_ Git - youtube-dl/blob - youtube_dl/extractor/xhamster.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     clean_html,
   9     determine_ext,
  10     dict_get,
  11     ExtractorError,
  12     int_or_none,
  13     parse_duration,
  14     try_get,
  15     unified_strdate,
  16     url_or_none,
  17 )
  18
  19
  20 class XHamsterIE(InfoExtractor):
  21     _VALID_URL = r'''(?x)
  22                     https?://
  23                         (?:.+?\.)?xhamster\.(?:com|one)/
  24                         (?:
  25                             movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
  26                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
  27                         )
  28                     '''
  29
  30     _TESTS = [{
  31         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  32         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  33         'info_dict': {
  34             'id': '1509445',
  35             'display_id': 'femaleagent_shy_beauty_takes_the_bait',
  36             'ext': 'mp4',
  37             'title': 'FemaleAgent Shy beauty takes the bait',
  38             'timestamp': 1350194821,
  39             'upload_date': '20121014',
  40             'uploader': 'Ruseful2011',
  41             'duration': 893,
  42             'age_limit': 18,
  43             'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Beauti', 'Beauties', 'Beautiful', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy', 'Taking'],
  44         },
  45     }, {
  46         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  47         'info_dict': {
  48             'id': '2221348',
  49             'display_id': 'britney_spears_sexy_booty',
  50             'ext': 'mp4',
  51             'title': 'Britney Spears  Sexy Booty',
  52             'timestamp': 1379123460,
  53             'upload_date': '20130914',
  54             'uploader': 'jojo747400',
  55             'duration': 200,
  56             'age_limit': 18,
  57             'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
  58         },
  59         'params': {
  60             'skip_download': True,
  61         },
  62     }, {
  63         # empty seo
  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             'categories': ['Amateur', 'Blowjobs'],
  75         },
  76         'params': {
  77             'skip_download': True,
  78         },
  79     }, {
  80         # mobile site
  81         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  82         'only_matching': True,
  83     }, {
  84         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  85         'only_matching': True,
  86     }, {
  87         # This video is visible for marcoalfa123456's friends only
  88         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  89         'only_matching': True,
  90     }, {
  91         # new URL schema
  92         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  93         'only_matching': True,
  94     }, {
  95         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  96         'only_matching': True,
  97     }]
  98
  99     def _real_extract(self, url):
 100         mobj = re.match(self._VALID_URL, url)
 101         video_id = mobj.group('id') or mobj.group('id_2')
 102         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 103
 104         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 105         webpage = self._download_webpage(desktop_url, video_id)
 106
 107         error = self._html_search_regex(
 108             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 109             webpage, 'error', default=None)
 110         if error:
 111             raise ExtractorError(error, expected=True)
 112
 113         age_limit = self._rta_search(webpage)
 114
 115         def get_height(s):
 116             return int_or_none(self._search_regex(
 117                 r'^(\d+)[pP]', s, 'height', default=None))
 118
 119         initials = self._parse_json(
 120             self._search_regex(
 121                 r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
 122                 default='{}'),
 123             video_id, fatal=False)
 124         if initials:
 125             video = initials['videoModel']
 126             title = video['title']
 127             formats = []
 128             for format_id, formats_dict in video['sources'].items():
 129                 if not isinstance(formats_dict, dict):
 130                     continue
 131                 for quality, format_item in formats_dict.items():
 132                     if format_id == 'download':
 133                         # Download link takes some time to be generated,
 134                         # skipping for now
 135                         continue
 136                         if not isinstance(format_item, dict):
 137                             continue
 138                         format_url = format_item.get('link')
 139                         filesize = int_or_none(
 140                             format_item.get('size'), invscale=1000000)
 141                     else:
 142                         format_url = format_item
 143                         filesize = None
 144                     format_url = url_or_none(format_url)
 145                     if not format_url:
 146                         continue
 147                     formats.append({
 148                         'format_id': '%s-%s' % (format_id, quality),
 149                         'url': format_url,
 150                         'ext': determine_ext(format_url, 'mp4'),
 151                         'height': get_height(quality),
 152                         'filesize': filesize,
 153                     })
 154             self._sort_formats(formats)
 155
 156             categories_list = video.get('categories')
 157             if isinstance(categories_list, list):
 158                 categories = []
 159                 for c in categories_list:
 160                     if not isinstance(c, dict):
 161                         continue
 162                     c_name = c.get('name')
 163                     if isinstance(c_name, compat_str):
 164                         categories.append(c_name)
 165             else:
 166                 categories = None
 167
 168             return {
 169                 'id': video_id,
 170                 'display_id': display_id,
 171                 'title': title,
