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     ExtractorError,
  10 )
  11
  12
  13 class XHamsterIE(InfoExtractor):
  14     """Information Extractor for xHamster"""
  15     _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
  16     _TESTS = [{
  17         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  18         'file': '1509445.mp4',
  19         'md5': '8281348b8d3c53d39fffb377d24eac4e',
  20         'info_dict': {
  21             "upload_date": "20121014",
  22             "uploader_id": "Ruseful2011",
  23             "title": "FemaleAgent Shy beauty takes the bait",
  24             "age_limit": 18,
  25         }
  26     },
  27     {
  28         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  29         'file': '2221348.flv',
  30         'md5': 'e767b9475de189320f691f49c679c4c7',
  31         'info_dict': {
  32             "upload_date": "20130914",
  33             "uploader_id": "jojo747400",
  34             "title": "Britney Spears  Sexy Booty",
  35             "age_limit": 18,
  36         }
  37     }]
  38
  39     def _real_extract(self,url):
  40         def extract_video_url(webpage):
  41             mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
  42             if mobj is None:
  43                 raise ExtractorError('Unable to extract media URL')
  44             if len(mobj.group('server')) == 0:
  45                 return compat_urllib_parse.unquote(mobj.group('file'))
  46             else:
  47                 return mobj.group('server')+'/key='+mobj.group('file')
  48
  49         def extract_mp4_video_url(webpage):
  50             mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
  51             if mp4 is None:
  52                 return None
  53             else:
  54                 return mp4.group(1)
  55
  56         def is_hd(webpage):
  57             return '<div class=\'icon iconHD\'' in webpage
  58
  59         mobj = re.match(self._VALID_URL, url)
  60
  61         video_id = mobj.group('id')
  62         seo = mobj.group('seo')
  63         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
  64         webpage = self._download_webpage(mrss_url, video_id)
  65
  66         video_title = self._html_search_regex(
  67             r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
  68
  69         # Only a few videos have an description
  70         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  71         video_description = mobj.group(1) if mobj else None
  72
  73         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)
  74         if mobj:
  75             video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
  76         else:
  77             video_upload_date = None
  78             self._downloader.report_warning('Unable to extract upload date')
  79
  80         video_uploader_id = self._html_search_regex(
  81             r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  82             webpage, 'uploader id', default='anonymous')
  83
  84         video_thumbnail = self._search_regex(
  85             r'\'image\':\'(?P<thumbnail>[^\']+)\'',
  86             webpage, 'thumbnail', fatal=False)
  87
  88         age_limit = self._rta_search(webpage)
  89
  90         hd = is_hd(webpage)
  91         video_url = extract_video_url(webpage)
  92         formats = [{
  93             'url': video_url,
  94             'format_id': 'hd' if hd else 'sd',
  95             'preference': 0,
  96         }]
  97
  98         video_mp4_url = extract_mp4_video_url(webpage)
  99         if video_mp4_url is not None:
 100             formats.append({
 101                 'url': video_mp4_url,
 102                 'ext': 'mp4',
 103                 'format_id': 'mp4-hd' if hd else 'mp4-sd',
 104                 'preference': 1,
 105             })
 106
 107         if not hd:
 108             webpage = self._download_webpage(
 109                 mrss_url + '?hd', video_id, note='Downloading HD webpage')
 110             if is_hd(webpage):
 111                 video_url = extract_video_url(webpage)
 112                 formats.append({
 113                     'url': video_url,
 114                     'format_id': 'hd',
 115                     'preference': 2,
 116                 })
 117
 118         self._sort_formats(formats)
 119
 120         return {
 121             'id': video_id,
 122             'title': video_title,
 123             'formats': formats,
 124             'description': video_description,
 125             'upload_date': video_upload_date,
 126             'uploader_id': video_uploader_id,
 127             'thumbnail': video_thumbnail,
 128             'age_limit': age_limit,
 129         }