youtube_dl/extractor/metacafe.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_parse_qs,
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10     determine_ext,
  11     ExtractorError,
  12 )
  13
  14
  15 class MetacafeIE(InfoExtractor):
  16     _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
  17     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
  18     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
  19     IE_NAME = 'metacafe'
  20     _TESTS = [
  21         # Youtube video
  22         {
  23             'add_ie': ['Youtube'],
  24             'url':  'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
  25             'info_dict': {
  26                 'id': '_aUehQsCQtM',
  27                 'ext': 'mp4',
  28                 'upload_date': '20090102',
  29                 'title': 'The Electric Company | \"Short I\" | PBS KIDS GO!',
  30                 'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
  31                 'uploader': 'PBS',
  32                 'uploader_id': 'PBS'
  33             }
  34         },
  35         # Normal metacafe video
  36         {
  37             'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
  38             'md5': '6e0bca200eaad2552e6915ed6fd4d9ad',
  39             'info_dict': {
  40                 'id': '11121940',
  41                 'ext': 'mp4',
  42                 'title': 'News: Stuff You Won\'t Do with Your PlayStation 4',
  43                 'uploader': 'ign',
  44                 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
  45             },
  46         },
  47         # AnyClip video
  48         {
  49             'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
  50             'info_dict': {
  51                 'id': 'an-dVVXnuY7Jh77J',
  52                 'ext': 'mp4',
  53                 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
  54                 'uploader': 'anyclip',
  55                 'description': 'md5:38c711dd98f5bb87acf973d573442e67',
  56             },
  57         },
  58         # age-restricted video
  59         {
  60             'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
  61             'md5': '98dde7c1a35d02178e8ab7560fe8bd09',
  62             'info_dict': {
  63                 'id': '5186653',
  64                 'ext': 'mp4',
  65                 'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
  66                 'uploader': 'Dwayne Pipe',
  67                 'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b',
  68                 'age_limit': 18,
  69             },
  70         },
  71         # cbs video
  72         {
  73             'url': 'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
  74             'info_dict': {
  75                 'id': '0rOxMBabDXN6',
  76                 'ext': 'flv',
  77                 'title': 'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
  78                 'description': 'md5:54d49fac53d26d5a0aaeccd061ada09d',
  79                 'duration': 129,
  80             },
  81             'params': {
  82                 # rtmp download
  83                 'skip_download': True,
  84             },
  85         },
  86     ]
  87
  88     def report_disclaimer(self):
  89         """Report disclaimer retrieval."""
  90         self.to_screen('Retrieving disclaimer')
  91
  92     def _real_initialize(self):
  93         # Retrieve disclaimer
  94         self.report_disclaimer()
  95         self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
  96
  97         # Confirm age
  98         disclaimer_form = {
  99             'filters': '0',
 100             'submit': "Continue - I'm over 18",
 101         }
 102         request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
 103         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 104         self.report_age_confirmation()
 105         self._download_webpage(request, None, False, 'Unable to confirm age')
 106
 107     def _real_extract(self, url):
 108         # Extract id and simplified title from URL
 109         mobj = re.match(self._VALID_URL, url)
 110         if mobj is None:
 111             raise ExtractorError('Invalid URL: %s' % url)
 112
 113         video_id = mobj.group(1)
 114
 115         # the video may come from an external site
 116         m_external = re.match('^(\w{2})-(.*)$', video_id)
 117         if m_external is not None:
 118             prefix, ext_id = m_external.groups()
 119             # Check if video comes from YouTube
 120             if prefix == 'yt':
 121                 return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube')
 122             # CBS videos use theplatform.com
 123             if prefix == 'cb':
 124                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 125
 126         # Retrieve video webpage to extract further information
 127         req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
 128
 129         # AnyClip videos require the flashversion cookie so that we get the link
 130         # to the mp4 file
 131         mobj_an = re.match(r'^an-(.*?)$', video_id)
 132         if mobj_an:
 133             req.headers['Cookie'] = 'flashVersion=0;'
 134         webpage = self._download_webpage(req, video_id)
 135
 136         # Extract URL, uploader and title from webpage
 137         self.report_extraction(video_id)
 138         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
 139         if mobj is not None:
 140             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
 141             video_ext = mediaURL[-3:]
 142
 143             # Extract gdaKey if available
 144             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
 145             if mobj is None:
 146                 video_url = mediaURL
 147             else:
 148                 gdaKey = mobj.group(1)
 149                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
 150         else:
 151             mobj = re.search(r'<video src="([^"]+)"', webpage)
 152             if mobj:
 153                 video_url = mobj.group(1)
 154                 video_ext = 'mp4'
 155             else:
 156                 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
 157                 if mobj is None:
 158                     raise ExtractorError('Unable to extract media URL')
 159                 vardict = compat_parse_qs(mobj.group(1))
 160                 if 'mediaData' not in vardict:
 161                     raise ExtractorError('Unable to extract media URL')
 162                 mobj = re.search(
 163                     r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
 164                 if mobj is None:
 165                     raise ExtractorError('Unable to extract media URL')
 166                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
 167                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
 168                 video_ext = determine_ext(video_url)
 169
 170         video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title')
 171         description = self._og_search_description(webpage)
 172         thumbnail = self._og_search_thumbnail(webpage)
 173         video_uploader = self._html_search_regex(
 174                 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
 175                 webpage, 'uploader nickname', fatal=False)
 176
 177         if re.search(r'"contentRating":"restricted"', webpage) is not None:
 178             age_limit = 18
 179         else:
 180             age_limit = 0
 181
 182         return {
 183             'id': video_id,
 184             'url': video_url,
 185             'description': description,
 186             'uploader': video_uploader,
 187             'title': video_title,
 188             'thumbnail':thumbnail,
 189             'ext': video_ext,
 190             'age_limit': age_limit,
 191         }