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