_ 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 )
  17
  18
  19 class XHamsterIE(InfoExtractor):
  20     _VALID_URL = r'''(?x)
  21                     https?://
  22                         (?:.+?\.)?xhamster\.com/
  23                         (?:
  24                             movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
  25                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
  26                         )
  27                     '''
  28
  29     _TESTS = [{
  30         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  31         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  32         'info_dict': {
  33             'id': '1509445',
  34             'display_id': 'femaleagent_shy_beauty_takes_the_bait',
  35             'ext': 'mp4',
  36             'title': 'FemaleAgent Shy beauty takes the bait',
  37             'timestamp': 1350194821,
  38             'upload_date': '20121014',
  39             'uploader': 'Ruseful2011',
  40             'duration': 893,
  41             'age_limit': 18,
  42             'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
  43         },
  44     }, {
  45         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  46         'info_dict': {
  47             'id': '2221348',
  48             'display_id': 'britney_spears_sexy_booty',
  49             'ext': 'mp4',
  50             'title': 'Britney Spears  Sexy Booty',
  51             'timestamp': 1379123460,
  52             'upload_date': '20130914',
  53             'uploader': 'jojo747400',
  54             'duration': 200,
  55             'age_limit': 18,
  56             'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
  57         },
  58         'params': {
  59             'skip_download': True,
  60         },
  61     }, {
  62         # empty seo
  63         'url': 'http://xhamster.com/movies/5667973/.html',
  64         'info_dict': {
  65             'id': '5667973',
  66             'ext': 'mp4',
  67             'title': '....',
  68             'timestamp': 1454948101,
  69             'upload_date': '20160208',
  70             'uploader': 'parejafree',
  71             'duration': 72,
  72             'age_limit': 18,
  73             'categories': ['Amateur', 'Blowjobs'],
  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
  95     def _real_extract(self, url):
  96         mobj = re.match(self._VALID_URL, url)
  97         video_id = mobj.group('id') or mobj.group('id_2')
  98         display_id = mobj.group('display_id') or mobj.group('display_id_2')
  99
 100         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
 101         webpage = self._download_webpage(desktop_url, video_id)
 102
 103         error = self._html_search_regex(
 104             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
 105             webpage, 'error', default=None)
 106         if error:
 107             raise ExtractorError(error, expected=True)
 108
 109         age_limit = self._rta_search(webpage)
 110
 111         def get_height(s):
 112             return int_or_none(self._search_regex(
 113                 r'^(\d+)[pP]', s, 'height', default=None))
 114
 115         initials = self._parse_json(
 116             self._search_regex(
 117                 r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
 118                 default='{}'),
 119             video_id, fatal=False)
 120         if initials:
 121             video = initials['videoModel']
 122             title = video['title']
 123             formats = []
 124             for format_id, formats_dict in video['sources'].items():
 125                 if not isinstance(formats_dict, dict):
 126                     continue
 127                 for quality, format_item in formats_dict.items():
 128                     if format_id == 'download':
 129                         # Download link takes some time to be generated,
 130                         # skipping for now
 131                         continue
 132                         if not isinstance(format_item, dict):
 133                             continue
 134                         format_url = format_item.get('link')
 135                         filesize = int_or_none(
 136                             format_item.get('size'), invscale=1000000)
 137                     else:
 138                         format_url = format_item
 139                         filesize = None
 140                     if not isinstance(format_url, compat_str):
 141                         continue
 142                     formats.append({
 143                         'format_id': '%s-%s' % (format_id, quality),
 144                         'url': format_url,
 145                         'ext': determine_ext(format_url, 'mp4'),
 146                         'height': get_height(quality),
 147                         'filesize': filesize,
 148                     })
 149             self._sort_formats(formats)
 150
 151             categories_list = video.get('categories')
 152             if isinstance(categories_list, list):
 153                 categories = []
 154                 for c in categories_list:
 155                     if not isinstance(c, dict):
 156                         continue
 157                     c_name = c.get('name')
 158                     if isinstance(c_name, compat_str):
 159                         categories.append(c_name)
 160             else:
 161                 categories = None
 162
 163             return {
 164                 'id': video_id,
 165                 'display_id': display_id,
 166                 'title': title,
 167                 'description': video.get('description'),
 168                 'timestamp': int_or_none(video.get('created')),
 169                 'uploader': try_get(
 170                     video, lambda x: x['author']['name'], compat_str),
 171                 'thumbnail': video.get('thumbURL'),
 172                 'duration': int_or_none(video.get('duration')),
 173                 'view_count': int_or_none(video.get('views')),
