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
  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     _TEST = {
  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
  37     def report_disclaimer(self):
  38         """Report disclaimer retrieval."""
  39         self.to_screen(u'Retrieving disclaimer')
  40
  41     def _real_initialize(self):
  42         # Retrieve disclaimer
  43         request = compat_urllib_request.Request(self._DISCLAIMER)
  44         try:
  45             self.report_disclaimer()
  46             compat_urllib_request.urlopen(request).read()
  47         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  48             raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
  49
  50         # Confirm age
  51         disclaimer_form = {
  52             'filters': '0',
  53             'submit': "Continue - I'm over 18",
  54             }
  55         request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
  56         try:
  57             self.report_age_confirmation()
  58             compat_urllib_request.urlopen(request).read()
  59         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  60             raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
  61
  62     def _real_extract(self, url):
  63         # Extract id and simplified title from URL
  64         mobj = re.match(self._VALID_URL, url)
  65         if mobj is None:
  66             raise ExtractorError(u'Invalid URL: %s' % url)
  67
  68         video_id = mobj.group(1)
  69
  70         # Check if video comes from YouTube
  71         mobj2 = re.match(r'^yt-(.*)$', video_id)
  72         if mobj2 is not None:
  73             return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
  74
  75         # Retrieve video webpage to extract further information
  76         webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id)
  77
  78         # Extract URL, uploader and title from webpage
  79         self.report_extraction(video_id)
  80         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
  81         if mobj is not None:
  82             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
  83             video_extension = mediaURL[-3:]
  84
  85             # Extract gdaKey if available
  86             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
  87             if mobj is None:
  88                 video_url = mediaURL
  89             else:
  90                 gdaKey = mobj.group(1)
  91                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
  92         else:
  93             mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
  94             if mobj is None:
  95                 raise ExtractorError(u'Unable to extract media URL')
  96             vardict = compat_parse_qs(mobj.group(1))
  97             if 'mediaData' not in vardict:
  98                 raise ExtractorError(u'Unable to extract media URL')
  99             mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
 100             if mobj is None:
 101                 raise ExtractorError(u'Unable to extract media URL')
 102             mediaURL = mobj.group('mediaURL').replace('\\/', '/')
 103             video_extension = mediaURL[-3:]
 104             video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
 105
 106         mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
 107         if mobj is None:
 108             raise ExtractorError(u'Unable to extract title')
 109         video_title = mobj.group(1).decode('utf-8')
 110
 111         mobj = re.search(r'submitter=(.*?);', webpage)
 112         if mobj is None:
 113             raise ExtractorError(u'Unable to extract uploader nickname')
 114         video_uploader = mobj.group(1)
 115
 116         return [{
 117             'id':       video_id.decode('utf-8'),
 118             'url':      video_url.decode('utf-8'),
 119             'uploader': video_uploader.decode('utf-8'),
 120             'upload_date':  None,
 121             'title':    video_title,
 122             'ext':      video_extension.decode('utf-8'),
 123         }]