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 ..utils import (
   7     dict_get,
   8     ExtractorError,
   9     int_or_none,
  10     parse_duration,
  11     unified_strdate,
  12 )
  13
  14
  15 class XHamsterIE(InfoExtractor):
  16     _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
  17     _TESTS = [{
  18         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  19         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  20         'info_dict': {
  21             'id': '1509445',
  22             'ext': 'mp4',
  23             'title': 'FemaleAgent Shy beauty takes the bait',
  24             'upload_date': '20121014',
  25             'uploader': 'Ruseful2011',
  26             'duration': 893,
  27             'age_limit': 18,
  28         },
  29     }, {
  30         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  31         'info_dict': {
  32             'id': '2221348',
  33             'ext': 'mp4',
  34             'title': 'Britney Spears  Sexy Booty',
  35             'upload_date': '20130914',
  36             'uploader': 'jojo747400',
  37             'duration': 200,
  38             'age_limit': 18,
  39         },
  40         'params': {
  41             'skip_download': True,
  42         },
  43     }, {
  44         # empty seo
  45         'url': 'http://xhamster.com/movies/5667973/.html',
  46         'info_dict': {
  47             'id': '5667973',
  48             'ext': 'mp4',
  49             'title': '....',
  50             'upload_date': '20160208',
  51             'uploader': 'parejafree',
  52             'duration': 72,
  53             'age_limit': 18,
  54         },
  55         'params': {
  56             'skip_download': True,
  57         },
  58     }, {
  59         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  60         'only_matching': True,
  61     }, {
  62         # This video is visible for marcoalfa123456's friends only
  63         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  64         'only_matching': True,
  65     }]
  66
  67     def _real_extract(self, url):
  68         def extract_video_url(webpage, name):
  69             return self._search_regex(
  70                 [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  71                  r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  72                  r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  73                 webpage, name, group='mp4')
  74
  75         def is_hd(webpage):
  76             return '<div class=\'icon iconHD\'' in webpage
  77
  78         mobj = re.match(self._VALID_URL, url)
  79
  80         video_id = mobj.group('id')
  81         seo = mobj.group('seo')
  82         proto = mobj.group('proto')
  83         mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
  84         webpage = self._download_webpage(mrss_url, video_id)
  85
  86         error = self._html_search_regex(
  87             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
  88             webpage, 'error', default=None)
  89         if error:
  90             raise ExtractorError(error, expected=True)
  91
  92         title = self._html_search_regex(
  93             [r'<h1[^>]*>([^<]+)</h1>',
  94              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
  95              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
  96             webpage, 'title')
  97
  98         # Only a few videos have an description
  99         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
 100         description = mobj.group(1) if mobj else None
 101
 102         upload_date = unified_strdate(self._search_regex(
 103             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
 104             webpage, 'upload date', fatal=False))
 105
 106         uploader = self._html_search_regex(
 107             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
 108             webpage, 'uploader', default='anonymous')
 109
 110         thumbnail = self._search_regex(
 111             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
 112              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
 113             webpage, 'thumbnail', fatal=False, group='thumbnail')
 114
 115         duration = parse_duration(self._search_regex(
 116             r'Runtime:\s*</span>\s*([\d:]+)', webpage,
 117             'duration', fatal=False))
 118
 119         view_count = int_or_none(self._search_regex(
 120             r'content=["\']User(?:View|Play)s:(\d+)',
 121             webpage, 'view count', fatal=False))
 122
 123         mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
 124         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 125
 126         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
 127         comment_count = mobj.group('commentcount') if mobj else 0
 128
 129         age_limit = self._rta_search(webpage)
 130
 131         hd = is_hd(webpage)
 132
 133         format_id = 'hd' if hd else 'sd'
 134
 135         video_url = extract_video_url(webpage, format_id)
 136         formats = [{
 137             'url': video_url,
 138             'format_id': 'hd' if hd else 'sd',
 139             'preference': 1,
 140         }]
 141
 142         if not hd:
 143             mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
 144             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
 145             if is_hd(webpage):
 146                 video_url = extract_video_url(webpage, 'hd')
 147                 formats.append({
 148                     'url': video_url,
 149                     'format_id': 'hd',
 150                     'preference': 2,
 151                 })
 152
 153         self._sort_formats(formats)
 154
 155         return {
 156             'id': video_id,
 157             'title': title,
 158             'description': description,
 159             'upload_date': upload_date,
 160             'uploader': uploader,
 161             'thumbnail': thumbnail,
 162             'duration': duration,
 163             'view_count': view_count,
 164             'like_count': int_or_none(like_count),
 165             'dislike_count': int_or_none(dislike_count),
 166             'comment_count': int_or_none(comment_count),
 167             'age_limit': age_limit,
 168             'formats': formats,
 169         }
 170
 171
 172 class XHamsterEmbedIE(InfoExtractor):
 173     _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
 174     _TEST = {
 175         'url': 'http://xhamster.com/xembed.php?video=3328539',
 176         'info_dict': {
 177             'id': '3328539',
 178             'ext': 'mp4',
 179             'title': 'Pen Masturbation',
 180             'upload_date': '20140728',
 181             'uploader_id': 'anonymous',
 182             'duration': 5,
 183             'age_limit': 18,
 184         }
 185     }
 186
 187     @staticmethod
 188     def _extract_urls(webpage):
 189         return [url for _, url in re.findall(
 190             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
 191             webpage)]
 192
 193     def _real_extract(self, url):
 194         video_id = self._match_id(url)
 195
 196         webpage = self._download_webpage(url, video_id)
 197
 198         video_url = self._search_regex(
 199             r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
 200             webpage, 'xhamster url', default=None)
 201
 202         if not video_url:
 203             vars = self._parse_json(
 204                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
 205                 video_id)
 206             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 207
 208         return self.url_result(video_url, 'XHamster')