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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate,
parse_duration,
qualities,
strip_jsonp,
url_basename,
fix_xml_ampersands,
)
class NPOIE(InfoExtractor):
IE_NAME = 'npo.nl'
_VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
_TESTS = [
{
'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
'md5': '4b3f9c429157ec4775f2c9cb7b911016',
'info_dict': {
'id': 'VPWON_1220719',
'ext': 'm4v',
'title': 'Nieuwsuur',
'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
'upload_date': '20140622',
},
},
{
'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
'info_dict': {
'id': 'VARA_101191800',
'ext': 'm4v',
'title': 'De Mega Mike & Mega Thomas show',
'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
'upload_date': '20090227',
'duration': 2400,
},
},
{
'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
'info_dict': {
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht',
'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
'upload_date': '20130225',
'duration': 3000,
},
},
{
'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
'info_dict': {
'id': 'WO_VPRO_043706',
'ext': 'wmv',
'title': 'De nieuwe mens - Deel 1',
'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
'duration': 4680,
},
'params': {
# mplayer mms download
'skip_download': True,
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
return self._get_info(video_id)
def _get_info(self, video_id):
metadata = self._download_json(
'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
video_id,
# We have to remove the javascript callback
transform_source=strip_jsonp,
)
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
video_id,
note='Downloading token'
)
token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
formats = []
pubopties = metadata.get('pubopties')
if pubopties:
quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
for format_id in pubopties:
format_info = self._download_json(
'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
% (video_id, format_id, token),
video_id, 'Downloading %s JSON' % format_id)
if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
continue
streams = format_info.get('streams')
if streams:
video_info = self._download_json(
streams[0] + '&type=json',
video_id, 'Downloading %s stream JSON' % format_id)
else:
video_info = format_info
video_url = video_info.get('url')
if not video_url:
continue
if format_id == 'adaptive':
formats.extend(self._extract_m3u8_formats(video_url, video_id))
else:
formats.append({
'url': video_url,
'format_id': format_id,
'quality': quality(format_id),
})
streams = metadata.get('streams')
if streams:
for i, stream in enumerate(streams):
stream_url = stream.get('url')
if not stream_url:
continue
asx = self._download_xml(
stream_url, video_id,
'Downloading stream %d ASX playlist' % i,
transform_source=fix_xml_ampersands)
ref = asx.find('./ENTRY/Ref')
if ref is None:
continue
video_url = ref.get('href')
if not video_url:
continue
formats.append({
'url': video_url,
'ext': stream.get('formaat', 'asf'),
'quality': stream.get('kwaliteit'),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': metadata['titel'],
'description': metadata['info'],
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'upload_date': unified_strdate(metadata.get('gidsdatum')),
'duration': parse_duration(metadata.get('tijdsduur')),
'formats': formats,
}
class TegenlichtVproIE(NPOIE):
IE_NAME = 'tegenlicht.vpro.nl'
_VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
_TESTS = [
{
'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
'info_dict': {
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht',
'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
'upload_date': '20130225',
},
},
]
def _real_extract(self, url):
name = url_basename(url)
webpage = self._download_webpage(url, name)
urn = self._html_search_meta('mediaurn', webpage)
info_page = self._download_json(
'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
return self._get_info(info_page['mid'])
|
