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]+)/(?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         }
  24     },
  25     {
  26         u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  27         u'file': u'2221348.flv',
  28         u'md5': u'e767b9475de189320f691f49c679c4c7',
  29         u'info_dict': {
  30             u"upload_date": u"20130914",
  31             u"uploader_id": u"jojo747400",
  32             u"title": u"Britney Spears  Sexy Booty"
  33         }
  34     }]
  35
  36     def _real_extract(self,url):
  37         mobj = re.match(self._VALID_URL, url)
  38
  39         video_id = mobj.group('id')
  40         seo = mobj.group('seo')
  41         mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo)
  42         webpage = self._download_webpage(mrss_url, video_id)
  43
  44         mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
  45         if mobj is None:
  46             raise ExtractorError(u'Unable to extract media URL')
  47         if len(mobj.group('server')) == 0:
  48             video_url = compat_urllib_parse.unquote(mobj.group('file'))
  49         else:
  50             video_url = mobj.group('server')+'/key='+mobj.group('file')
  51
  52         video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
  53             webpage, u'title')
  54
  55         # Only a few videos have an description
  56         mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
  57         if mobj:
  58             video_description = unescapeHTML(mobj.group('description'))
  59         else:
  60             video_description = None
  61
  62         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)
  63         if mobj:
  64             video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
  65         else:
  66             video_upload_date = None
  67             self._downloader.report_warning(u'Unable to extract upload date')
  68
  69         video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  70             webpage, u'uploader id', default=u'anonymous')
  71
  72         video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
  73             webpage, u'thumbnail', fatal=False)
  74
  75         return [{
  76             'id':       video_id,
  77             'url':      video_url,
  78             'ext':      determine_ext(video_url),
  79             'title':    video_title,
  80             'description': video_description,
  81             'upload_date': video_upload_date,
  82             'uploader_id': video_uploader_id,
  83             'thumbnail': video_thumbnail
  84         }]