return [url for _, url in re.findall(
 396             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 397             webpage)]
 398
 399     def _real_extract(self, url):
 400         video_id = self._match_id(url)
 401
 402         webpage = self._download_webpage(url, video_id)
 403
 404         video_url = self._search_regex(
 405             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 406             webpage, 'xhamster url', default=None)
 407
 408         if not video_url:
 409             vars = self._parse_json(
 410                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 411                 video_id)
 412             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 413
 414         return self.url_result(video_url, 'XHamster')
 415
 416
 417 class XHamsterUserIE(InfoExtractor):
 418     _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
 419     _TESTS = [{
 420         # Paginated user profile
 421         'url': 'https://xhamster.com/users/netvideogirls/videos',
 422         'info_dict': {
 423             'id': 'netvideogirls',
 424         },
 425         'playlist_mincount': 267,
 426     }, {
 427         # Non-paginated user profile
 428         'url': 'https://xhamster.com/users/firatkaan/videos',
 429         'info_dict': {
 430             'id': 'firatkaan',
 431         },
 432         'playlist_mincount': 1,
 433     }, {
 434         'url': 'https://xhday.com/users/mobhunter',
 435         'only_matching': True,
 436     }]
 437
 438     def _entries(self, user_id):
 439         next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
 440         for pagenum in itertools.count(1):
 441             page = self._download_webpage(
 442                 next_page_url, user_id, 'Downloading page %s' % pagenum)
 443             for video_tag in re.findall(
 444                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
 445                     page):
 446                 video = extract_attributes(video_tag)
 447                 video_url = url_or_none(video.get('href'))
 448                 if not video_url or not XHamsterIE.suitable(video_url):
 449                     continue
 450                 video_id = XHamsterIE._match_id(video_url)
 451                 yield self.url_result(
 452                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
 453             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
 454             if not mobj:
 455                 break
 456             next_page = extract_attributes(mobj.group(0))
 457             next_page_url = url_or_none(next_page.get('href'))
 458             if not next_page_url:
 459                 break
 460
 461     def _real_extract(self, url):
 462         user_id = self._match_id(url)
 463         return self.playlist_result(self._entries(user_id), user_id)