aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/rai.py
blob: ecb628f1494e8e18e2a7da21cf14d068f60c3425 (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
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_urlparse,
    compat_str,
)
from ..utils import (
    ExtractorError,
    determine_ext,
    find_xpath_attr,
    fix_xml_ampersands,
    GeoRestrictedError,
    int_or_none,
    parse_duration,
    remove_start,
    strip_or_none,
    try_get,
    unified_strdate,
    unified_timestamp,
    update_url_query,
    urljoin,
    xpath_text,
)


class RaiBaseIE(InfoExtractor):
    _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
    _GEO_COUNTRIES = ['IT']
    _GEO_BYPASS = False

    def _extract_relinker_info(self, relinker_url, video_id):
        if not re.match(r'https?://', relinker_url):
            return {'formats': [{'url': relinker_url}]}

        formats = []
        geoprotection = None
        is_live = None
        duration = None

        for platform in ('mon', 'flash', 'native'):
            relinker = self._download_xml(
                relinker_url, video_id,
                note='Downloading XML metadata for platform %s' % platform,
                transform_source=fix_xml_ampersands,
                query={'output': 45, 'pl': platform},
                headers=self.geo_verification_headers())

            if not geoprotection:
                geoprotection = xpath_text(
                    relinker, './geoprotection', default=None) == 'Y'

            if not is_live:
                is_live = xpath_text(
                    relinker, './is_live', default=None) == 'Y'
            if not duration:
                duration = parse_duration(xpath_text(
                    relinker, './duration', default=None))

            url_elem = find_xpath_attr(relinker, './url', 'type', 'content')
            if url_elem is None:
                continue

            media_url = url_elem.text

            # This does not imply geo restriction (e.g.
            # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
            if '/video_no_available.mp4' in media_url:
                continue

            ext = determine_ext(media_url)
            if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
                continue

            if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon':
                formats.extend(self._extract_m3u8_formats(
                    media_url, video_id, 'mp4', 'm3u8_native',
                    m3u8_id='hls', fatal=False))
            elif ext == 'f4m' or platform == 'flash':
                manifest_url = update_url_query(
                    media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'),
                    {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'})
                formats.extend(self._extract_f4m_formats(
                    manifest_url, video_id, f4m_id='hds', fatal=False))
            else:
                bitrate = int_or_none(xpath_text(relinker, 'bitrate'))
                formats.append({
                    'url': media_url,
                    'tbr': bitrate if bitrate > 0 else None,
                    'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
                })

        if not formats and geoprotection is True:
            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)

        return dict((k, v) for k, v in {
            'is_live': is_live,
            'duration': duration,
            'formats': formats,
        }.items() if v is not None)

    @staticmethod
    def _extract_subtitles(url, subtitle_url):
        subtitles = {}
        if subtitle_url and isinstance(subtitle_url, compat_str):
            subtitle_url = urljoin(url, subtitle_url)
            STL_EXT = '.stl'
            SRT_EXT = '.srt'
            subtitles['it'] = [{
                'ext': 'stl',
                'url': subtitle_url,
            }]
            if subtitle_url.endswith(STL_EXT):
                srt_url = subtitle_url[:-len(STL_EXT)] + SRT_EXT
                subtitles['it'].append({
                    'ext': 'srt',
                    'url': srt_url,
                })
        return subtitles


class RaiPlayIE(RaiBaseIE):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE
    _TESTS = [{
        'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
        'md5': '8970abf8caf8aef4696e7b1f2adfc696',
        'info_dict': {
            'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
            'ext': 'mp4',
            'title': 'Report del 07/04/2014',
            'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014',
            'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'Rai Gulp',
            'duration': 6160,
            'series': 'Report',
            'season': '2013/14',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        base, video_id = re.match(self._VALID_URL, url).groups()

        media = self._download_json(
            base + '.json', video_id, 'Downloading video JSON')

        title = media['name']

        video = media['video']

        relinker_info = self._extract_relinker_info(video['content_url'], video_id)
        self._sort_formats(relinker_info['formats'])

        thumbnails = []
        for _, value in media.get('images', {}).items():
            if value:
                thumbnails.append({
                    'url': urljoin(url, value),
                })

        date_published = media.get('date_published')
        time_published = media.get('time_published')
        if date_published and time_published:
            date_published += ' ' + time_published

        subtitles = self._extract_subtitles(url, video.get('subtitles'))

        program_info = media.get('program_info') or {}
        season = media.get('season')

        info = {
            'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
            'display_id': video_id,
            'title': self._live_title(title) if relinker_info.get(
                'is_live') else title,
            'alt_title': strip_or_none(media.get('subtitle')),
            'description': media.get('description'),
            'uploader': strip_or_none(media.get('channel')),
            'creator': strip_or_none(media.get('editor') or None),
            'duration': parse_duration(video.get('duration')),
            'timestamp': unified_timestamp(date_published),
            'thumbnails': thumbnails,
            'series': program_info.get('name'),
            'season_number': int_or_none(season),
            'season': season if (season and not season.isdigit()) else None,
            'episode': media.get('episode_title'),
            'episode_number': int_or_none(media.get('episode')),
            'subtitles': subtitles,
        }

        info.update(relinker_info)
        return info


class RaiPlayLiveIE(RaiPlayIE):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
    _TESTS = [{
        'url': 'http://www.raiplay.it/dirette/rainews24',
        'info_dict': {
            'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
            'display_id': 'rainews24',
            'ext': 'mp4',
            'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
            'uploader': 'Rai News 24',
            'creator': 'Rai News 24',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }]


class RaiPlayPlaylistIE(InfoExtractor):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
    _TESTS = [{
        'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
        'info_dict': {
            'id': 'nondirloalmiocapo',
            'title': 'Non dirlo al mio capo',
            'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
        },
        'playlist_mincount': 12,
    }]

