]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/srgssr.py
246970c4d98a7d4592deadc1c7744c1504ccefef
[youtubedl] / youtube_dl / extractor / srgssr.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 parse_iso8601,
10 qualities,
11 )
12
13
14 class SRGSSRIE(InfoExtractor):
15 _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
16
17 _ERRORS = {
18 'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
19 'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.',
20 # 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
21 'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.',
22 'LEGAL': 'The video cannot be transmitted for legal reasons.',
23 'STARTDATE': 'This video is not yet available. Please try again later.',
24 }
25
26 def get_media_data(self, bu, media_type, media_id):
27 media_data = self._download_json(
28 'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
29 media_id)[media_type.capitalize()]
30
31 if media_data.get('block') and media_data['block'] in self._ERRORS:
32 raise ExtractorError('%s said: %s' % (
33 self.IE_NAME, self._ERRORS[media_data['block']]), expected=True)
34
35 return media_data
36
37 def _real_extract(self, url):
38 bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
39
40 if bu == 'rts':
41 return self.url_result('rts:%s' % media_id, 'RTS')
42
43 media_data = self.get_media_data(bu, media_type, media_id)
44
45 metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
46 title = metadata['title']
47 description = metadata.get('description')
48 created_date = media_data.get('createdDate') or metadata.get('createdDate')
49 timestamp = parse_iso8601(created_date)
50
51 thumbnails = [{
52 'id': image.get('id'),
53 'url': image['url'],
54 } for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]
55
56 preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
57 formats = []
58 for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
59 protocol = source.get('@protocol')
60 for asset in source['url']:
61 asset_url = asset['text']
62 quality = asset['@quality']
63 format_id = '%s-%s' % (protocol, quality)
64 if protocol == 'HTTP-HDS':
65 formats.extend(self._extract_f4m_formats(
66 asset_url + '?hdcore=3.4.0', media_id,
67 f4m_id=format_id, fatal=False))
68 elif protocol == 'HTTP-HLS':
69 formats.extend(self._extract_m3u8_formats(
70 asset_url, media_id, 'mp4', 'm3u8_native',
71 m3u8_id=format_id, fatal=False))
72 else:
73 formats.append({
74 'format_id': format_id,
75 'url': asset_url,
76 'preference': preference(quality),
77 'ext': 'flv' if protocol == 'RTMP' else None,
78 })
79 self._sort_formats(formats)
80
81 return {
82 'id': media_id,
83 'title': title,
84 'description': description,
85 'timestamp': timestamp,
86 'thumbnails': thumbnails,
87 'formats': formats,
88 }
89
90
91 class SRGSSRPlayIE(InfoExtractor):
92 IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
93 _VALID_URL = r'https?://(?:(?:www|play)\.)?(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/[^/]+/(?P<type>video|audio)/[^?]+\?id=(?P<id>[0-9a-f\-]{36}|\d+)'
94
95 _TESTS = [{
96 'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
97 'md5': '4cd93523723beff51bb4bee974ee238d',
98 'info_dict': {
99 'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
100 'ext': 'm4v',
101 'upload_date': '20130701',
102 'title': 'Snowden beantragt Asyl in Russland',
103 'timestamp': 1372713995,
104 }
105 }, {
106 # No Speichern (Save) button
107 'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
108 'md5': '0a274ce38fda48c53c01890651985bc6',
109 'info_dict': {
110 'id': '677f5829-e473-4823-ac83-a1087fe97faa',
111 'ext': 'flv',
112 'upload_date': '20130710',
113 'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
114 'description': 'md5:88604432b60d5a38787f152dec89cd56',
115 'timestamp': 1373493600,
116 },
117 }, {
118 'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
119 'info_dict': {
120 'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
121 'ext': 'mp3',
122 'upload_date': '20151013',
123 'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
124 'timestamp': 1444750398,
125 },
126 'params': {
127 # rtmp download
128 'skip_download': True,
129 },
130 }, {
131 'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
132 'md5': '67a2a9ae4e8e62a68d0e9820cc9782df',
133 'info_dict': {
134 'id': '6348260',
135 'display_id': '6348260',
136 'ext': 'mp4',
137 'duration': 1796,
138 'title': 'Le 19h30',
139 'description': '',
140 'uploader': '19h30',
141 'upload_date': '20141201',
142 'timestamp': 1417458600,
143 'thumbnail': 're:^https?://.*\.image',
144 'view_count': int,
145 },
146 'params': {
147 # m3u8 download
148 'skip_download': True,
149 }
150 }]
151
152 def _real_extract(self, url):
153 bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
154 # other info can be extracted from url + '&layout=json'
155 return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')