_ Git - youtube-dl/blob - 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     int_or_none,
  15     parse_duration,
  16     try_get,
  17     unified_strdate,
  18     url_or_none,
  19 )
  20
  21
  22 class XHamsterIE(InfoExtractor):
  23     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
  24     _VALID_URL = r'''(?x)
  25                     https?://
  26                         (?:.+?\.)?%s/
  27                         (?:
  28                             movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
  29                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
  30                         )
  31                     ''' % _DOMAINS
  32     _TESTS = [{
  33         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  34         'md5': '98b4687efb1ffd331c4197854dc09e8f',
  35         'info_dict': {
  36             'id': '1509445',
  37             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
  38             'ext': 'mp4',
  39             'title': 'FemaleAgent Shy beauty takes the bait',
  40             'timestamp': 1350194821,
  41             'upload_date': '20121014',
  42             'uploader': 'Ruseful2011',
  43             'duration': 893,
  44             'age_limit': 18,
  45         },
  46     }, {
  47         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  48         'info_dict': {
  49             'id': '2221348',
  50             'display_id': 'britney-spears-sexy-booty',
  51             'ext': 'mp4',
  52             'title': 'Britney Spears  Sexy Booty',
  53             'timestamp': 1379123460,
  54             'upload_date': '20130914',
  55             'uploader': 'jojo747400',
  56             'duration': 200,
  57             'age_limit': 18,
  58         },
  59         'params': {
  60             'skip_download': True,
  61         },
  62     }, {
  63         # empty seo, unavailable via new URL schema
  64         'url': 'http://xhamster.com/movies/5667973/.html',
  65         'info_dict': {
  66             'id': '5667973',
  67             'ext': 'mp4',
  68             'title': '....',
  69             'timestamp': 1454948101,
  70             'upload_date': '20160208',
  71             'uploader': 'parejafree',
  72             'duration': 72,
  73             'age_limit': 18,
  74         },
  75         'params': {
  76             'skip_download': True,
  77         },
  78     }, {
  79         # mobile site
  80         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  81         'only_matching': True,
  82     }, {
  83         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  84         'only_matching': True,
  85     }, {
  86         # This video is visible for marcoalfa123456's friends only
  87         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  88         'only_matching': True,
  89     }, {
  90         # new URL schema
  91         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  92         'only_matching': True,
  93     }, {
  94         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  95         'only_matching': True,
  96     }, {
  97         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  98         'only_matching': True,
  99     }, {
 100         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
 101         'only_matching': True,
 102     }, {
 103         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
 104         'only_matching': True,
 105     }, {
 106         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
 107         'only_matching': True,
 108     }]
 109
 110     def _real_extract(self, url):
 111         mobj = re.match(self._VALID_URL, url)
 112         video_id = mobj.group('id') or mobj.group('id_2')
 113         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 114
 115         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 116         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 117
 118         error = self._html_search_regex(
 119             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 120             webpage, 'error', default=None)
 121         if error:
 122             raise ExtractorError(error, expected=True)
 123
 124         age_limit = self._rta_search(webpage)
 125
 126         def get_height(s):
 127             return int_or_none(self._search_regex(
 128                 r'^(\d+)[pP]', s, 'height', default=None))
 129
 130         initials = self._parse_json(
 131             self._search_regex(
 132                 r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
 133                 default='{}'),
 134             video_id, fatal=False)
 135         if initials:
 136             video = initials['videoModel']
 137             title = video['title']
 138             formats = []
 139             for format_id, formats_dict in video['sources'].items():
 140                 if not isinstance(formats_dict, dict):
 141                     continue
 142                 for quality, format_item in formats_dict.items():
 143                     if format_id == 'download':
 144                         # Download link takes some time to be generated,
 145                         # skipping for now
 146                         continue
 147                         if not isinstance(format_item, dict):
 148                             continue
 149                         format_url = format_item.get('link')
 150                         filesize = int_or_none(
 151                             format_item.get('size'), invscale=1000000)
 152                     else:
 153                         format_url = format_item
 154                         filesize = None
 155                     format_url = url_or_none(format_url)
 156                     if not format_url:
 157                         continue
 158                     formats.append({
 159                         'format_id': '%s-%s' % (format_id, quality),
 160                         'url': format_url,
 161                         'ext': determine_ext(format_url, 'mp4'),
 162                         'height': get_height(quality),
 163                         'filesize': filesize,
 164                         'http_headers': {
 165                             'Referer': urlh.geturl(),
 166                         },
 167                     })
 168             self._sort_formats(formats)
 169
 170             categories_list = video.get('categories')
 171             if isinstance(categories_list, list):
 172                 categories = []
 173                 for c in categories_list:
 174                     if not isinstance(c, dict):
 175                         continue
 176                     c_name = c.get('name')
 177                     if isinstance(c_name, compat_str):
 178                         categories.append(c_name)
 179             else:
 180                 categories = None
 181
 182             return {
 183                 'id': video_id,
 184                 'display_id': display_id,
 185                 'title': title,
 186                 'description': video.get('description'),
 187                 'timestamp': int_or_none(video.get('created')),
 188                 'uploader': try_get(
 189                     video, lambda x: x['author']['name'], compat_str),
 190                 'thumbnail': video.get('thumbURL'),
 191                 'duration': int_or_none(video.get('duration')),
 192                 'view_count': int_or_none(video.get('views')),
 193                 'like_count': int_or_none(try_get(
 194                     video, lambda x: x['rating']['likes'], int)),
 195                 'dislike_count': int_or_none(try_get(
 196                     video, lambda x: x['rating']['dislikes'], int)),
