import re from .common import InfoExtractor from ..utils import ( ExtractorError, unescapeHTML, ) class SteamIE(InfoExtractor): _VALID_URL = r"""http://store\.steampowered\.com/ (agecheck/)? (?Pvideo|app)/ #If the page is only for videos or for a game (?P\d+)/? (?P\d*)(?P\??) #For urltype == video we sometimes get the videoID """ _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/' _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' @classmethod def suitable(cls, url): """Receives a URL and returns True if suitable for this IE.""" return re.match(cls._VALID_URL, url, re.VERBOSE) is not None def _real_extract(self, url): m = re.match(self._VALID_URL, url, re.VERBOSE) gameID = m.group('gameID') videourl = self._VIDEO_PAGE_TEMPLATE % gameID webpage = self._download_webpage(videourl, gameID) if re.search('

Please enter your birth date to continue:

', webpage) is not None: videourl = self._AGECHECK_TEMPLATE % gameID self.report_age_confirmation() webpage = self._download_webpage(videourl, gameID) self.report_extraction(gameID) game_title = self._html_search_regex(r'', webpage, 'game title') urlRE = r"'movie_(?P\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\}," mweb = re.finditer(urlRE, webpage) namesRE = r'(?P.+?)' titles = re.finditer(namesRE, webpage) thumbsRE = r'' thumbs = re.finditer(thumbsRE, webpage) videos = [] for vid,vtitle,thumb in zip(mweb,titles,thumbs): video_id = vid.group('videoID') title = vtitle.group('videoName') video_url = vid.group('videoURL') video_thumb = thumb.group('thumbnail') if not video_url: raise ExtractorError(u'Cannot find video url for %s' % video_id) info = { 'id':video_id, 'url':video_url, 'ext': 'flv', 'title': unescapeHTML(title), 'thumbnail': video_thumb } videos.append(info) return [self.playlist_result(videos, gameID, game_title)]