]>
Commit | Line | Data |
---|---|---|
331ae266 JMF |
1 | from __future__ import unicode_literals |
2 | ||
331ae266 JMF |
3 | from .common import InfoExtractor |
4 | from ..utils import ( | |
5c4a81d9 | 5 | fix_xml_ampersands, |
944a3de2 | 6 | parse_duration, |
c9ea760e | 7 | qualities, |
609a61e3 | 8 | strip_jsonp, |
5c4a81d9 | 9 | unified_strdate, |
d0df9292 | 10 | url_basename, |
331ae266 JMF |
11 | ) |
12 | ||
13 | ||
04e0bac2 S |
14 | class NPOBaseIE(InfoExtractor): |
15 | def _get_token(self, video_id): | |
16 | token_page = self._download_webpage( | |
17 | 'http://ida.omroep.nl/npoplayer/i.js', | |
18 | video_id, note='Downloading token') | |
19 | return self._search_regex( | |
20 | r'npoplayer\.token = "(.+?)"', token_page, 'token') | |
21 | ||
22 | ||
23 | class NPOIE(NPOBaseIE): | |
331ae266 JMF |
24 | IE_NAME = 'npo.nl' |
25 | _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)' | |
26 | ||
944a3de2 S |
27 | _TESTS = [ |
28 | { | |
29 | 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', | |
30 | 'md5': '4b3f9c429157ec4775f2c9cb7b911016', | |
31 | 'info_dict': { | |
32 | 'id': 'VPWON_1220719', | |
33 | 'ext': 'm4v', | |
34 | 'title': 'Nieuwsuur', | |
35 | 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', | |
36 | 'upload_date': '20140622', | |
37 | }, | |
331ae266 | 38 | }, |
944a3de2 S |
39 | { |
40 | 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800', | |
41 | 'md5': 'da50a5787dbfc1603c4ad80f31c5120b', | |
42 | 'info_dict': { | |
43 | 'id': 'VARA_101191800', | |
44 | 'ext': 'm4v', | |
45 | 'title': 'De Mega Mike & Mega Thomas show', | |
46 | 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', | |
47 | 'upload_date': '20090227', | |
48 | 'duration': 2400, | |
49 | }, | |
50 | }, | |
51 | { | |
52 | 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', | |
53 | 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', | |
54 | 'info_dict': { | |
55 | 'id': 'VPWON_1169289', | |
56 | 'ext': 'm4v', | |
57 | 'title': 'Tegenlicht', | |
58 | 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', | |
59 | 'upload_date': '20130225', | |
60 | 'duration': 3000, | |
61 | }, | |
1ff30d7b S |
62 | }, |
63 | { | |
64 | 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', | |
65 | 'info_dict': { | |
66 | 'id': 'WO_VPRO_043706', | |
67 | 'ext': 'wmv', | |
68 | 'title': 'De nieuwe mens - Deel 1', | |
69 | 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', | |
70 | 'duration': 4680, | |
71 | }, | |
72 | 'params': { | |
73 | # mplayer mms download | |
74 | 'skip_download': True, | |
75 | } | |
76 | }, | |
c85f3683 S |
77 | # non asf in streams |
78 | { | |
79 | 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771', | |
80 | 'md5': 'b3da13de374cbe2d5332a7e910bef97f', | |
81 | 'info_dict': { | |
82 | 'id': 'WO_NOS_762771', | |
83 | 'ext': 'mp4', | |
84 | 'title': 'Hoe gaat Europa verder na Parijs?', | |
85 | }, | |
86 | }, | |
944a3de2 | 87 | ] |
331ae266 JMF |
88 | |
89 | def _real_extract(self, url): | |
04e0bac2 | 90 | video_id = self._match_id(url) |
d0df9292 | 91 | return self._get_info(video_id) |
331ae266 | 92 | |
d0df9292 | 93 | def _get_info(self, video_id): |
331ae266 JMF |
94 | metadata = self._download_json( |
95 | 'http://e.omroep.nl/metadata/aflevering/%s' % video_id, | |
96 | video_id, | |
97 | # We have to remove the javascript callback | |
609a61e3 | 98 | transform_source=strip_jsonp, |
331ae266 | 99 | ) |
04e0bac2 S |
100 | |
101 | token = self._get_token(video_id) | |
331ae266 | 102 | |
c9ea760e | 103 | formats = [] |
1ff30d7b S |
104 | |
105 | pubopties = metadata.get('pubopties') | |
106 | if pubopties: | |
107 | quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) | |
108 | for format_id in pubopties: | |
109 | format_info = self._download_json( | |
110 | 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' | |
111 | % (video_id, format_id, token), | |
112 | video_id, 'Downloading %s JSON' % format_id) | |
113 | if format_info.get('error_code', 0) or format_info.get('errorcode', 0): | |
114 | continue | |
115 | streams = format_info.get('streams') | |
116 | if streams: | |
117 | video_info = self._download_json( | |
118 | streams[0] + '&type=json', | |
119 | video_id, 'Downloading %s stream JSON' % format_id) | |
120 | else: | |
121 | video_info = format_info | |
122 | video_url = video_info.get('url') | |
123 | if not video_url: | |
124 | continue | |
125 | if format_id == 'adaptive': | |
126 | formats.extend(self._extract_m3u8_formats(video_url, video_id)) | |
127 | else: | |
128 | formats.append({ | |
129 | 'url': video_url, | |
130 | 'format_id': format_id, | |
131 | 'quality': quality(format_id), | |
132 | }) | |
133 | ||
134 | streams = metadata.get('streams') | |
135 | if streams: | |
136 | for i, stream in enumerate(streams): | |
137 | stream_url = stream.get('url') | |
138 | if not stream_url: | |
139 | continue | |
