SteamIE: only verify the age if needed

Also use the _html_search_regex function
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-06-20 13:43:44 +02:00
parent bb47437686
commit 68f54207a3

View File

@ -3365,6 +3365,8 @@ class SteamIE(InfoExtractor):
(?P<gameID>\d+)/? (?P<gameID>\d+)/?
(?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID (?P<videoID>\d*)(?P<extra>\??) #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 @classmethod
def suitable(cls, url): def suitable(cls, url):
@ -3374,10 +3376,18 @@ def suitable(cls, url):
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE) m = re.match(self._VALID_URL, url, re.VERBOSE)
gameID = m.group('gameID') gameID = m.group('gameID')
videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
videourl = self._VIDEO_PAGE_TEMPLATE % gameID
webpage = self._download_webpage(videourl, gameID)
if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
videourl = self._AGECHECK_TEMPLATE % gameID
self.report_age_confirmation() self.report_age_confirmation()
webpage = self._download_webpage(videourl, gameID) webpage = self._download_webpage(videourl, gameID)
game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title')
self.report_extraction(gameID)
game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
webpage, 'game title')
urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\}," urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
mweb = re.finditer(urlRE, webpage) mweb = re.finditer(urlRE, webpage)