aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/francetv.py
blob: 095bb3954c523852be8d7d09d498d324d429c826 (plain)
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
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
# coding: utf-8

from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    clean_html,
    ExtractorError,
    int_or_none,
    parse_duration,
    determine_ext,
)
from .dailymotion import DailymotionIE


class FranceTVBaseInfoExtractor(InfoExtractor):
    def _extract_video(self, video_id, catalogue=None):
        info = self._download_json(
            'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
            video_id, 'Downloading video JSON', query={
                'idDiffusion': video_id,
                'catalogue': catalogue or '',
            })

        if info.get('status') == 'NOK':
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
        allowed_countries = info['videos'][0].get('geoblocage')
        if allowed_countries:
            georestricted = True
            geo_info = self._download_json(
                'http://geo.francetv.fr/ws/edgescape.json', video_id,
                'Downloading geo restriction info')
            country = geo_info['reponse']['geo_info']['country_code']
            if country not in allowed_countries:
                raise ExtractorError(
                    'The video is not available from your location',
                    expected=True)
        else:
            georestricted = False

        formats = []
        for video in info['videos']:
            if video['statut'] != 'ONLINE':
                continue
            video_url = video['url']
            if not video_url:
                continue
            format_id = video['format']
            ext = determine_ext(video_url)
            if ext == 'f4m':
                if georestricted:
                    # See https://github.com/rg3/youtube-dl/issues/3963
                    # m3u8 urls work fine
                    continue
                f4m_url = self._download_webpage(
                    'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
                    video_id, 'Downloading f4m manifest token', fatal=False)
                if f4m_url:
                    formats.extend(self._extract_f4m_formats(
                        f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
                        video_id, f4m_id=format_id, fatal=False))
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
                    m3u8_id=format_id, fatal=False))
            elif video_url.startswith('rtmp'):
                formats.append({
                    'url': video_url,
                    'format_id': 'rtmp-%s' % format_id,
                    'ext': 'flv',
                })
            else:
                if self._is_valid_url(video_url, video_id, format_id):
                    formats.append({
                        'url': video_url,
                        'format_id': format_id,
                    })
        self._sort_formats(formats)

        title = info['titre']
        subtitle = info.get('sous_titre')
        if subtitle:
            title += ' - %s' % subtitle
        title = title.strip()

        subtitles = {}
        subtitles_list = [{
            'url': subformat['url'],
            'ext': subformat.get('format'),
        } for subformat in info.get('subtitles', []) if subformat.get('url')]
        if subtitles_list:
            subtitles['fr'] = subtitles_list

        return {
            'id': video_id,
            'title': title,
            'description': clean_html(info['synopsis']),
            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
            'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
            'timestamp': int_or_none(info['diffusion']['timestamp']),
            'formats': formats,
            'subtitles': subtitles,
        }


class FranceTVIE(FranceTVBaseInfoExtractor):
    _VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'

    _TESTS = [{
        'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
        'info_dict': {
            'id': '157550144',
            'ext': 'mp4',
            'title': '13h15, le dimanche... - Les mystères de Jésus',
            'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
            'timestamp': 1494156300,
            'upload_date': '20170507',
        },
        'params': {
            # m3u8 downloads
            'skip_download': True,
        },
    }, {
        # france3
        'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
        'only_matching': True,
    }, {
        # france4
        'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
        'only_matching': True,
    }, {
        # france5
        'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
        'only_matching': True,
    }, {
        # franceo
        'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
        'only_matching': True,
    }, {
        # france2 live
        'url': 'https://www.france.tv/france-2/direct.html',
        'only_matching': True,
    }, {
        'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
        'only_matching': True,
    }, {
        'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
        'only_matching': True,
    }, {
        'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
        'only_matching': True,
    }, {
        'url': 'https://www.france.tv/142749-rouge-sang.html',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)

        webpage = self._download_webpage(url, display_id)

        catalogue = None
        video_id = self._search_regex(
            r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
            webpage, 'video id', default=None, group='id')

        if not video_id:
            video_id, catalogue = self._html_search_regex(
                r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
                webpage, 'video ID').split('@')
        return self._extract_video(video_id, catalogue)


class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
    _VALID_URL = r'https?://embed\.francetv\.fr/*\?.*?\bue=(?P<id>[^&]+)'

