Raphaël G. Git Repositories - youtubedl/blob - 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]+)/.*\.html'
  15     _TEST = {
  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         }
  24     }
  25
  26     def _real_extract(self,url):
  27         mobj = re.match(self._VALID_URL, url)
  28
  29         video_id = mobj.group('id')
  30         mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
  31         webpage = self._download_webpage(mrss_url, video_id)
  32
  33         mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
  34         if mobj is None:
  35             raise ExtractorError(u'Unable to extract media URL')
  36         if len(mobj.group('server')) == 0:
  37             video_url = compat_urllib_parse.unquote(mobj.group('file'))
  38         else:
  39             video_url = mobj.group('server')+'/key='+mobj.group('file')
  40
  41         video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
  42             webpage, u'title')
  43
  44         # Only a few videos have an description
  45         mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
  46         if mobj:
  47             video_description = unescapeHTML(mobj.group('description'))
  48         else:
  49             video_description = None
  50
  51         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)
  52         if mobj:
  53             video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
  54         else:
  55             video_upload_date = None
  56             self._downloader.report_warning(u'Unable to extract upload date')
  57
  58         video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  59             webpage, u'uploader id', default=u'anonymous')
  60
  61         video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
  62             webpage, u'thumbnail', fatal=False)
  63
  64         return [{
  65             'id':       video_id,
  66             'url':      video_url,
  67             'ext':      determine_ext(video_url),
  68             'title':    video_title,
  69             'description': video_description,
  70             'upload_date': video_upload_date,
  71             'uploader_id': video_uploader_id,
  72             'thumbnail': video_thumbnail
  73         }]