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
  20     @classmethod
  21     def suitable(cls, url):
  22         """Receives a URL and returns True if suitable for this IE."""
  23         return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
  24
  25     def _real_extract(self, url):
  26         m = re.match(self._VALID_URL, url, re.VERBOSE)
  27         gameID = m.group('gameID')
  28
  29         videourl = self._VIDEO_PAGE_TEMPLATE % gameID
  30         webpage = self._download_webpage(videourl, gameID)
  31
  32         if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
  33             videourl = self._AGECHECK_TEMPLATE % gameID
  34             self.report_age_confirmation()
  35             webpage = self._download_webpage(videourl, gameID)
  36
  37         self.report_extraction(gameID)
  38         game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
  39                                              webpage, 'game title')
  40
  41         urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
  42         mweb = re.finditer(urlRE, webpage)
  43         namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
  44         titles = re.finditer(namesRE, webpage)
  45         thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
  46         thumbs = re.finditer(thumbsRE, webpage)
  47         videos = []
  48         for vid,vtitle,thumb in zip(mweb,titles,thumbs):
  49             video_id = vid.group('videoID')
  50             title = vtitle.group('videoName')
  51             video_url = vid.group('videoURL')
  52             video_thumb = thumb.group('thumbnail')
  53             if not video_url:
  54                 raise ExtractorError(u'Cannot find video url for %s' % video_id)
  55             info = {
  56                 'id':video_id,
  57                 'url':video_url,
  58                 'ext': 'flv',
  59                 'title': unescapeHTML(title),
  60                 'thumbnail': video_thumb
  61                   }
  62             videos.append(info)
  63         return [self.playlist_result(videos, gameID, game_title)]