Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/escapist.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_str,
   7     compat_urllib_parse,
   8
   9     ExtractorError,
  10 )
  11
  12
  13 class EscapistIE(InfoExtractor):
  14     _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
  15     _TEST = {
  16         u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  17         u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
  18         u'md5': u'c6793dbda81388f4264c1ba18684a74d',
  19         u'info_dict': {
  20             u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
  21             u"uploader": u"the-escapist-presents",
  22             u"title": u"Breaking Down Baldur's Gate"
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         if mobj is None:
  29             raise ExtractorError(u'Invalid URL: %s' % url)
  30         showName = mobj.group('showname')
  31         videoId = mobj.group('episode')
  32
  33         self.report_extraction(videoId)
  34         webpage = self._download_webpage(url, videoId)
  35
  36         videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
  37             webpage, u'description', fatal=False)
  38
  39         imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
  40             webpage, u'thumbnail', fatal=False)
  41
  42         playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
  43             webpage, u'player url')
  44
  45         title = self._html_search_regex('<meta name="title" content="([^"]*)"',
  46             webpage, u'player url').split(' : ')[-1]
  47
  48         configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
  49         configUrl = compat_urllib_parse.unquote(configUrl)
  50
  51         configJSON = self._download_webpage(configUrl, videoId,
  52                                             u'Downloading configuration',
  53                                             u'unable to download configuration')
  54
  55         # Technically, it's JavaScript, not JSON
  56         configJSON = configJSON.replace("'", '"')
  57
  58         try:
  59             config = json.loads(configJSON)
  60         except (ValueError,) as err:
  61             raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
  62
  63         playlist = config['playlist']
  64         videoUrl = playlist[1]['url']
  65
  66         info = {
  67             'id': videoId,
  68             'url': videoUrl,
  69             'uploader': showName,
  70             'upload_date': None,
  71             'title': title,
  72             'ext': 'mp4',
  73             'thumbnail': imgUrl,
  74             'description': videoDesc,
  75             'player_url': playerUrl,
  76         }
  77
  78         return [info]