_ 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     compat_urllib_request,
   7 )
   8 from ..utils import (
   9     ExtractorError,
  10     js_to_json,
  11     parse_duration,
  12 )
  13
  14
  15 class EscapistIE(InfoExtractor):
  16     _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
  17     _USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'
  18     _TEST = {
  19         'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
  20         'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
  21         'info_dict': {
  22             'id': '6618',
  23             'ext': 'mp4',
  24             'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
  25             'uploader_id': 'the-escapist-presents',
  26             'uploader': 'The Escapist Presents',
  27             'title': "Breaking Down Baldur's Gate",
  28             'thumbnail': 're:^https?://.*\.jpg$',
  29             'duration': 264,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         webpage_req = compat_urllib_request.Request(url)
  36         webpage_req.add_header('User-Agent', self._USER_AGENT)
  37         webpage = self._download_webpage(webpage_req, video_id)
  38
  39         uploader_id = self._html_search_regex(
  40             r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
  41             webpage, 'uploader ID', fatal=False)
  42         uploader = self._html_search_regex(
  43             r"<h1\s+class='headline'>(.*?)</a>",
  44             webpage, 'uploader', fatal=False)
  45         description = self._html_search_meta('description', webpage)
  46         duration = parse_duration(self._html_search_meta('duration', webpage))
  47
  48         raw_title = self._html_search_meta('title', webpage, fatal=True)
  49         title = raw_title.partition(' : ')[2]
  50
  51         config_url = compat_urllib_parse.unquote(self._html_search_regex(
  52             r'''(?x)
  53             (?:
  54                 <param\s+name="flashvars".*?\s+value="config=|
  55                 flashvars=&quot;config=
  56             )
  57             (https?://[^"&]+)
  58             ''',
  59             webpage, 'config URL'))
  60
  61         formats = []
  62         ad_formats = []
  63
  64         def _add_format(name, cfg_url, quality):
  65             cfg_req = compat_urllib_request.Request(cfg_url)
  66             cfg_req.add_header('User-Agent', self._USER_AGENT)
  67             config = self._download_json(
  68                 cfg_req, video_id,
  69                 'Downloading ' + name + ' configuration',
  70                 'Unable to download ' + name + ' configuration',
  71                 transform_source=js_to_json)
  72
  73             playlist = config['playlist']
  74             for p in playlist:
  75                 if p.get('eventCategory') == 'Video':
  76                     ar = formats
  77                 elif p.get('eventCategory') == 'Video Postroll':
  78                     ar = ad_formats
  79                 else:
  80                     continue
  81
  82                 ar.append({
  83                     'url': p['url'],
  84                     'format_id': name,
  85                     'quality': quality,
  86                     'http_headers': {
  87                         'User-Agent': self._USER_AGENT,
  88                     },
  89                 })
  90
  91         _add_format('normal', config_url, quality=0)
  92         hq_url = (config_url +
  93                   ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
  94         try:
  95             _add_format('hq', hq_url, quality=1)
  96         except ExtractorError:
  97             pass  # That's fine, we'll just use normal quality
  98         self._sort_formats(formats)
  99
 100         if '/escapist/sales-marketing/' in formats[-1]['url']:
 101             raise ExtractorError('This IP address has been blocked by The Escapist', expected=True)
 102
 103         res = {
 104             'id': video_id,
 105             'formats': formats,
 106             'uploader': uploader,
 107             'uploader_id': uploader_id,
 108             'title': title,
 109             'thumbnail': self._og_search_thumbnail(webpage),
 110             'description': description,
 111             'duration': duration,
 112         }
 113
 114         if self._downloader.params.get('include_ads') and ad_formats:
 115             self._sort_formats(ad_formats)
 116             ad_res = {
 117                 'id': '%s-ad' % video_id,
 118                 'title': '%s (Postroll)' % title,
 119                 'formats': ad_formats,
 120             }
 121             return {
 122                 '_type': 'playlist',
 123                 'entries': [res, ad_res],
 124                 'title': title,
 125                 'id': video_id,
 126             }
 127
 128         return res