1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class UbuIE(InfoExtractor):
13 _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
15 'url': 'http://ubu.com/film/her_noise.html',
16 'md5': '138d5652618bf0f03878978db9bef1ee',
20 'title': 'Her Noise - The Making Of (2007)',
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27 webpage = self._download_webpage(url, video_id)
29 title = self._html_search_regex(
30 r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
32 duration = int_or_none(self._html_search_regex(
33 r'Duration: (\d+) minutes', webpage, 'duration', fatal=False),
38 ('sq', r"'flashvars'\s*,\s*'file=([^']+)'"),
39 ('hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'),
41 preference = qualities([fid for fid, _ in FORMAT_REGEXES])
42 for format_id, format_regex in FORMAT_REGEXES:
43 m = re.search(format_regex, webpage)
47 'format_id': format_id,
48 'preference': preference(format_id),
50 self._sort_formats(formats)