 174                 'like_count': int_or_none(try_get(
 175                     video, lambda x: x['rating']['likes'], int)),
 176                 'dislike_count': int_or_none(try_get(
 177                     video, lambda x: x['rating']['dislikes'], int)),
 178                 'comment_count': int_or_none(video.get('views')),
 179                 'age_limit': age_limit,
 180                 'categories': categories,
 181                 'formats': formats,
 182             }
 183
 184         # Old layout fallback
 185
 186         title = self._html_search_regex(
 187             [r'<h1[^>]*>([^<]+)</h1>',
 188              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 189              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 190             webpage, 'title')
 191
 192         formats = []
 193         format_urls = set()
 194
 195         sources = self._parse_json(
 196             self._search_regex(
 197                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 198                 default='{}'),
 199             video_id, fatal=False)
 200         for format_id, format_url in sources.items():
 201             if not isinstance(format_url, compat_str):
 202                 continue
 203             if format_url in format_urls:
 204                 continue
 205             format_urls.add(format_url)
 206             formats.append({
 207                 'format_id': format_id,
 208                 'url': format_url,
 209                 'height': get_height(format_id),
 210             })
 211
 212         video_url = self._search_regex(
 213             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 214              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 215              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 216             webpage, 'video url', group='mp4', default=None)
 217         if video_url and video_url not in format_urls:
 218             formats.append({
 219                 'url': video_url,
 220             })
 221
 222         self._sort_formats(formats)
 223
 224         # Only a few videos have an description
 225         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 226         description = mobj.group(1) if mobj else None
 227
 228         upload_date = unified_strdate(self._search_regex(
 229             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 230             webpage, 'upload date', fatal=False))
 231
 232         uploader = self._html_search_regex(
 233             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 234             webpage, 'uploader', default='anonymous')
 235
 236         thumbnail = self._search_regex(
 237             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 238              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 239             webpage, 'thumbnail', fatal=False, group='thumbnail')
 240
 241         duration = parse_duration(self._search_regex(
 242             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 243              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 244             'duration', fatal=False))
 245
 246         view_count = int_or_none(self._search_regex(
 247             r'content=["\']User(?:View|Play)s:(\d+)',
 248             webpage, 'view count', fatal=False))
 249
 250         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 251         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 252
 253         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 254         comment_count = mobj.group('commentcount') if mobj else 0
 255
 256         categories_html = self._search_regex(
 257             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 258             'categories', default=None)
 259         categories = [clean_html(category) for category in re.findall(
 260             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 261
 262         return {
 263             'id': video_id,
 264             'display_id': display_id,
 265             'title': title,
 266             'description': description,
 267             'upload_date': upload_date,
 268             'uploader': uploader,
 269             'thumbnail': thumbnail,
 270             'duration': duration,
 271             'view_count': view_count,
 272             'like_count': int_or_none(like_count),
 273             'dislike_count': int_or_none(dislike_count),
 274             'comment_count': int_or_none(comment_count),
 275             'age_limit': age_limit,
 276             'categories': categories,
 277             'formats': formats,
 278         }
 279
 280
 281 class XHamsterEmbedIE(InfoExtractor):
 282     _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 283     _TEST = {
 284         'url': 'http://xhamster.com/xembed.php?video=3328539',
 285         'info_dict': {
 286             'id': '3328539',
 287             'ext': 'mp4',
 288             'title': 'Pen Masturbation',
 289             'timestamp': 1406581861,
 290             'upload_date': '20140728',
 291             'uploader': 'ManyakisArt',
 292             'duration': 5,
 293             'age_limit': 18,
 294         }
 295     }
 296
 297     @staticmethod
 298     def _extract_urls(webpage):
 299         return [url for _, url in re.findall(
 300             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 301             webpage)]
 302
 303     def _real_extract(self, url):
 304         video_id = self._match_id(url)
 305
 306         webpage = self._download_webpage(url, video_id)
 307
 308         video_url = self._search_regex(
 309             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
 310             webpage, 'xhamster url', default=None)
 311
 312         if not video_url:
 313             vars = self._parse_json(
 314                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 315                 video_id)
 316             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 317
 318         return self.url_result(video_url, 'XHamster')