]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/francetv.py
095bb3954c523852be8d7d09d498d324d429c826
[youtubedl] / youtube_dl / extractor / francetv.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import re
6
7 from .common import InfoExtractor
8 from ..compat import compat_urlparse
9 from ..utils import (
10 clean_html,
11 ExtractorError,
12 int_or_none,
13 parse_duration,
14 determine_ext,
15 )
16 from .dailymotion import DailymotionIE
17
18
19 class FranceTVBaseInfoExtractor(InfoExtractor):
20 def _extract_video(self, video_id, catalogue=None):
21 info = self._download_json(
22 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
23 video_id, 'Downloading video JSON', query={
24 'idDiffusion': video_id,
25 'catalogue': catalogue or '',
26 })
27
28 if info.get('status') == 'NOK':
29 raise ExtractorError(
30 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
31 allowed_countries = info['videos'][0].get('geoblocage')
32 if allowed_countries:
33 georestricted = True
34 geo_info = self._download_json(
35 'http://geo.francetv.fr/ws/edgescape.json', video_id,
36 'Downloading geo restriction info')
37 country = geo_info['reponse']['geo_info']['country_code']
38 if country not in allowed_countries:
39 raise ExtractorError(
40 'The video is not available from your location',
41 expected=True)
42 else:
43 georestricted = False
44
45 formats = []
46 for video in info['videos']:
47 if video['statut'] != 'ONLINE':
48 continue
49 video_url = video['url']
50 if not video_url:
51 continue
52 format_id = video['format']
53 ext = determine_ext(video_url)
54 if ext == 'f4m':
55 if georestricted:
56 # See https://github.com/rg3/youtube-dl/issues/3963
57 # m3u8 urls work fine
58 continue
59 f4m_url = self._download_webpage(
60 'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
61 video_id, 'Downloading f4m manifest token', fatal=False)
62 if f4m_url:
63 formats.extend(self._extract_f4m_formats(
64 f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
65 video_id, f4m_id=format_id, fatal=False))
66 elif ext == 'm3u8':
67 formats.extend(self._extract_m3u8_formats(
68 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
69 m3u8_id=format_id, fatal=False))
70 elif video_url.startswith('rtmp'):
71 formats.append({
72 'url': video_url,
73 'format_id': 'rtmp-%s' % format_id,
74 'ext': 'flv',
75 })
76 else:
77 if self._is_valid_url(video_url, video_id, format_id):
78 formats.append({
79 'url': video_url,
80 'format_id': format_id,
81 })
82 self._sort_formats(formats)
83
84 title = info['titre']
85 subtitle = info.get('sous_titre')
86 if subtitle:
87 title += ' - %s' % subtitle
88 title = title.strip()
89
90 subtitles = {}
91 subtitles_list = [{
92 'url': subformat['url'],
93 'ext': subformat.get('format'),
94 } for subformat in info.get('subtitles', []) if subformat.get('url')]
95 if subtitles_list:
96 subtitles['fr'] = subtitles_list
97
98 return {
99 'id': video_id,
100 'title': title,
101 'description': clean_html(info['synopsis']),
102 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
103 'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
104 'timestamp': int_or_none(info['diffusion']['timestamp']),
105 'formats': formats,
106 'subtitles': subtitles,
107 }
108
109
110 class FranceTVIE(FranceTVBaseInfoExtractor):
111 _VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
112
113 _TESTS = [{
114 'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
115 'info_dict': {
116 'id': '157550144',
117 'ext': 'mp4',
118 'title': '13h15, le dimanche... - Les mystères de Jésus',
119 'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
120 'timestamp': 1494156300,
121 'upload_date': '20170507',
122 },
123 'params': {
124 # m3u8 downloads
125 'skip_download': True,
126 },
127 }, {
128 # france3
129 'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
130 'only_matching': True,
131 }, {
132 # france4
133 'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
134 'only_matching': True,
135 }, {
136 # france5
137 'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
138 'only_matching': True,
139 }, {
140 # franceo
141 'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
142 'only_matching': True,
143 }, {
144 # france2 live
145 'url': 'https://www.france.tv/france-2/direct.html',
146 'only_matching': True,
147 }, {
148 'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
149 'only_matching': True,
150 }, {
151 'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
152 'only_matching': True,
153 }, {
154 'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
155 'only_matching': True,
156 }, {
157 'url': 'https://www.france.tv/142749-rouge-sang.html',
158 'only_matching': True,
159 }]
160
161 def _real_extract(self, url):
162 display_id = self._match_id(url)
163
164 webpage = self._download_webpage(url, display_id)
165
166 catalogue = None
167 video_id = self._search_regex(
168 r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
169 webpage, 'video id', default=None, group='id')
170
171 if not video_id:
172 video_id, catalogue = self._html_search_regex(
173 r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
174 webpage, 'video ID').split('@')
175 return self._extract_video(video_id, catalogue)
176
177
178 class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
179 _VALID_URL = r'https?://embed\.francetv\.fr/*\?.*?\bue=(?P<id>[^&]+)'
180
181 _TEST = {
182 'url': 'http://embed.francetv.fr/?ue=7fd581a2ccf59d2fc5719c5c13cf6961',
