_ 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 ..utils import (
   7     compat_urllib_parse,
   8     unescapeHTML,
   9     determine_ext,
  10     ExtractorError,
  11 )
  12
  13
  14 class XHamsterIE(InfoExtractor):
  15     """Information Extractor for xHamster"""
  16     _VALID_URL = r'(?:http://)?(?:www\.)?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         'file': '1509445.flv',
  20         'md5': '9f48e0e8d58e3076bb236ff412ab62fa',
  21         'info_dict': {
  22             "upload_date": "20121014",
  23             "uploader_id": "Ruseful2011",
  24             "title": "FemaleAgent Shy beauty takes the bait",
  25             "age_limit": 18,
  26         }
  27     },
  28     {
  29         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  30         'file': '2221348.flv',
  31         'md5': 'e767b9475de189320f691f49c679c4c7',
  32         'info_dict': {
  33             "upload_date": "20130914",
  34             "uploader_id": "jojo747400",
  35             "title": "Britney Spears  Sexy Booty",
  36             "age_limit": 18,
  37         }
  38     }]
  39
  40     def _real_extract(self,url):
  41         def extract_video_url(webpage):
  42             mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
  43             if mobj is None:
  44                 raise ExtractorError(u'Unable to extract media URL')
  45             if len(mobj.group('server')) == 0:
  46                 return compat_urllib_parse.unquote(mobj.group('file'))
  47             else:
  48                 return mobj.group('server')+'/key='+mobj.group('file')
  49
  50         def extract_mp4_video_url(webpage):
  51             mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
  52             if mp4 is None:
  53                 return None
  54             else:
  55                 return mp4.group(1)
  56
  57         def is_hd(webpage):
  58             return webpage.find('<div class=\'icon iconHD\'') != -1
  59
  60         mobj = re.match(self._VALID_URL, url)
  61
  62         video_id = mobj.group('id')
  63         seo = mobj.group('seo')
  64         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
  65         webpage = self._download_webpage(mrss_url, video_id)
  66
  67         video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
  68             webpage, 'title')
  69
  70         # Only a few videos have an description
  71         mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
  72         if mobj:
  73             video_description = unescapeHTML(mobj.group('description'))
  74         else:
  75             video_description = None
  76
  77         mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
  78         if mobj:
  79             video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
  80         else:
  81             video_upload_date = None
  82             self._downloader.report_warning(u'Unable to extract upload date')
  83
  84         video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  85             webpage, 'uploader id', default=u'anonymous')
  86
  87         video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
  88             webpage, 'thumbnail', fatal=False)
  89
  90         age_limit = self._rta_search(webpage)
  91
  92         hd = is_hd(webpage)
  93
  94         video_url = extract_video_url(webpage)
  95         formats = [{
  96             'url': video_url,
  97             'ext': determine_ext(video_url),
  98             'format': 'hd' if hd else 'sd',
  99             'format_id': 'hd' if hd else 'sd',
 100         }]
 101
 102         video_mp4_url = extract_mp4_video_url(webpage)
 103         if (not video_mp4_url is None) and (formats[0]['ext'] != 'mp4'):
 104             formats.append({
 105                 'url': video_mp4_url,
 106                 'ext': 'mp4',
 107                 'format': 'hd' if hd else 'sd',
 108                 'format_id': 'hd' if hd else 'sd',
 109             })
 110
 111         if not hd:
 112             webpage = self._download_webpage(mrss_url+'?hd', video_id)
 113             if is_hd(webpage):
 114                 video_url = extract_video_url(webpage)
 115                 formats.append({
 116                     'url': video_url,
 117                     'ext': determine_ext(video_url),
 118                     'format': 'hd',
 119                     'format_id': 'hd',
 120                 })
 121
 122         return {
 123             'id': video_id,
 124             'title': video_title,
 125             'formats': formats,
 126             'description': video_description,
 127             'upload_date': video_upload_date,
 128             'uploader_id': video_uploader_id,
 129             'thumbnail': video_thumbnail,
 130             'age_limit': age_limit,
 131         }