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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11 )
  12
  13
  14 class EscapistIE(InfoExtractor):
  15     _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
  16     _TEST = {
  17         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  18         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
  19         'info_dict': {
  20             'id': '6618',
  21             'ext': 'mp4',
  22             '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.",
  23             'uploader': 'the-escapist-presents',
  24             'title': "Breaking Down Baldur's Gate",
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         showName = mobj.group('showname')
  31         video_id = mobj.group('id')
  32
  33         self.report_extraction(video_id)
  34         webpage = self._download_webpage(url, video_id)
  35
  36         videoDesc = self._html_search_regex(
  37             r'<meta name="description" content="([^"]*)"',
  38             webpage, 'description', fatal=False)
  39
  40         playerUrl = self._og_search_video_url(webpage, name='player URL')
  41
  42         title = self._html_search_regex(
  43             r'<meta name="title" content="([^"]*)"',
  44             webpage, 'title').split(' : ')[-1]
  45
  46         configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
  47         configUrl = compat_urllib_parse.unquote(configUrl)
  48
  49         formats = []
  50
  51         def _add_format(name, cfgurl, quality):
  52             config = self._download_json(
  53                 cfgurl, video_id,
  54                 'Downloading ' + name + ' configuration',
  55                 'Unable to download ' + name + ' configuration',
  56                 transform_source=lambda s: s.replace("'", '"'))
  57
  58             playlist = config['playlist']
  59             formats.append({
  60                 'url': playlist[1]['url'],
  61                 'format_id': name,
  62                 'quality': quality,
  63             })
  64
  65         _add_format('normal', configUrl, quality=0)
  66         hq_url = (configUrl +
  67                   ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
  68         try:
  69             _add_format('hq', hq_url, quality=1)
  70         except ExtractorError:
  71             pass  # That's fine, we'll just use normal quality
  72
  73         self._sort_formats(formats)
  74
  75         return {
  76             'id': video_id,
  77             'formats': formats,
  78             'uploader': showName,
  79             'title': title,
  80             'thumbnail': self._og_search_thumbnail(webpage),
  81             'description': videoDesc,
  82             'player_url': playerUrl,
  83         }