_ Git - youtube-dl/blob - 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]+)-[^/?#]*(?:$|[?#])'
  15     _TEST = {
  16         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  17         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
  18         'info_dict': {
  19             'id': '6618',
  20             'ext': 'mp4',
  21             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
  22             'uploader_id': 'the-escapist-presents',
  23             'uploader': 'The Escapist Presents',
  24             'title': "Breaking Down Baldur's Gate",
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32
  33         uploader_id = self._html_search_regex(
  34             r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
  35             webpage, 'uploader ID', fatal=False)
  36         uploader = self._html_search_regex(
  37             r"<h1\s+class='headline'>(.*?)</a>",
  38             webpage, 'uploader', fatal=False)
  39         description = self._html_search_meta('description', webpage)
  40
  41         raw_title = self._html_search_meta('title', webpage, fatal=True)
  42         title = raw_title.partition(' : ')[2]
  43
  44         config_url = compat_urllib_parse.unquote(self._html_search_regex(
  45             r'''(?x)
  46             (?:
  47                 <param\s+name="flashvars"\s+value="config=|
  48                 flashvars=&quot;config=
  49             )
  50             ([^"&]+)
  51             ''',
  52             webpage, 'config URL'))
  53
  54         formats = []
  55
  56         def _add_format(name, cfgurl, quality):
  57             config = self._download_json(
  58                 cfgurl, video_id,
  59                 'Downloading ' + name + ' configuration',
  60                 'Unable to download ' + name + ' configuration',
  61                 transform_source=js_to_json)
  62
  63             playlist = config['playlist']
  64             video_url = next(
  65                 p['url'] for p in playlist
  66                 if p.get('eventCategory') == 'Video')
  67             formats.append({
  68                 'url': video_url,
  69                 'format_id': name,
  70                 'quality': quality,
  71             })
  72
  73         _add_format('normal', config_url, quality=0)
  74         hq_url = (config_url +
  75                   ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
  76         try:
  77             _add_format('hq', hq_url, quality=1)
  78         except ExtractorError:
  79             pass  # That's fine, we'll just use normal quality
  80
  81         self._sort_formats(formats)
  82
  83         return {
  84             'id': video_id,
  85             'formats': formats,
  86             'uploader': uploader,
  87             'uploader_id': uploader_id,
  88             'title': title,
  89             'thumbnail': self._og_search_thumbnail(webpage),
  90             'description': description,
  91         }