5c4a81d9 | 140 | if '.asf' not in stream_url: |
a0977064 S |
141 | formats.append({ |
142 | 'url': stream_url, | |
143 | 'quality': stream.get('kwaliteit'), | |
144 | }) | |
145 | continue | |
1ff30d7b S |
146 | asx = self._download_xml( |
147 | stream_url, video_id, | |
148 | 'Downloading stream %d ASX playlist' % i, | |
149 | transform_source=fix_xml_ampersands) | |
150 | ref = asx.find('./ENTRY/Ref') | |
151 | if ref is None: | |
152 | continue | |
153 | video_url = ref.get('href') | |
154 | if not video_url: | |
155 | continue | |
c9ea760e | 156 | formats.append({ |
944a3de2 | 157 | 'url': video_url, |
1ff30d7b S |
158 | 'ext': stream.get('formaat', 'asf'), |
159 | 'quality': stream.get('kwaliteit'), | |
c9ea760e | 160 | }) |
1ff30d7b | 161 | |
c9ea760e | 162 | self._sort_formats(formats) |
331ae266 JMF |
163 | |
164 | return { | |
165 | 'id': video_id, | |
166 | 'title': metadata['titel'], | |
331ae266 | 167 | 'description': metadata['info'], |
944a3de2 S |
168 | 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], |
169 | 'upload_date': unified_strdate(metadata.get('gidsdatum')), | |
170 | 'duration': parse_duration(metadata.get('tijdsduur')), | |
c9ea760e | 171 | 'formats': formats, |
331ae266 | 172 | } |
d0df9292 JMF |
173 | |
174 | ||
04e0bac2 S |
175 | class NPOLiveIE(NPOBaseIE): |
176 | IE_NAME = 'npo.nl:live' | |
177 | _VALID_URL = r'https?://www\.npo\.nl/live/(?P<id>.+)' | |
178 | ||
179 | _TEST = { | |
180 | 'url': 'http://www.npo.nl/live/npo-1', | |
181 | 'info_dict': { | |
182 | 'id': 'LI_NEDERLAND1_136692', | |
183 | 'display_id': 'npo-1', | |
184 | 'ext': 'mp4', | |
185 | 'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', | |
186 | 'description': 'Livestream', | |
187 | 'is_live': True, | |
188 | }, | |
189 | 'params': { | |
190 | 'skip_download': True, | |
191 | } | |
192 | } | |
193 | ||
194 | def _real_extract(self, url): | |
195 | display_id = self._match_id(url) | |
196 | ||
197 | webpage = self._download_webpage(url, display_id) | |
198 | ||
199 | live_id = self._search_regex( | |
200 | r'data-prid="([^"]+)"', webpage, 'live id') | |
201 | ||
202 | metadata = self._download_json( | |
203 | 'http://e.omroep.nl/metadata/%s' % live_id, | |
204 | display_id, transform_source=strip_jsonp) | |
205 | ||
206 | token = self._get_token(display_id) | |
207 | ||
208 | formats = [] | |
209 | ||
210 | streams = metadata.get('streams') | |
211 | if streams: | |
212 | for stream in streams: | |
213 | stream_type = stream.get('type').lower() | |
214 | if stream_type == 'ss': | |
215 | continue | |
216 | stream_info = self._download_json( | |
217 | 'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp' | |
218 | % (stream.get('url'), token), | |
219 | display_id, 'Downloading %s JSON' % stream_type) | |
220 | if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0): | |
221 | continue | |
222 | stream_url = self._download_json( | |
223 | stream_info['stream'], display_id, | |
224 | 'Downloading %s URL' % stream_type, | |
225 | transform_source=strip_jsonp) | |
226 | if stream_type == 'hds': | |
227 | f4m_formats = self._extract_f4m_formats(stream_url, display_id) | |
228 | # f4m downloader downloads only piece of live stream | |
229 | for f4m_format in f4m_formats: | |
230 | f4m_format['preference'] = -1 | |
231 | formats.extend(f4m_formats) | |
232 | elif stream_type == 'hls': | |
233 | formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4')) | |
234 | else: | |
235 | formats.append({ | |
236 | 'url': stream_url, | |
237 | }) | |
238 | ||
239 | self._sort_formats(formats) | |
240 | ||
241 | return { | |
242 | 'id': live_id, | |
243 | 'display_id': display_id, | |
244 | 'title': self._live_title(metadata['titel']), | |
245 | 'description': metadata['info'], | |
246 | 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], | |
247 | 'formats': formats, | |
248 | 'is_live': True, | |
249 | } | |
250 | ||
251 | ||
d0df9292 JMF |
252 | class TegenlichtVproIE(NPOIE): |
253 | IE_NAME = 'tegenlicht.vpro.nl' | |
254 | _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?' | |
255 | ||
256 | _TESTS = [ | |
257 | { | |
258 | 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html', | |
259 | 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', | |
260 | 'info_dict': { | |
261 | 'id': 'VPWON_1169289', | |
262 | 'ext': 'm4v', | |
263 | 'title': 'Tegenlicht', | |
264 | 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', | |
265 | 'upload_date': '20130225', | |
266 | }, | |
267 | }, | |
268 | ] | |
269 | ||
270 | def _real_extract(self, url): | |
271 | name = url_basename(url) | |
272 | webpage = self._download_webpage(url, name) | |
273 | urn = self._html_search_meta('mediaurn', webpage) | |
274 | info_page = self._download_json( | |
275 | 'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name) | |
276 | return self._get_info(info_page['mid']) |