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