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