aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/francetv.py
blob: fd3e7aa7b50035f02fd463c5629bfe859c20ec8b (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
# encoding: utf-8

from __future__ import unicode_literals

import re
import json

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


class FranceTVBaseInfoExtractor(InfoExtractor):
    def _extract_video(self, video_id, catalogue):
        info = self._download_json(
            'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
            % (video_id, catalogue),
            video_id, 'Downloading video JSON')

        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
                video_url_parsed = compat_urllib_parse_urlparse(video_url)
                f4m_url = self._download_webpage(
                    'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
                    video_id, 'Downloading f4m manifest token', fatal=False)
                if f4m_url:
                    formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
            elif video_url.startswith('rtmp'):
                formats.append({
                    'url': video_url,
                    'format_id': 'rtmp-%s' % format_id,
                    'ext': 'flv',
                    'preference': 1,
                })
            else:
                formats.append({
                    'url': video_url,
                    'format_id': format_id,
                    'preference': -1,
                })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': info['titre'],
            'description': clean_html(info['synopsis']),
            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
            'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']),
            'timestamp': int_or_none(info['diffusion']['timestamp']),
            'formats': formats,
        }


class PluzzIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'pluzz.francetv.fr'
    _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'

    # Can't use tests, videos expire in 7 days

    def _real_extract(self, url):
        title = re.match(self._VALID_URL, url).group(1)
        webpage = self._download_webpage(url, title)
        video_id = self._search_regex(
            r'data-diffusion="(\d+)"', webpage, 'ID')
        return self._extract_video(video_id, 'Pluzz')


class FranceTvInfoIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'francetvinfo.fr'
    _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'

    _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': 'flv',
            'title': 'Soir 3',
            'upload_date': '20130826',
            'timestamp': 1377548400,
        },
    }, {
        '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.',
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        page_title = mobj.group('title')
        webpage = self._download_webpage(url, page_title)
        video_id, catalogue = self._search_regex(
            r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
        return self._extract_video(video_id, catalogue)


class FranceTVIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'francetv'
    IE_DESC = 'France 2, 3, 4, 5 and Ô'
    _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
        (?:
            emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
        |   (emissions?|jt)/(?P<key>[^/?]+)
        )'''

    _TESTS = [
        # france2
        {
            'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
            'md5': 'c03fc87cb85429ffd55df32b9fc05523',
            'info_dict': {
                'id': '109169362',
                'ext': 'flv',
                'title': '13h15, le dimanche...',
                'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
                'upload_date': '20140914',
                'timestamp': 1410693600,
            },
        },
        # france3
        {
            'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
            'md5': '679bb8f8921f8623bd658fa2f8364da0',
            'info_dict': {
                'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
                'ext': 'mp4',
                'title': 'Le scandale du prix des médicaments',
                'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
                'upload_date': '20131113',
                'timestamp': 1384380000,
            },
        },
        # france4
        {
            'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
            'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
            'info_dict': {
                'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
                'ext': 'mp4',
                'title': 'Hero Corp Making of - Extrait 1',
                'description': 'md5:c87d54871b1790679aec1197e73d650a',
                'upload_date': '20131106',
                'timestamp': 1383766500,
            },
        },
        # france5
        {
            'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
            'md5': '78f0f4064f9074438e660785bbf2c5d9',
            'info_dict': {
                'id': '108961659',
                'ext': 'flv',
                'title': 'C à dire ?!',
                'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
                'upload_date': '20140915',
                'timestamp': 1410795000,
            },
        },
        # franceo
        {
            'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013',
            'md5': '52f0bfe202848b15915a2f39aaa8981b',
            'info_dict': {
                'id': '108634970',
                'ext': 'flv',
                'title': 'Infô Afrique',
                'description': 'md5:ebf346da789428841bee0fd2a935ea55',
                'upload_date': '20140915',
                'timestamp': 1410822000,
            },
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id'))
        video_id, catalogue = self._html_search_regex(
            r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"',
            webpage, 'video ID').split('@')
        return self._extract_video(video_id, catalogue)


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

    _TEST = {
        'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
        'info_dict': {
            'id': 'k7FJX8VBcvvLmX4wA5Q',
            'ext': 'mp4',
            'title': 'Génération Quoi - Garde à Vous',
            'uploader': 'Génération Quoi',
        },
        'params': {
            # It uses Dailymotion
            'skip_download': True,
        },
    }

    def _real_extract(self, url):
        display_id = self._match_id(url)
        info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
        info_json = self._download_webpage(info_url, display_id)
        info = json.loads(info_json)
        return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
                               ie='Dailymotion')


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',
        'info_dict': {
            'id': 'EV_50111',
            'ext': 'mp4',
            'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
            'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
            'upload_date': '20150320',
            'timestamp': 1426892400,
            'duration': 2760.9,
        },
        'params': {
            'skip_download': True,
        },
    }

    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'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')

        return self._extract_video(video_id, catalogue)