youtube_dl/extractor/xhamster.py

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