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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     unescapeHTML,
   7 )
   8
   9
  10 class SteamIE(InfoExtractor):
  11     _VALID_URL = r"""http://store\.steampowered\.com/
  12                 (agecheck/)?
  13                 (?P<urltype>video|app)/ #If the page is only for videos or for a game
  14                 (?P<gameID>\d+)/?
  15                 (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
  16                 """
  17     _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
  18     _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
  19     _TEST = {
  20         u"url": u"http://store.steampowered.com/video/105600/",
  21         u"playlist": [
  22             {
  23                 u"file": u"81300.flv",
  24                 u"md5": u"f870007cee7065d7c76b88f0a45ecc07",
  25                 u"info_dict": {
  26                         u"title": u"Terraria 1.1 Trailer"
  27                 }
  28             },
  29             {
  30                 u"file": u"80859.flv",
  31                 u"md5": u"61aaf31a5c5c3041afb58fb83cbb5751",
  32                 u"info_dict": {
  33                     u"title": u"Terraria Trailer"
  34                 }
  35             }
  36         ]
  37     }
  38
  39
  40     @classmethod
  41     def suitable(cls, url):
  42         """Receives a URL and returns True if suitable for this IE."""
  43         return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
  44
  45     def _real_extract(self, url):
  46         m = re.match(self._VALID_URL, url, re.VERBOSE)
  47         gameID = m.group('gameID')
  48
  49         videourl = self._VIDEO_PAGE_TEMPLATE % gameID
  50         webpage = self._download_webpage(videourl, gameID)
  51
  52         if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
  53             videourl = self._AGECHECK_TEMPLATE % gameID
  54             self.report_age_confirmation()
  55             webpage = self._download_webpage(videourl, gameID)
  56
  57         self.report_extraction(gameID)
  58         game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
  59                                              webpage, 'game title')
  60
  61         urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
  62         mweb = re.finditer(urlRE, webpage)
  63         namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
  64         titles = re.finditer(namesRE, webpage)
  65         thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
  66         thumbs = re.finditer(thumbsRE, webpage)
  67         videos = []
  68         for vid,vtitle,thumb in zip(mweb,titles,thumbs):
  69             video_id = vid.group('videoID')
  70             title = vtitle.group('videoName')
  71             video_url = vid.group('videoURL')
  72             video_thumb = thumb.group('thumbnail')
  73             if not video_url:
  74                 raise ExtractorError(u'Cannot find video url for %s' % video_id)
  75             info = {
  76                 'id':video_id,
  77                 'url':video_url,
  78                 'ext': 'flv',
  79                 'title': unescapeHTML(title),
  80                 'thumbnail': video_thumb
  81                   }
  82             videos.append(info)
  83         return [self.playlist_result(videos, gameID, game_title)]