 172                 'description': video.get('description'),
 173                 'timestamp': int_or_none(video.get('created')),
 174                 'uploader': try_get(
 175                     video, lambda x: x['author']['name'], compat_str),
 176                 'thumbnail': video.get('thumbURL'),
 177                 'duration': int_or_none(video.get('duration')),
 178                 'view_count': int_or_none(video.get('views')),
 179                 'like_count': int_or_none(try_get(
 180                     video, lambda x: x['rating']['likes'], int)),
 181                 'dislike_count': int_or_none(try_get(
 182                     video, lambda x: x['rating']['dislikes'], int)),
 183                 'comment_count': int_or_none(video.get('views')),
 184                 'age_limit': age_limit,
 185                 'categories': categories,
 186                 'formats': formats,
 187             }
 188
 189         # Old layout fallback
 190
 191         title = self._html_search_regex(
 192             [r'<h1[^>]*>([^<]+)</h1>',
 193              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 194              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 195             webpage, 'title')
 196
 197         formats = []
 198         format_urls = set()
 199
 200         sources = self._parse_json(
 201             self._search_regex(
 202                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 203                 default='{}'),
 204             video_id, fatal=False)
 205         for format_id, format_url in sources.items():
 206             format_url = url_or_none(format_url)
 207             if not format_url:
 208                 continue
 209             if format_url in format_urls:
 210                 continue
 211             format_urls.add(format_url)
 212             formats.append({
 213                 'format_id': format_id,
 214                 'url': format_url,
 215                 'height': get_height(format_id),
 216             })
 217
 218         video_url = self._search_regex(
 219             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 220              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 221              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 222             webpage, 'video url', group='mp4', default=None)
 223         if video_url and video_url not in format_urls:
 224             formats.append({
 225                 'url': video_url,
 226             })
 227
 228         self._sort_formats(formats)
 229
 230         # Only a few videos have an description
 231         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 232         description = mobj.group(1) if mobj else None
 233
 234         upload_date = unified_strdate(self._search_regex(
 235             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 236             webpage, 'upload date', fatal=False))
 237
 238         uploader = self._html_search_regex(
 239             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 240             webpage, 'uploader', default='anonymous')
 241
 242         thumbnail = self._search_regex(
 243             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 244              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 245             webpage, 'thumbnail', fatal=False, group='thumbnail')
 246
 247         duration = parse_duration(self._search_regex(
 248             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 249              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 250             'duration', fatal=False))
 251
 252         view_count = int_or_none(self._search_regex(
 253             r'content=["\']User(?:View|Play)s:(\d+)',
 254             webpage, 'view count', fatal=False))
 255
 256         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 257         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 258
 259         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 260         comment_count = mobj.group('commentcount') if mobj else 0
 261
 262         categories_html = self._search_regex(
 263             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 264             'categories', default=None)
 265         categories = [clean_html(category) for category in re.findall(
 266             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 267
 268         return {
 269             'id': video_id,
 270             'display_id': display_id,
 271             'title': title,
 272             'description': description,
 273             'upload_date': upload_date,
 274             'uploader': uploader,
 275             'thumbnail': thumbnail,
 276             'duration': duration,
 277             'view_count': view_count,
 278             'like_count': int_or_none(like_count),
 279             'dislike_count': int_or_none(dislike_count),
 280             'comment_count': int_or_none(comment_count),
 281             'age_limit': age_limit,
 282             'categories': categories,
 283             'formats': formats,
 284         }
 285
 286
 287 class XHamsterEmbedIE(InfoExtractor):
 288     _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 289     _TEST = {
 290         'url': 'http://xhamster.com/xembed.php?video=3328539',
 291         'info_dict': {
 292             'id': '3328539',
 293             'ext': 'mp4',
 294             'title': 'Pen Masturbation',
 295             'timestamp': 1406581861,
 296             'upload_date': '20140728',
 297             'uploader': 'ManyakisArt',
 298             'duration': 5,
 299             'age_limit': 18,
 300         }
 301     }
 302
 303     @staticmethod
 304     def _extract_urls(webpage):
 305         return [url for _, url in re.findall(
 306             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 307             webpage)]
 308
 309     def _real_extract(self, url):
 310         video_id = self._match_id(url)
 311
 312         webpage = self._download_webpage(url, video_id)
 313
 314         video_url = self._search_regex(
 315             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 316             webpage, 'xhamster url', default=None)
 317
 318         if not video_url:
 319             vars = self._parse_json(
 320                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 321                 video_id)
 322             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 323
 324         return self.url_result(video_url, 'XHamster')