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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
fix_xml_ampersands,
parse_duration,
qualities,
strip_jsonp,
unified_strdate,
url_basename,
)
class NPOBaseIE(InfoExtractor):
def _get_token(self, video_id):
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
video_id, note='Downloading token')
return self._search_regex(
r'npoplayer\.token = "(.+?)"', token_page, 'token')
class NPOIE(NPOBaseIE):
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,
}
},
# non asf in streams
{
'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
'md5': 'b3da13de374cbe2d5332a7e910bef97f',
'info_dict': {
'id': 'WO_NOS_762771',
'ext': 'mp4',
'title': 'Hoe gaat Europa verder na Parijs?',
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
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 = self._get_token(video_id)
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
if '.asf' not in stream_url:
formats.append({
'url': stream_url,
'quality': stream.get('kwaliteit'),
})
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 NPOLiveIE(NPOBaseIE):
IE_NAME = 'npo.nl:live'
_VALID_URL = r'https?://www\.npo\.nl/live/(?P<id>.+)'
_TEST = {
'url': 'http://www.npo.nl/live/npo-1',
'info_dict': {
'id': 'LI_NEDERLAND1_136692',
'display_id': 'npo-1',
'ext': 'mp4',
'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'Livestream',
'is_live': True,
},
'params': {
'skip_download': True,
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
live_id = self._search_regex(
r'data-prid="([^"]+)"', webpage, 'live id')
metadata = self._download_json(
'http://e.omroep.nl/metadata/%s' % live_id,
display_id, transform_source=strip_jsonp)
token = self._get_token(display_id)
formats = []
streams = metadata.get('streams')
if streams:
for stream in streams:
stream_type = stream.get('type').lower()
if stream_type == 'ss':
continue
stream_info = self._download_json(
'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
% (stream.get('url'), token),
display_id, 'Downloading %s JSON' % stream_type)
if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
continue
stream_url = self._download_json(
stream_info['stream'], display_id,
'Downloading %s URL' % stream_type,
transform_source=strip_jsonp)
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(stream_url, display_id)
# f4m downloader downloads only piece of live stream
for f4m_format in f4m_formats:
f4m_format['preference'] = -1
formats.extend(f4m_formats)
elif stream_type == 'hls':
formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
else:
formats.append({
'url': stream_url,
})
self._sort_formats(formats)
return {
'id': live_id,
'display_id': display_id,
'title': self._live_title(metadata['titel']),
'description': metadata['info'],
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'formats': formats,
'is_live': True,
}
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'])
|
