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             (https?://[^"&]+)
  51             ''',
  52             webpage, 'config URL'))
  53
  54         formats = []
  55         ad_formats = []
  56
  57         def _add_format(name, cfgurl, quality):
  58             config = self._download_json(
  59                 cfgurl, video_id,
  60                 'Downloading ' + name + ' configuration',
  61                 'Unable to download ' + name + ' configuration',
  62                 transform_source=js_to_json)
  63
  64             playlist = config['playlist']
  65             for p in playlist:
  66                 if p.get('eventCategory') == 'Video':
  67                     ar = formats
  68                 elif p.get('eventCategory') == 'Video Postroll':
  69                     ar = ad_formats
  70                 else:
  71                     continue
  72
  73                 ar.append({
  74                     'url': p['url'],
  75                     'format_id': name,
  76                     'quality': quality,
  77                 })
  78
  79         _add_format('normal', config_url, quality=0)
  80         hq_url = (config_url +
  81                   ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
  82         try:
  83             _add_format('hq', hq_url, quality=1)
  84         except ExtractorError:
  85             pass  # That's fine, we'll just use normal quality
  86         self._sort_formats(formats)
  87
  88         res = {
  89             'id': video_id,
  90             'formats': formats,
  91             'uploader': uploader,
  92             'uploader_id': uploader_id,
  93             'title': title,
  94             'thumbnail': self._og_search_thumbnail(webpage),
  95             'description': description,
  96         }
  97
  98         if self._downloader.params.get('include_ads') and ad_formats:
  99             self._sort_formats(ad_formats)
 100             ad_res = {
 101                 'id': '%s-ad' % video_id,
 102                 'title': '%s (Postroll)' % title,
 103                 'formats': ad_formats,
 104             }
 105             return {
 106                 '_type': 'playlist',
 107                 'entries': [res, ad_res],
 108                 'title': title,
 109                 'id': video_id,
 110             }
 111
 112         return res