 197                 'comment_count': int_or_none(video.get('views')),
 198                 'age_limit': age_limit,
 199                 'categories': categories,
 200                 'formats': formats,
 201             }
 202
 203         # Old layout fallback
 204
 205         title = self._html_search_regex(
 206             [r'<h1[^>]*>([^<]+)</h1>',
 207              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 208              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 209             webpage, 'title')
 210
 211         formats = []
 212         format_urls = set()
 213
 214         sources = self._parse_json(
 215             self._search_regex(
 216                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 217                 default='{}'),
 218             video_id, fatal=False)
 219         for format_id, format_url in sources.items():
 220             format_url = url_or_none(format_url)
 221             if not format_url:
 222                 continue
 223             if format_url in format_urls:
 224                 continue
 225             format_urls.add(format_url)
 226             formats.append({
 227                 'format_id': format_id,
 228                 'url': format_url,
 229                 'height': get_height(format_id),
 230             })
 231
 232         video_url = self._search_regex(
 233             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 234              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 235              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 236             webpage, 'video url', group='mp4', default=None)
 237         if video_url and video_url not in format_urls:
 238             formats.append({
 239                 'url': video_url,
 240             })
 241
 242         self._sort_formats(formats)
 243
 244         # Only a few videos have an description
 245         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 246         description = mobj.group(1) if mobj else None
 247
 248         upload_date = unified_strdate(self._search_regex(
 249             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 250             webpage, 'upload date', fatal=False))
 251
 252         uploader = self._html_search_regex(
 253             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 254             webpage, 'uploader', default='anonymous')
 255
 256         thumbnail = self._search_regex(
 257             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 258              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 259             webpage, 'thumbnail', fatal=False, group='thumbnail')
 260
 261         duration = parse_duration(self._search_regex(
 262             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 263              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 264             'duration', fatal=False))
 265
 266         view_count = int_or_none(self._search_regex(
 267             r'content=["\']User(?:View|Play)s:(\d+)',
 268             webpage, 'view count', fatal=False))
 269
 270         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 271         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 272
 273         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 274         comment_count = mobj.group('commentcount') if mobj else 0
 275
 276         categories_html = self._search_regex(
 277             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 278             'categories', default=None)
 279         categories = [clean_html(category) for category in re.findall(
 280             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 281
 282         return {
 283             'id': video_id,
 284             'display_id': display_id,
 285             'title': title,
 286             'description': description,
 287             'upload_date': upload_date,
 288             'uploader': uploader,
 289             'thumbnail': thumbnail,
 290             'duration': duration,
 291             'view_count': view_count,
 292             'like_count': int_or_none(like_count),
 293             'dislike_count': int_or_none(dislike_count),
 294             'comment_count': int_or_none(comment_count),
 295             'age_limit': age_limit,
 296             'categories': categories,
 297             'formats': formats,
 298         }
 299
 300
 301 class XHamsterEmbedIE(InfoExtractor):
 302     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
 303     _TEST = {
 304         'url': 'http://xhamster.com/xembed.php?video=3328539',
 305         'info_dict': {
 306             'id': '3328539',
 307             'ext': 'mp4',
 308             'title': 'Pen Masturbation',
 309             'timestamp': 1406581861,
 310             'upload_date': '20140728',
 311             'uploader': 'ManyakisArt',
 312             'duration': 5,
 313             'age_limit': 18,
 314         }
 315     }
 316
 317     @staticmethod
 318     def _extract_urls(webpage):
 319         return [url for _, url in re.findall(
 320             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 321             webpage)]
 322
 323     def _real_extract(self, url):
 324         video_id = self._match_id(url)
 325
 326         webpage = self._download_webpage(url, video_id)
 327
 328         video_url = self._search_regex(
 329             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 330             webpage, 'xhamster url', default=None)
 331
 332         if not video_url:
 333             vars = self._parse_json(
 334                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 335                 video_id)
 336             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 337
 338         return self.url_result(video_url, 'XHamster')
 339
 340
 341 class XHamsterUserIE(InfoExtractor):
 342     _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
 343     _TESTS = [{
 344         # Paginated user profile
 345         'url': 'https://xhamster.com/users/netvideogirls/videos',
 346         'info_dict': {
 347             'id': 'netvideogirls',
 348         },
 349         'playlist_mincount': 267,
 350     }, {
 351         # Non-paginated user profile
 352         'url': 'https://xhamster.com/users/firatkaan/videos',
 353         'info_dict': {
 354             'id': 'firatkaan',
 355         },
 356         'playlist_mincount': 1,
 357     }]
 358
 359     def _entries(self, user_id):
 360         next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
 361         for pagenum in itertools.count(1):
 362             page = self._download_webpage(
 363                 next_page_url, user_id, 'Downloading page %s' % pagenum)
 364             for video_tag in re.findall(
 365                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
 366                     page):
 367                 video = extract_attributes(video_tag)
 368                 video_url = url_or_none(video.get('href'))
 369                 if not video_url or not XHamsterIE.suitable(video_url):
 370                     continue
 371                 video_id = XHamsterIE._match_id(video_url)
 372                 yield self.url_result(
 373                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
 374             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
 375             if not mobj:
 376                 break
 377             next_page = extract_attributes(mobj.group(0))
 378             next_page_url = url_or_none(next_page.get('href'))
 379             if not next_page_url:
 380                 break
 381
 382     def _real_extract(self, url):
 383         user_id = self._match_id(url)
 384         return self.playlist_result(self._entries(user_id), user_id)