2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_etree_fromstring
15 class FazIE(InfoExtractor):
17 _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
20 'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
24 'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
25 'description': 'md5:1453fbf9a0d041d985a47306192ea253',
28 'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
29 'only_matching': True,
31 'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
32 'only_matching': True,
34 'url': 'http://www.faz.net/-13659345.html',
35 'only_matching': True,
37 'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
38 'only_matching': True,
40 'url': 'http://www.faz.net/foobarblafasel-13659345.html',
41 'only_matching': True,
44 def _real_extract(self, url):
45 video_id = self._match_id(url)
47 webpage = self._download_webpage(url, video_id)
48 description = self._og_search_description(webpage)
49 media = self._html_search_regex(
50 r"data-videojs-media='([^']+)",
53 perform_url = self._search_regex(
54 r"<iframe[^>]+?src='((?:http:)?//player\.performgroup\.com/eplayer/eplayer\.html#/?[0-9a-f]{26}\.[0-9a-z]{26})",
55 webpage, 'perform url')
56 return self.url_result(perform_url)
57 config = compat_etree_fromstring(media)
59 encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
61 for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
62 encoding = xpath_element(encodings, code)
63 if encoding is not None:
64 encoding_url = xpath_text(encoding, 'FILENAME')
66 tbr = xpath_text(encoding, 'AVERAGEBITRATE', 1000)
68 tbr = int_or_none(tbr.replace(',', '.'))
71 'format_id': code.lower(),
74 'vcodec': xpath_text(encoding, 'CODEC'),
76 mobj = re.search(r'(\d+)x(\d+)_(\d+)\.mp4', encoding_url)
79 'width': int(mobj.group(1)),
80 'height': int(mobj.group(2)),
81 'tbr': tbr or int(mobj.group(3)),
84 self._sort_formats(formats)
88 'title': self._og_search_title(webpage),
90 'description': description.strip() if description else None,
91 'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
92 'duration': int_or_none(xpath_text(config, 'DURATION')),