    _TEST = {
        'url': 'http://embed.francetv.fr/?ue=7fd581a2ccf59d2fc5719c5c13cf6961',
        'info_dict': {
            'id': 'NI_983319',
            'ext': 'mp4',
            'title': 'Le Pen Reims',
            'upload_date': '20170505',
            'timestamp': 1493981780,
            'duration': 16,
        },
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)

        video = self._download_json(
            'http://api-embed.webservices.francetelevisions.fr/key/%s' % video_id,
            video_id)

        return self._extract_video(video['video_id'], video.get('catalog'))


class FranceTVInfoIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'francetvinfo.fr'
    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'

    _TESTS = [{
        'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
        'info_dict': {
            'id': '84981923',
            'ext': 'mp4',
            'title': 'Soir 3',
            'upload_date': '20130826',
            'timestamp': 1377548400,
            'subtitles': {
                'fr': 'mincount:2',
            },
        },
        'params': {
            # m3u8 downloads
            'skip_download': True,
        },
    }, {
        'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
        'info_dict': {
            'id': 'EV_20019',
            'ext': 'mp4',
            'title': 'Débat des candidats à la Commission européenne',
            'description': 'Débat des candidats à la Commission européenne',
        },
        'params': {
            'skip_download': 'HLS (reqires ffmpeg)'
        },
        'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
    }, {
        'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
        'md5': 'f485bda6e185e7d15dbc69b72bae993e',
        'info_dict': {
            'id': 'NI_173343',
            'ext': 'mp4',
            'title': 'Les entreprises familiales : le secret de la réussite',
            'thumbnail': r're:^https?://.*\.jpe?g$',
            'timestamp': 1433273139,
            'upload_date': '20150602',
        },
        'params': {
            # m3u8 downloads
            'skip_download': True,
        },
    }, {
        'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
        'md5': 'f485bda6e185e7d15dbc69b72bae993e',
        'info_dict': {
            'id': 'NI_657393',
            'ext': 'mp4',
            'title': 'Olivier Monthus, réalisateur de "Bretagne, le choix de l’Armor"',
            'description': 'md5:a3264114c9d29aeca11ced113c37b16c',
            'thumbnail': r're:^https?://.*\.jpe?g$',
            'timestamp': 1458300695,
            'upload_date': '20160318',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # Dailymotion embed
        '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',
        'md5': 'ee7f1828f25a648addc90cb2687b1f12',
        'info_dict': {
            'id': 'x4iiko0',
            'ext': 'mp4',
            'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
            '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',
            'timestamp': 1467011958,
            'upload_date': '20160627',
            'uploader': 'France Inter',
            'uploader_id': 'x2q2ez',
        },
        'add_ie': ['Dailymotion'],
    }, {
        'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        page_title = mobj.group('title')
        webpage = self._download_webpage(url, page_title)

        dailymotion_urls = DailymotionIE._extract_urls(webpage)
        if dailymotion_urls:
            return self.playlist_result([
                self.url_result(dailymotion_url, DailymotionIE.ie_key())
                for dailymotion_url in dailymotion_urls])

        video_id, catalogue = self._search_regex(
            (r'id-video=([^@]+@[^"]+)',
             r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
            webpage, 'video id').split('@')
        return self._extract_video(video_id, catalogue)


class GenerationWhatIE(InfoExtractor):
    IE_NAME = 'france2.fr:generation-what'
    _VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#]+)'

    _TESTS = [{
        'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
        'info_dict': {
            'id': 'wtvKYUG45iw',
            'ext': 'mp4',
            'title': 'Generation What - Garde à vous - FRA',
            'uploader': 'Generation What',
            'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
            'upload_date': '20160411',
        },
    }, {
        'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)
        youtube_id = self._search_regex(
            r"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
            webpage, 'youtube id')
        return self.url_result(youtube_id, 'Youtube', youtube_id)


class CultureboxIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'culturebox.francetvinfo.fr'
    _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'

    _TEST = {
        'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
        'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
        'info_dict': {
            'id': 'EV_50111',
            'ext': 'flv',
            'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
            'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
            'upload_date': '20150320',
            'timestamp': 1426892400,
            'duration': 2760.9,
        },
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        name = mobj.group('name')

        webpage = self._download_webpage(url, name)

        if ">Ce live n'est plus disponible en replay<" in webpage:
            raise ExtractorError('Video %s is not available' % name, expected=True)

        video_id, catalogue = self._search_regex(
            r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]',
            webpage, 'video id').split('@')

        return self._extract_video(video_id, catalogue)