Raphaël G. Git Repositories - youtubedl/blob - 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         u"add_ie": ["Youtube"],
  25         u"url":  u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
  26         u"file":  u"_aUehQsCQtM.flv",
  27         u"info_dict": {
  28             u"upload_date": u"20090102",
  29             u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
  30             u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
  31             u"uploader": u"PBS",
  32             u"uploader_id": u"PBS"
  33         }
  34     },
  35     {
  36         u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
  37         u"file": u"an-dVVXnuY7Jh77J.mp4",
  38         u"info_dict": {
  39             u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
  40             u"uploader": u"anyclip",
  41             u"description": u"md5:38c711dd98f5bb87acf973d573442e67"
  42         }
  43     }]
  44
  45
  46     def report_disclaimer(self):
  47         """Report disclaimer retrieval."""
  48         self.to_screen(u'Retrieving disclaimer')
  49
  50     def _real_initialize(self):
  51         # Retrieve disclaimer
  52         request = compat_urllib_request.Request(self._DISCLAIMER)
  53         try:
  54             self.report_disclaimer()
  55             compat_urllib_request.urlopen(request).read()
  56         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  57             raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
  58
  59         # Confirm age
  60         disclaimer_form = {
  61             'filters': '0',
  62             'submit': "Continue - I'm over 18",
  63             }
  64         request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
  65         try:
  66             self.report_age_confirmation()
  67             compat_urllib_request.urlopen(request).read()
  68         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  69             raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
  70
  71     def _real_extract(self, url):
  72         # Extract id and simplified title from URL
  73         mobj = re.match(self._VALID_URL, url)
  74         if mobj is None:
  75             raise ExtractorError(u'Invalid URL: %s' % url)
  76
  77         video_id = mobj.group(1)
  78
  79         # Check if video comes from YouTube
  80         mobj2 = re.match(r'^yt-(.*)$', video_id)
  81         if mobj2 is not None:
  82             return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
  83
  84         # Retrieve video webpage to extract further information
  85         req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
  86         req.headers['Cookie'] = 'flashVersion=0;'
  87         webpage = self._download_webpage(req, video_id)
  88
  89         # Extract URL, uploader and title from webpage
  90         self.report_extraction(video_id)
  91         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
  92         if mobj is not None:
  93             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
  94             video_ext = mediaURL[-3:]
  95
  96             # Extract gdaKey if available
  97             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
  98             if mobj is None:
  99                 video_url = mediaURL
 100             else:
 101                 gdaKey = mobj.group(1)
 102                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
 103         else:
 104             mobj = re.search(r'<video src="([^"]+)"', webpage)
 105             if mobj:
 106                 video_url = mobj.group(1)
 107                 video_ext = 'mp4'
 108             else:
 109                 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
 110                 if mobj is None:
 111                     raise ExtractorError(u'Unable to extract media URL')
 112                 vardict = compat_parse_qs(mobj.group(1))
 113                 if 'mediaData' not in vardict:
 114                     raise ExtractorError(u'Unable to extract media URL')
 115                 mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
 116                 if mobj is None:
 117                     raise ExtractorError(u'Unable to extract media URL')
 118                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
 119                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
 120                 video_ext = determine_ext(video_url)
 121
 122         video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
 123         description = self._og_search_description(webpage)
 124         video_uploader = self._html_search_regex(
 125                 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("channel","([^"]+)"\);',
 126                 webpage, u'uploader nickname', fatal=False)
 127
 128         return {
 129             '_type':    'video',
 130             'id':       video_id,
 131             'url':      video_url,
 132             'description': description,
 133             'uploader': video_uploader,
 134             'upload_date':  None,
 135             'title':    video_title,
 136             'ext':      video_ext,
 137         }