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>[^/?]+)[/?]?.*$'
  15     _TEST = {
  16         u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  17         u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
  18         u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
  19         u'info_dict': {
  20             u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
  21             u"uploader": u"the-escapist-presents",
  22             u"title": u"Breaking Down Baldur's Gate"
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         showName = mobj.group('showname')
  29         videoId = mobj.group('episode')
  30
  31         self.report_extraction(videoId)
  32         webpage = self._download_webpage(url, videoId)
  33
  34         videoDesc = self._html_search_regex(
  35             r'<meta name="description" content="([^"]*)"',
  36             webpage, u'description', fatal=False)
  37
  38         playerUrl = self._og_search_video_url(webpage, name=u'player URL')
  39
  40         title = self._html_search_regex(
  41             r'<meta name="title" content="([^"]*)"',
  42             webpage, u'title').split(' : ')[-1]
  43
  44         configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
  45         configUrl = compat_urllib_parse.unquote(configUrl)
  46
  47         formats = []
  48
  49         def _add_format(name, cfgurl):
  50             configJSON = self._download_webpage(
  51                 cfgurl, videoId,
  52                 u'Downloading ' + name + ' configuration',
  53                 u'Unable to download ' + name + ' 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             playlist = config['playlist']
  63             formats.append({
  64                 'url': playlist[1]['url'],
  65                 'format_id': name,
  66             })
  67
  68         _add_format(u'normal', configUrl)
  69         hq_url = (configUrl +
  70                   ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
  71         try:
  72             _add_format(u'hq', hq_url)
  73         except ExtractorError:
  74             pass  # That's fine, we'll just use normal quality
  75
  76         return {
  77             'id': videoId,
  78             'formats': formats,
  79             'uploader': showName,
  80             'title': title,
  81             'thumbnail': self._og_search_thumbnail(webpage),
  82             'description': videoDesc,
  83             'player_url': playerUrl,
  84         }