1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
|
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class NDRIE(InfoExtractor):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Mediathek'
_VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
_TESTS = [
{
'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
'md5': 'e7a6079ca39d3568f4996cb858dd6708',
'note': 'Video file',
'info_dict': {
'id': '7959',
'ext': 'mp4',
'title': 'Markt - die ganze Sendung',
'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
'duration': 2655,
},
},
{
'url': 'http://www.ndr.de/903/audio191719.html',
'md5': '41ed601768534dd18a9ae34d84798129',
'note': 'Audio file',
'info_dict': {
'id': '191719',
'ext': 'mp3',
'title': '"Es war schockierend"',
'description': 'md5:ed7ff8364793545021a6355b97e95f10',
'duration': 112,
}
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id, 'Downloading page')
title = self._og_search_title(page)
description = self._og_search_description(page)
mobj = re.search(
r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
page)
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
formats = []
mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
if mp3_url:
formats.append({
'url': mp3_url.group('audio'),
'format_id': 'mp3',
})
thumbnail = None
video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
if video_url:
thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
page, 'thumbnail', fatal=False)
if thumbnail:
thumbnail = 'http://www.ndr.de' + thumbnail
for format_id in ['lo', 'hi', 'hq']:
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
'format_id': format_id,
})
if not formats:
raise ExtractorError('No media links available for %s' % video_id)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}
|