    def _real_extract(self, url):
        base, playlist_id = re.match(self._VALID_URL, url).groups()

        program = self._download_json(
            base + '.json', playlist_id, 'Downloading program JSON')

        entries = []
        for b in (program.get('blocks') or []):
            for s in (b.get('sets') or []):
                s_id = s.get('id')
                if not s_id:
                    continue
                medias = self._download_json(
                    '%s/%s.json' % (base, s_id), s_id,
                    'Downloading content set JSON', fatal=False)
                if not medias:
                    continue
                for m in (medias.get('items') or []):
                    path_id = m.get('path_id')
                    if not path_id:
                        continue
                    video_url = urljoin(url, path_id)
                    entries.append(self.url_result(
                        video_url, ie=RaiPlayIE.ie_key(),
                        video_id=RaiPlayIE._match_id(video_url)))

        return self.playlist_result(
            entries, playlist_id, program.get('name'),
            try_get(program, lambda x: x['program_info']['description']))


class RaiIE(RaiBaseIE):
    _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
    _TESTS = [{
        # var uniquename = "ContentItem-..."
        # data-id="ContentItem-..."
        'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
        'info_dict': {
            'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
            'ext': 'mp4',
            'title': 'TG PRIMO TEMPO',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 1758,
            'upload_date': '20140612',
        },
        'skip': 'This content is available only in Italy',
    }, {
        # with ContentItem in many metas
        'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
        'info_dict': {
            'id': '1632c009-c843-4836-bb65-80c33084a64b',
            'ext': 'mp4',
            'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
            'description': 'I film in uscita questa settimana.',
            'thumbnail': r're:^https?://.*\.png$',
            'duration': 833,
            'upload_date': '20161103',
        }
    }, {
        # with ContentItem in og:url
        'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
        'md5': '6865dd00cf0bbf5772fdd89d59bd768a',
        'info_dict': {
            'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
            'ext': 'mp4',
            'title': 'TG1 ore 20:00 del 03/11/2016',
            'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 2214,
            'upload_date': '20161103',
        }
    }, {
        # initEdizione('ContentItem-...'
        'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
        'info_dict': {
            'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
            'ext': 'mp4',
            'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
            'duration': 2274,
            'upload_date': '20170401',
        },
        'skip': 'Changes daily',
    }, {
        # HLS live stream with ContentItem in og:url
        'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
        'info_dict': {
            'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
            'ext': 'mp4',
            'title': 'La diretta di Rainews24',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # Direct MMS URL
        'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
        'only_matching': True,
    }, {
        'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
        'only_matching': True,
    }]

    def _extract_from_content_id(self, content_id, url):
        media = self._download_json(
            'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id,
            content_id, 'Downloading video JSON')

        title = media['name'].strip()

        media_type = media['type']
        if 'Audio' in media_type:
            relinker_info = {
                'formats': [{
                    'format_id': media.get('formatoAudio'),
                    'url': media['audioUrl'],
                    'ext': media.get('formatoAudio'),
                }]
            }
        elif 'Video' in media_type:
            relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)
        else:
            raise ExtractorError('not a media file')

        self._sort_formats(relinker_info['formats'])

        thumbnails = []
        for image_type in ('image', 'image_medium', 'image_300'):
            thumbnail_url = media.get(image_type)
            if thumbnail_url:
                thumbnails.append({
                    'url': compat_urlparse.urljoin(url, thumbnail_url),
                })

        subtitles = self._extract_subtitles(url, media.get('subtitlesUrl'))

        info = {
            'id': content_id,
            'title': title,
            'description': strip_or_none(media.get('desc')),
            'thumbnails': thumbnails,
            'uploader': media.get('author'),
            'upload_date': unified_strdate(media.get('date')),
            'duration': parse_duration(media.get('length')),
            'subtitles': subtitles,
        }

        info.update(relinker_info)

        return info

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

        webpage = self._download_webpage(url, video_id)

        content_item_id = None

        content_item_url = self._html_search_meta(
            ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
             'twitter:player', 'jsonlink'), webpage, default=None)
        if content_item_url:
            content_item_id = self._search_regex(
                r'ContentItem-(%s)' % self._UUID_RE, content_item_url,
                'content item id', default=None)

        if not content_item_id:
            content_item_id = self._search_regex(
                r'''(?x)
                    (?:
                        (?:initEdizione|drawMediaRaiTV)\(|
                        <(?:[^>]+\bdata-id|var\s+uniquename)=
                    )
                    (["\'])
                    (?:(?!\1).)*\bContentItem-(?P<id>%s)
                ''' % self._UUID_RE,
                webpage, 'content item id', default=None, group='id')

        content_item_ids = set()
        if content_item_id:
            content_item_ids.add(content_item_id)
        if video_id not in content_item_ids:
            content_item_ids.add(video_id)

        for content_item_id in content_item_ids:
            try:
                return self._extract_from_content_id(content_item_id, url)
            except GeoRestrictedError:
                raise
            except ExtractorError:
                pass

        relinker_url = self._proto_relative_url(self._search_regex(
            r'''(?x)
                (?:
                    var\s+videoURL|
                    mediaInfo\.mediaUri
                )\s*=\s*
                ([\'"])
                (?P<url>
                    (?:https?:)?
                    //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
                    (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
            ''',
            webpage, 'relinker URL', group='url'))

        relinker_info = self._extract_relinker_info(
            urljoin(url, relinker_url), video_id)
        self._sort_formats(relinker_info['formats'])

        title = self._search_regex(
            r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1',
            webpage, 'title', group='title',
            default=None) or self._og_search_title(webpage)

        info = {
            'id': video_id,
            'title': title,
        }

        info.update(relinker_info)

        return info