2 from __future__ import unicode_literals
4 from .common import InfoExtractor
7 class FazIE(InfoExtractor):
9 _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
12 'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
16 'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
17 'description': 'md5:1453fbf9a0d041d985a47306192ea253',
21 def _real_extract(self, url):
22 video_id = self._match_id(url)
24 webpage = self._download_webpage(url, video_id)
25 config_xml_url = self._search_regex(
26 r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
27 config = self._download_xml(
28 config_xml_url, video_id, 'Downloading config xml')
30 encodings = config.find('ENCODINGS')
32 for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
33 encoding = encodings.find(code)
36 encoding_url = encoding.find('FILENAME').text
39 'format_id': code.lower(),
42 self._sort_formats(formats)
44 descr = self._html_search_regex(
45 r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
48 'title': self._og_search_title(webpage),
51 'thumbnail': config.find('STILL/STILL_BIG').text,