youtube_dl/extractor/metacafe.py

   1 import re
   2 import socket
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_http_client,
   7     compat_parse_qs,
   8     compat_urllib_error,
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11     compat_str,
  12     determine_ext,
  13     ExtractorError,
  14 )
  15
  16 class MetacafeIE(InfoExtractor):
  17     """Information Extractor for metacafe.com."""
  18
  19     _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
  20     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
  21     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
  22     IE_NAME = u'metacafe'
  23     _TESTS = [
  24     # Youtube video
  25     {
  26         u"add_ie": ["Youtube"],
  27         u"url":  u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
  28         u"file":  u"_aUehQsCQtM.mp4",
  29         u"info_dict": {
  30             u"upload_date": u"20090102",
  31             u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
  32             u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
  33             u"uploader": u"PBS",
  34             u"uploader_id": u"PBS"
  35         }
  36     },
  37     # Normal metacafe video
  38     {
  39         u'url': u'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
  40         u'md5': u'6e0bca200eaad2552e6915ed6fd4d9ad',
  41         u'info_dict': {
  42             u'id': u'11121940',
  43             u'ext': u'mp4',
  44             u'title': u'News: Stuff You Won\'t Do with Your PlayStation 4',
  45             u'uploader': u'ign',
  46             u'description': u'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
  47         },
  48     },
  49     # AnyClip video
  50     {
  51         u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
  52         u"file": u"an-dVVXnuY7Jh77J.mp4",
  53         u"info_dict": {
  54             u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
  55             u"uploader": u"anyclip",
  56             u"description": u"md5:38c711dd98f5bb87acf973d573442e67",
  57         },
  58     },
  59     # age-restricted video
  60     {
  61         u'url': u'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
  62         u'md5': u'98dde7c1a35d02178e8ab7560fe8bd09',
  63         u'info_dict': {
  64             u'id': u'5186653',
  65             u'ext': u'mp4',
  66             u'title': u'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
  67             u'uploader': u'Dwayne Pipe',
  68             u'description': u'md5:950bf4c581e2c059911fa3ffbe377e4b',
  69             u'age_limit': 18,
  70         },
  71     },
  72     ]
  73
  74
  75     def report_disclaimer(self):
  76         """Report disclaimer retrieval."""
  77         self.to_screen(u'Retrieving disclaimer')
  78
  79     def _real_initialize(self):
  80         # Retrieve disclaimer
  81         request = compat_urllib_request.Request(self._DISCLAIMER)
  82         try:
  83             self.report_disclaimer()
  84             compat_urllib_request.urlopen(request).read()
  85         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  86             raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
  87
  88         # Confirm age
  89         disclaimer_form = {
  90             'filters': '0',
  91             'submit': "Continue - I'm over 18",
  92             }
  93         request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
  94         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  95         try:
  96             self.report_age_confirmation()
  97             compat_urllib_request.urlopen(request).read()
  98         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  99             raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
 100
 101     def _real_extract(self, url):
 102         # Extract id and simplified title from URL
 103         mobj = re.match(self._VALID_URL, url)
 104         if mobj is None:
 105             raise ExtractorError(u'Invalid URL: %s' % url)
 106
 107         video_id = mobj.group(1)
 108
 109         # Check if video comes from YouTube
 110         mobj2 = re.match(r'^yt-(.*)$', video_id)
 111         if mobj2 is not None:
 112             return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
 113
 114         # Retrieve video webpage to extract further information
 115         req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
 116
 117         # AnyClip videos require the flashversion cookie so that we get the link
 118         # to the mp4 file
 119         mobj_an = re.match(r'^an-(.*?)$', video_id)
 120         if mobj_an:
 121             req.headers['Cookie'] = 'flashVersion=0;'
 122         webpage = self._download_webpage(req, video_id)
 123
 124         # Extract URL, uploader and title from webpage
 125         self.report_extraction(video_id)
 126         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
 127         if mobj is not None:
 128             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
 129             video_ext = mediaURL[-3:]
 130
 131             # Extract gdaKey if available
 132             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
 133             if mobj is None:
 134                 video_url = mediaURL
 135             else:
 136                 gdaKey = mobj.group(1)
 137                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
 138         else:
 139             mobj = re.search(r'<video src="([^"]+)"', webpage)
 140             if mobj:
 141                 video_url = mobj.group(1)
 142                 video_ext = 'mp4'
 143             else:
 144                 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
 145                 if mobj is None:
 146                     raise ExtractorError(u'Unable to extract media URL')
 147                 vardict = compat_parse_qs(mobj.group(1))
 148                 if 'mediaData' not in vardict:
 149                     raise ExtractorError(u'Unable to extract media URL')
 150                 mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
 151                 if mobj is None:
 152                     raise ExtractorError(u'Unable to extract media URL')
 153                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
 154                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
 155                 video_ext = determine_ext(video_url)
 156
 157         video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
 158         description = self._og_search_description(webpage)
 159         video_uploader = self._html_search_regex(
 160                 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
 161                 webpage, u'uploader nickname', fatal=False)
 162
 163         if re.search(r'"contentRating":"restricted"', webpage) is not None:
 164             age_limit = 18
 165         else:
 166             age_limit = 0
 167
 168         return {
 169             '_type':    'video',
 170             'id':       video_id,
 171             'url':      video_url,
 172             'description': description,
 173             'uploader': video_uploader,
 174             'upload_date':  None,
 175             'title':    video_title,
 176             'ext':      video_ext,
 177             'age_limit': age_limit,
 178         }