Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ign.py

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7 )
   8
   9
  10 class IGNIE(InfoExtractor):
  11     """
  12     Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
  13     Some videos of it.ign.com are also supported
  14     """
  15
  16     _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles)(/.+)?/(?P<name_or_id>.+)'
  17     IE_NAME = u'ign.com'
  18
  19     _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
  20     _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>',
  21                        r'id="my_show_video">.*?<p>(.*?)</p>',
  22                        ]
  23
  24     _TEST = {
  25         u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
  26         u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
  27         u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
  28         u'info_dict': {
  29             u'title': u'The Last of Us Review',
  30             u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
  31         }
  32     }
  33
  34     def _find_video_id(self, webpage):
  35         res_id = [r'data-video-id="(.+?)"',
  36                   r'<object id="vid_(.+?)"',
  37                   r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
  38                   ]
  39         return self._search_regex(res_id, webpage, 'video id')
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         name_or_id = mobj.group('name_or_id')
  44         page_type = mobj.group('type')
  45         webpage = self._download_webpage(url, name_or_id)
  46         if page_type == 'articles':
  47             video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
  48             return self.url_result(video_url, ie='IGN')
  49         video_id = self._find_video_id(webpage)
  50         result = self._get_video_info(video_id)
  51         description = self._html_search_regex(self._DESCRIPTION_RE,
  52                                               webpage, 'video description',
  53                                               flags=re.DOTALL)
  54         result['description'] = description
  55         return result
  56
  57     def _get_video_info(self, video_id):
  58         config_url = self._CONFIG_URL_TEMPLATE % video_id
  59         config = json.loads(self._download_webpage(config_url, video_id,
  60                             u'Downloading video info'))
  61         media = config['playlist']['media']
  62         video_url = media['url']
  63
  64         return {'id': media['metadata']['videoId'],
  65                 'url': video_url,
  66                 'ext': determine_ext(video_url),
  67                 'title': media['metadata']['title'],
  68                 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
  69                 }
  70
  71
  72 class OneUPIE(IGNIE):
  73     """Extractor for 1up.com, it uses the ign videos system."""
  74
  75     _VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
  76     IE_NAME = '1up.com'
  77
  78     _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
  79
  80     _TEST = {
  81         u'url': u'http://gamevideos.1up.com/video/id/34976',
  82         u'file': u'34976.mp4',
  83         u'md5': u'68a54ce4ebc772e4b71e3123d413163d',
  84         u'info_dict': {
  85             u'title': u'Sniper Elite V2 - Trailer',
  86             u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf',
  87         }
  88     }
  89
  90     def _real_extract(self, url):
  91         mobj = re.match(self._VALID_URL, url)
  92         id = mobj.group('name_or_id')
  93         result = super(OneUPIE, self)._real_extract(url)
  94         result['id'] = id
  95         return result