youtube_dl/extractor/escapist.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_urllib_parse,
   6 )
   7 from ..utils import (
   8     ExtractorError,
   9     js_to_json,
  10 )
  11
  12
  13 class EscapistIE(InfoExtractor):
  14     _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
  15     _TEST = {
  16         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  17         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
  18         'info_dict': {
  19             'id': '6618',
  20             'ext': 'mp4',
  21             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
  22             'uploader_id': 'the-escapist-presents',
  23             'uploader': 'The Escapist Presents',
  24             'title': "Breaking Down Baldur's Gate",
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         uploader_id = self._html_search_regex(
  33             r"<h1 class='headline'><a href='/videos/view/(.*?)'",
  34             webpage, 'uploader ID', fatal=False)
  35         uploader = self._html_search_regex(
  36             r"<h1 class='headline'>(.*?)</a>",
  37             webpage, 'uploader', fatal=False)
  38         description = self._html_search_meta('description', webpage)
  39
  40         raw_title = self._html_search_meta('title', webpage, fatal=True)
  41         title = raw_title.partition(' : ')[2]
  42
  43         player_url = self._og_search_video_url(webpage, name='player URL')
  44         config_url = compat_urllib_parse.unquote(self._search_regex(
  45             r'config=(.*)$', player_url, 'config URL'))
  46
  47         formats = []
  48
  49         def _add_format(name, cfgurl, quality):
  50             config = self._download_json(
  51                 cfgurl, video_id,
  52                 'Downloading ' + name + ' configuration',
  53                 'Unable to download ' + name + ' configuration',
  54                 transform_source=js_to_json)
  55
  56             playlist = config['playlist']
  57             formats.append({
  58                 'url': playlist[1]['url'],
  59                 'format_id': name,
  60                 'quality': quality,
  61             })
  62
  63         _add_format('normal', config_url, quality=0)
  64         hq_url = (config_url +
  65                   ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
  66         try:
  67             _add_format('hq', hq_url, quality=1)
  68         except ExtractorError:
  69             pass  # That's fine, we'll just use normal quality
  70
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': video_id,
  75             'formats': formats,
  76             'uploader': uploader,
  77             'uploader_id': uploader_id,
  78             'title': title,
  79             'thumbnail': self._og_search_thumbnail(webpage),
  80             'description': description,
  81             'player_url': player_url,
  82         }