_ Git - youtube-dl/blob - youtube_dl/extractor/metacafe.py

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