183 'info_dict': {
184 'id': 'NI_983319',
185 'ext': 'mp4',
186 'title': 'Le Pen Reims',
187 'upload_date': '20170505',
188 'timestamp': 1493981780,
189 'duration': 16,
190 },
191 }
192
193 def _real_extract(self, url):
194 video_id = self._match_id(url)
195
196 video = self._download_json(
197 'http://api-embed.webservices.francetelevisions.fr/key/%s' % video_id,
198 video_id)
199
200 return self._extract_video(video['video_id'], video.get('catalog'))
201
202
203 class FranceTVInfoIE(FranceTVBaseInfoExtractor):
204 IE_NAME = 'francetvinfo.fr'
205 _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
206
207 _TESTS = [{
208 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
209 'info_dict': {
210 'id': '84981923',
211 'ext': 'mp4',
212 'title': 'Soir 3',
213 'upload_date': '20130826',
214 'timestamp': 1377548400,
215 'subtitles': {
216 'fr': 'mincount:2',
217 },
218 },
219 'params': {
220 # m3u8 downloads
221 'skip_download': True,
222 },
223 }, {
224 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
225 'info_dict': {
226 'id': 'EV_20019',
227 'ext': 'mp4',
228 'title': 'Débat des candidats à la Commission européenne',
229 'description': 'Débat des candidats à la Commission européenne',
230 },
231 'params': {
232 'skip_download': 'HLS (reqires ffmpeg)'
233 },
234 'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
235 }, {
236 'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
237 'md5': 'f485bda6e185e7d15dbc69b72bae993e',
238 'info_dict': {
239 'id': 'NI_173343',
240 'ext': 'mp4',
241 'title': 'Les entreprises familiales : le secret de la réussite',
242 'thumbnail': r're:^https?://.*\.jpe?g$',
243 'timestamp': 1433273139,
244 'upload_date': '20150602',
245 },
246 'params': {
247 # m3u8 downloads
248 'skip_download': True,
249 },
250 }, {
251 'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
252 'md5': 'f485bda6e185e7d15dbc69b72bae993e',
253 'info_dict': {
254 'id': 'NI_657393',
255 'ext': 'mp4',
256 'title': 'Olivier Monthus, réalisateur de "Bretagne, le choix de l’Armor"',
257 'description': 'md5:a3264114c9d29aeca11ced113c37b16c',
258 'thumbnail': r're:^https?://.*\.jpe?g$',
259 'timestamp': 1458300695,
260 'upload_date': '20160318',
261 },
262 'params': {
263 'skip_download': True,
264 },
265 }, {
266 # Dailymotion embed
267 'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html',
268 'md5': 'ee7f1828f25a648addc90cb2687b1f12',
269 'info_dict': {
270 'id': 'x4iiko0',
271 'ext': 'mp4',
272 'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
273 'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016',
274 'timestamp': 1467011958,
275 'upload_date': '20160627',
276 'uploader': 'France Inter',
277 'uploader_id': 'x2q2ez',
278 },
279 'add_ie': ['Dailymotion'],
280 }, {
281 'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
282 'only_matching': True,
283 }]
284
285 def _real_extract(self, url):
286 mobj = re.match(self._VALID_URL, url)
287 page_title = mobj.group('title')
288 webpage = self._download_webpage(url, page_title)
289
290 dailymotion_urls = DailymotionIE._extract_urls(webpage)
291 if dailymotion_urls:
292 return self.playlist_result([
293 self.url_result(dailymotion_url, DailymotionIE.ie_key())
294 for dailymotion_url in dailymotion_urls])
295
296 video_id, catalogue = self._search_regex(
297 (r'id-video=([^@]+@[^"]+)',
298 r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
299 webpage, 'video id').split('@')
300 return self._extract_video(video_id, catalogue)
301
302
303 class GenerationWhatIE(InfoExtractor):
304 IE_NAME = 'france2.fr:generation-what'
305 _VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#]+)'
306
307 _TESTS = [{
308 'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
309 'info_dict': {
310 'id': 'wtvKYUG45iw',
311 'ext': 'mp4',
312 'title': 'Generation What - Garde à vous - FRA',
313 'uploader': 'Generation What',
314 'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
315 'upload_date': '20160411',
316 },
317 }, {
318 'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
319 'only_matching': True,
320 }]
321
322 def _real_extract(self, url):
323 display_id = self._match_id(url)
324 webpage = self._download_webpage(url, display_id)
325 youtube_id = self._search_regex(
326 r"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
327 webpage, 'youtube id')
328 return self.url_result(youtube_id, 'Youtube', youtube_id)
329
330
331 class CultureboxIE(FranceTVBaseInfoExtractor):
332 IE_NAME = 'culturebox.francetvinfo.fr'
333 _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
334
335 _TEST = {
336 'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
337 'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
338 'info_dict': {
339 'id': 'EV_50111',
340 'ext': 'flv',
341 'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
342 'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
343 'upload_date': '20150320',
344 'timestamp': 1426892400,
345 'duration': 2760.9,
346 },
347 }
348
349 def _real_extract(self, url):
350 mobj = re.match(self._VALID_URL, url)
351 name = mobj.group('name')
352
353 webpage = self._download_webpage(url, name)
354
355 if ">Ce live n'est plus disponible en replay<" in webpage:
356 raise ExtractorError('Video %s is not available' % name, expected=True)
357
358 video_id, catalogue = self._search_regex(
359 r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]',
360 webpage, 'video id').split('@')
361
362 return self._extract_video(video_id, catalogue)