_ Git - youtube-dl/blob - youtube_dl/extractor/gametrailers.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     parse_age_limit,
   7     url_basename,
   8 )
   9
  10
  11 class GametrailersIE(InfoExtractor):
  12     _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
  13
  14     _TEST = {
  15         'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',
  16         'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a',
  17         'info_dict': {
  18             'id': '2983958',
  19             'ext': 'mp4',
  20             'display_id': '116437-Just-Cause-3-Review',
  21             'title': 'Just Cause 3 - Review',
  22             'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         display_id = self._match_id(url)
  28         webpage = self._download_webpage(url, display_id)
  29         title = self._html_search_regex(
  30             r'<title>(.+?)\|', webpage, 'title').strip()
  31         embed_url = self._proto_relative_url(
  32             self._search_regex(
  33                 r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage,
  34                 'embed url'),
  35             scheme='http:')
  36         video_id = url_basename(embed_url)
  37         embed_page = self._download_webpage(embed_url, video_id)
  38         embed_vars_json = self._search_regex(
  39             r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page,
  40             'embed vars')
  41         info = self._parse_json(embed_vars_json, video_id)
  42
  43         formats = []
  44         for media in info['media']:
  45             if media['mediaPurpose'] == 'play':
  46                 formats.append({
  47                     'url': media['uri'],
  48                     'height': media['height'],
  49                     'width:': media['width'],
  50                 })
  51         self._sort_formats(formats)
  52
  53         return {
  54             'id': video_id,
  55             'display_id': display_id,
  56             'title': title,
  57             'formats': formats,
  58             'thumbnail': info.get('thumbUri'),
  59             'description': self._og_search_description(webpage),
  60             'duration': int_or_none(info.get('videoLengthInSeconds')),
  61             'age_limit': parse_age_limit(info.get('audienceRating')),
  62         }