4 from .common import InfoExtractor
10 class MetacriticIE(InfoExtractor):
11 _VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)'
14 u'url': u'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',
15 u'file': u'3698222.mp4',
17 u'title': u'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors',
18 u'description': u'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.',
23 def _real_extract(self, url):
24 mobj = re.match(self._VALID_URL, url)
25 video_id = mobj.group('id')
26 webpage = self._download_webpage(url, video_id)
27 # The xml is not well formatted, there are raw '&'
28 info = self._download_xml('http://www.metacritic.com/video_data?video=' + video_id,
29 video_id, u'Downloading info xml', transform_source=fix_xml_all_ampersand)
31 clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id)
33 for videoFile in clip.findall('httpURI/videoFile'):
34 rate_str = videoFile.find('rate').text
35 video_url = videoFile.find('filePath').text
39 'format_id': rate_str,
40 'rate': int(rate_str),
42 formats.sort(key=operator.itemgetter('rate'))
44 description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>',
45 webpage, u'description', flags=re.DOTALL)
49 'title': clip.find('title').text,
51 'description': description,
52 'duration': int(clip.find('duration').text),