]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rts.py
Prepare for release.
[youtubedl] / youtube_dl / extractor / rts.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import (
8 compat_str,
9 )
10 from ..utils import (
11 int_or_none,
12 parse_duration,
13 parse_iso8601,
14 unescapeHTML,
15 )
16
17
18 class RTSIE(InfoExtractor):
19 IE_DESC = 'RTS.ch'
20 _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))'
21
22 _TESTS = [
23 {
24 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
25 'md5': '753b877968ad8afaeddccc374d4256a5',
26 'info_dict': {
27 'id': '3449373',
28 'display_id': 'les-enfants-terribles',
29 'ext': 'mp4',
30 'duration': 1488,
31 'title': 'Les Enfants Terribles',
32 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
33 'uploader': 'Divers',
34 'upload_date': '19680921',
35 'timestamp': -40280400,
36 'thumbnail': 're:^https?://.*\.image',
37 'view_count': int,
38 },
39 },
40 {
41 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
42 'md5': 'c148457a27bdc9e5b1ffe081a7a8337b',
43 'info_dict': {
44 'id': '5624067',
45 'display_id': 'entre-ciel-et-mer',
46 'ext': 'mp4',
47 'duration': 3720,
48 'title': 'Les yeux dans les cieux - Mon homard au Canada',
49 'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
50 'uploader': 'Passe-moi les jumelles',
51 'upload_date': '20140404',
52 'timestamp': 1396635300,
53 'thumbnail': 're:^https?://.*\.image',
54 'view_count': int,
55 },
56 },
57 {
58 'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
59 'md5': 'b4326fecd3eb64a458ba73c73e91299d',
60 'info_dict': {
61 'id': '5745975',
62 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
63 'ext': 'mp4',
64 'duration': 48,
65 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
66 'description': 'Hockey - Playoff',
67 'uploader': 'Hockey',
68 'upload_date': '20140403',
69 'timestamp': 1396556882,
70 'thumbnail': 're:^https?://.*\.image',
71 'view_count': int,
72 },
73 'skip': 'Blocked outside Switzerland',
74 },
75 {
76 'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
77 'md5': '9bb06503773c07ce83d3cbd793cebb91',
78 'info_dict': {
79 'id': '5745356',
80 'display_id': 'londres-cachee-par-un-epais-smog',
81 'ext': 'mp4',
82 'duration': 33,
83 'title': 'Londres cachée par un épais smog',
84 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
85 'uploader': 'Le Journal en continu',
86 'upload_date': '20140403',
87 'timestamp': 1396537322,
88 'thumbnail': 're:^https?://.*\.image',
89 'view_count': int,
90 },
91 },
92 {
93 'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
94 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
95 'info_dict': {
96 'id': '5706148',
97 'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
98 'ext': 'mp3',
99 'duration': 123,
100 'title': '"Urban Hippie", de Damien Krisl',
101 'description': 'Des Hippies super glam.',
102 'upload_date': '20140403',
103 'timestamp': 1396551600,
104 },
105 },
106 {
107 'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
108 'md5': '968777c8779e5aa2434be96c54e19743',
109 'info_dict': {
110 'id': '6348260',
111 'display_id': 'le-19h30',
112 'ext': 'mp4',
113 'duration': 1796,
114 'title': 'Le 19h30',
115 'description': '',
116 'uploader': 'Le 19h30',
117 'upload_date': '20141201',
118 'timestamp': 1417458600,
119 'thumbnail': 're:^https?://.*\.image',
120 'view_count': int,
121 },
122 },
123 {
124 'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280',
125 'only_matching': True,
126 }
127 ]
128
129 def _real_extract(self, url):
130 m = re.match(self._VALID_URL, url)
131 video_id = m.group('id') or m.group('id_new')
132 display_id = m.group('display_id') or m.group('display_id_new')
133
134 def download_json(internal_id):
135 return self._download_json(
136 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
137 display_id)
138
139 all_info = download_json(video_id)
140
141 # video_id extracted out of URL is not always a real id
142 if 'video' not in all_info and 'audio' not in all_info:
143 page = self._download_webpage(url, display_id)
144 internal_id = self._html_search_regex(
145 r'<(?:video|audio) data-id="([0-9]+)"', page,
146 'internal video id')
147 all_info = download_json(internal_id)
148
149 info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
150
151 upload_timestamp = parse_iso8601(info.get('broadcast_date'))
152 duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
153 if isinstance(duration, compat_str):
154 duration = parse_duration(duration)
155 view_count = info.get('plays')
156 thumbnail = unescapeHTML(info.get('preview_image_url'))
157
158 def extract_bitrate(url):
159 return int_or_none(self._search_regex(
160 r'-([0-9]+)k\.', url, 'bitrate', default=None))
161
162 formats = [{
163 'format_id': fid,
164 'url': furl,
165 'tbr': extract_bitrate(furl),
166 } for fid, furl in info['streams'].items()]
167
168 if 'media' in info:
169 formats.extend([{
170 'format_id': '%s-%sk' % (media['ext'], media['rate']),
171 'url': 'http://download-video.rts.ch/%s' % media['url'],
172 'tbr': media['rate'] or extract_bitrate(media['url']),
173 } for media in info['media'] if media.get('rate')])
174
175 self._sort_formats(formats)
176
177 return {
178 'id': video_id,
179 'display_id': display_id,
180 'formats': formats,
181 'title': info['title'],
182 'description': info.get('intro'),
183 'duration': duration,
184 'view_count': view_count,
185 'uploader': info.get('programName'),
186 'timestamp': upload_timestamp,
187 'thumbnail': thumbnail,
188 }