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