1 from __future__ import unicode_literals
5 from .common import InfoExtractor
6 from ..utils import int_or_none
9 class UbuIE(InfoExtractor):
10 _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
12 'url': 'http://ubu.com/film/her_noise.html',
13 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9',
17 'title': 'Her Noise - The Making Of (2007)',
22 def _real_extract(self, url):
23 mobj = re.match(self._VALID_URL, url)
24 video_id = mobj.group('id')
26 webpage = self._download_webpage(url, video_id)
28 title = self._html_search_regex(
29 r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
31 duration = int_or_none(self._html_search_regex(
32 r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None))
39 ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"],
40 ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"']
43 for format_id, format_regex in FORMAT_REGEXES:
44 m = re.search(format_regex, webpage)
48 'format_id': format_id,