2 from __future__ import unicode_literals
6 from .common import InfoExtractor
14 class NDRIE(InfoExtractor):
16 IE_DESC = 'NDR.de - Mediathek'
17 _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
21 'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
22 'md5': 'e7a6079ca39d3568f4996cb858dd6708',
27 'title': 'Markt - die ganze Sendung',
28 'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
33 'url': 'http://www.ndr.de/info/audio51535.html',
34 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
39 'title': 'La Valette entgeht der Hinrichtung',
40 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
46 def _real_extract(self, url):
47 mobj = re.match(self._VALID_URL, url)
48 video_id = mobj.group('id')
50 page = self._download_webpage(url, video_id, 'Downloading page')
52 title = self._og_search_title(page).strip()
53 description = self._og_search_description(page)
55 description = description.strip()
57 duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', fatal=False))
61 mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
64 'url': mp3_url.group('audio'),
70 video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
72 thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
74 quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
75 largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
76 thumbnail = 'http://www.ndr.de' + largest[0]
78 for format_id in 'lo', 'hi', 'hq':
80 'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
81 'format_id': format_id,
85 raise ExtractorError('No media links available for %s' % video_id)
90 'description': description,
91 'thumbnail': thumbnail,