Raphaël G. Git Repositories - youtubedl/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     dict_get,
  10     ExtractorError,
  11     int_or_none,
  12     parse_duration,
  13     unified_strdate,
  14 )
  15
  16
  17 class XHamsterIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)
  19                     https?://
  20                         (?:.+?\.)?xhamster\.com/
  21                         (?:
  22                             movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
  23                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
  24                         )
  25                     '''
  26
  27     _TESTS = [{
  28         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  29         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  30         'info_dict': {
  31             'id': '1509445',
  32             'display_id': 'femaleagent_shy_beauty_takes_the_bait',
  33             'ext': 'mp4',
  34             'title': 'FemaleAgent Shy beauty takes the bait',
  35             'upload_date': '20121014',
  36             'uploader': 'Ruseful2011',
  37             'duration': 893,
  38             'age_limit': 18,
  39             'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
  40         },
  41     }, {
  42         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  43         'info_dict': {
  44             'id': '2221348',
  45             'display_id': 'britney_spears_sexy_booty',
  46             'ext': 'mp4',
  47             'title': 'Britney Spears  Sexy Booty',
  48             'upload_date': '20130914',
  49             'uploader': 'jojo747400',
  50             'duration': 200,
  51             'age_limit': 18,
  52             'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
  53         },
  54         'params': {
  55             'skip_download': True,
  56         },
  57     }, {
  58         # empty seo
  59         'url': 'http://xhamster.com/movies/5667973/.html',
  60         'info_dict': {
  61             'id': '5667973',
  62             'ext': 'mp4',
  63             'title': '....',
  64             'upload_date': '20160208',
  65             'uploader': 'parejafree',
  66             'duration': 72,
  67             'age_limit': 18,
  68             'categories': ['Amateur', 'Blowjobs'],
  69         },
  70         'params': {
  71             'skip_download': True,
  72         },
  73     }, {
  74         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  75         'only_matching': True,
  76     }, {
  77         # This video is visible for marcoalfa123456's friends only
  78         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  79         'only_matching': True,
  80     }, {
  81         # new URL schema
  82         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  83         'only_matching': True,
  84     }]
  85
  86     def _real_extract(self, url):
  87         mobj = re.match(self._VALID_URL, url)
  88         video_id = mobj.group('id') or mobj.group('id_2')
  89         display_id = mobj.group('display_id') or mobj.group('display_id_2')
  90
  91         webpage = self._download_webpage(url, video_id)
  92
  93         error = self._html_search_regex(
  94             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
  95             webpage, 'error', default=None)
  96         if error:
  97             raise ExtractorError(error, expected=True)
  98
  99         title = self._html_search_regex(
 100             [r'<h1[^>]*>([^<]+)</h1>',
 101              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
 102              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
 103             webpage, 'title')
 104
 105         formats = []
 106         format_urls = set()
 107
 108         sources = self._parse_json(
 109             self._search_regex(
 110                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
 111                 default='{}'),
 112             video_id, fatal=False)
 113         for format_id, format_url in sources.items():
 114             if not isinstance(format_url, compat_str):
 115                 continue
 116             if format_url in format_urls:
 117                 continue
 118             format_urls.add(format_url)
 119             formats.append({
 120                 'format_id': format_id,
 121                 'url': format_url,
 122                 'height': int_or_none(self._search_regex(
 123                     r'^(\d+)[pP]', format_id, 'height', default=None))
 124             })
 125
 126         video_url = self._search_regex(
 127             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
 128              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
 129              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
 130             webpage, 'video url', group='mp4', default=None)
 131         if video_url and video_url not in format_urls:
 132             formats.append({
 133                 'url': video_url,
 134             })
 135
 136         self._sort_formats(formats)
 137
 138         # Only a few videos have an description
 139         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 140         description = mobj.group(1) if mobj else None
 141
 142         upload_date = unified_strdate(self._search_regex(
 143             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 144             webpage, 'upload date', fatal=False))
 145
 146         uploader = self._html_search_regex(
 147             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
 148             webpage, 'uploader', default='anonymous')
 149
 150         thumbnail = self._search_regex(
 151             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 152              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 153             webpage, 'thumbnail', fatal=False, group='thumbnail')
 154
 155         duration = parse_duration(self._search_regex(
 156             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
 157              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
 158             'duration', fatal=False))
 159
 160         view_count = int_or_none(self._search_regex(
 161             r'content=["\']User(?:View|Play)s:(\d+)',
 162             webpage, 'view count', fatal=False))
 163
 164         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
 165         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 166
 167         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 168         comment_count = mobj.group('commentcount') if mobj else 0
 169
 170         age_limit = self._rta_search(webpage)
 171
 172         categories_html = self._search_regex(
 173             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
 174             'categories', default=None)
 175         categories = [clean_html(category) for category in re.findall(
 176             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
 177
 178         return {
 179             'id': video_id,
 180             'display_id': display_id,
 181             'title': title,
 182             'description': description,
 183             'upload_date': upload_date,
 184             'uploader': uploader,
 185             'thumbnail': thumbnail,
 186             'duration': duration,
 187             'view_count': view_count,
 188             'like_count': int_or_none(like_count),
 189             'dislike_count': int_or_none(dislike_count),
 190             'comment_count': int_or_none(comment_count),
 191             'age_limit': age_limit,
 192             'categories': categories,
 193             'formats': formats,
 194         }
 195
 196
 197 class XHamsterEmbedIE(InfoExtractor):
 198     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 199     _TEST = {
 200         'url': 'http://xhamster.com/xembed.php?video=3328539',
 201         'info_dict': {
 202             'id': '3328539',
 203             'ext': 'mp4',
 204             'title': 'Pen Masturbation',
 205             'upload_date': '20140728',
 206             'uploader_id': 'anonymous',
 207             'duration': 5,
 208             'age_limit': 18,
 209         }
 210     }
 211
 212     @staticmethod
 213     def _extract_urls(webpage):
 214         return [url for _, url in re.findall(
 215             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 216             webpage)]
 217
 218     def _real_extract(self, url):
 219         video_id = self._match_id(url)
 220
 221         webpage = self._download_webpage(url, video_id)
 222
 223         video_url = self._search_regex(
 224             r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
 225             webpage, 'xhamster url', default=None)
 226
 227         if not video_url:
 228             vars = self._parse_json(
 229                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 230                 video_id)
 231             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 232
 233         return self.url_result(video_url, 'XHamster')