2 from __future__ import unicode_literals
6 from .common import InfoExtractor
13 class NDRIE(InfoExtractor):
15 IE_DESC = 'NDR.de - Mediathek'
16 _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
20 'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
21 'md5': 'e7a6079ca39d3568f4996cb858dd6708',
26 'title': 'Markt - die ganze Sendung',
27 'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
32 'url': 'http://www.ndr.de/info/audio51535.html',
33 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
38 'title': 'La Valette entgeht der Hinrichtung',
39 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
45 def _real_extract(self, url):
46 mobj = re.match(self._VALID_URL, url)
47 video_id = mobj.group('id')
49 page = self._download_webpage(url, video_id, 'Downloading page')
51 title = self._og_search_title(page).strip()
52 description = self._og_search_description(page)
54 description = description.strip()
56 duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
60 mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
63 'url': mp3_url.group('audio'),
69 video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
71 thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
73 QUALITIES = ['xs', 's', 'm', 'l', 'xl']
74 thumbnails.sort(key=lambda thumb: QUALITIES.index(thumb[1]) if thumb[1] in QUALITIES else -1)
75 thumbnail = 'http://www.ndr.de' + thumbnails[-1][0]
77 for format_id in ['lo', 'hi', 'hq']:
79 'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
80 'format_id': format_id,
84 raise ExtractorError('No media links available for %s' % video_id)
89 'description': description,
90 'thumbnail': thumbnail,