aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/rai.py
blob: 1f0fcd6094c223315a9dedee674087e6f040e735 (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
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    determine_ext,
    ExtractorError,
    find_xpath_attr,
    fix_xml_ampersands,
    int_or_none,
    parse_duration,
    unified_strdate,
    update_url_query,
    xpath_text,
)


class RaiBaseIE(InfoExtractor):
    def _extract_relinker_formats(self, relinker_url, video_id):
        formats = []

        for platform in ('mon', 'flash', 'native'):
            headers = {}
            # TODO: rename --cn-verification-proxy
            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
            if cn_verification_proxy:
                headers['Ytdl-request-proxy'] = cn_verification_proxy

            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=headers)

            media_url = find_xpath_attr(relinker, './url', 'type', 'content').text
            if media_url == 'http://download.rai.it/video_no_available.mp4':
                self.raise_geo_restricted()

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

            if ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    media_url, video_id, 'mp4', 'm3u8_native',
                    m3u8_id='hls', fatal=False))
            elif ext == 'f4m':
                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',
                })

        return formats

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

        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(base_url, thumbnail_url),
                })

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

        subtitles = {}
        captions = media.get('subtitlesUrl')
        if captions:
            STL_EXT = '.stl'
            SRT_EXT = '.srt'
            if captions.endswith(STL_EXT):
                captions = captions[:-len(STL_EXT)] + SRT_EXT
            subtitles['it'] = [{
                'ext': 'srt',
                'url': captions,
            }]

        return {
            'id': content_id,
            'title': media['name'],
            'description': media.get('desc'),
            'thumbnails': thumbnails,
            'uploader': media.get('author'),
            'upload_date': unified_strdate(media.get('date')),
            'duration': parse_duration(media.get('length')),
            'formats': formats,
            'subtitles': subtitles,
        }


class RaiTVIE(RaiBaseIE):
    _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+(?:media|ondemand)/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
    _TESTS = [
        {
            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
            'md5': '8970abf8caf8aef4696e7b1f2adfc696',
            'info_dict': {
                'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
                'ext': 'mp4',
                'title': 'Report del 07/04/2014',
                'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
                'upload_date': '20140407',
                'duration': 6160,
                'thumbnail': 're:^https?://.*\.jpg$',
            }
        },
        {
            # no m3u8 stream
            'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
            # HDS download, MD5 is unstable
            'info_dict': {
                'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
                'ext': 'flv',
                'title': 'TG PRIMO TEMPO',
                'upload_date': '20140612',
                'duration': 1758,
                'thumbnail': 're:^https?://.*\.jpg$',
            },
            'skip': 'Geo-restricted to Italy',
        },
        {
            'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
            'md5': '35cf7c229f22eeef43e48b5cf923bef0',
            'info_dict': {
                'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
                'ext': 'mp4',
                'title': 'State of the Net, Antonella La Carpia: regole virali',
                'description': 'md5:b0ba04a324126903e3da7763272ae63c',
                'upload_date': '20140613',
            },
            'skip': 'Error 404',
        },
        {
            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
            'info_dict': {
                'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
                'ext': 'mp4',
                'title': 'Alluvione in Sardegna e dissesto idrogeologico',
                'description': 'Edizione delle ore 20:30 ',
            },
            'skip': 'invalid urls',
        },
        {
            'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
            'md5': 'e57493e1cb8bc7c564663f363b171847',
            'info_dict': {
                'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
                'ext': 'mp4',
                'title': 'Il Candidato - Primo episodio: "Le Primarie"',
                'description': 'md5:364b604f7db50594678f483353164fb8',
                'upload_date': '20140923',
                'duration': 386,
                'thumbnail': 're:^https?://.*\.jpg$',
            }
        },
    ]

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

        return self._extract_from_content_id(video_id, url)


class RaiIE(RaiBaseIE):
    _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
    _TESTS = [
        {
            'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
            'md5': '2dd727e61114e1ee9c47f0da6914e178',
            'info_dict': {
                'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
                'ext': 'mp4',
                'title': 'Il pacco',
                'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
                'upload_date': '20141221',
            },
        },
        {
            # Direct relinker URL
            'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
            # HDS live stream, MD5 is unstable
            'info_dict': {
                'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
                'ext': 'flv',
                'title': 'EuroNews',
            },
            'skip': 'Geo-restricted to Italy',
        },
        {
            # Embedded content item ID
            'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
            'md5': '84c1135ce960e8822ae63cec34441d63',
            'info_dict': {
                'id': '0960e765-62c8-474a-ac4b-7eb3e2be39c8',
                'ext': 'mp4',
                'title': 'TG1 ore 20:00 del 02/07/2016',
                'upload_date': '20160702',
            },
        },
        {
            'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
            # HDS live stream, MD5 is unstable
            'info_dict': {
                'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
                'ext': 'flv',
                'title': 'La diretta di Rainews24',
            },
        },
    ]

    @classmethod
    def suitable(cls, url):
        return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)

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

        iframe_url = self._search_regex(
            [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
             r'drawMediaRaiTV\(["\'](.+?)["\']'],
            webpage, 'iframe', default=None)
        if iframe_url:
            if not iframe_url.startswith('http'):
                iframe_url = compat_urlparse.urljoin(url, iframe_url)
            return self.url_result(iframe_url)

        content_item_id = self._search_regex(
            r'initEdizione\((?P<q1>[\'"])ContentItem-(?P<content_id>[^\'"]+)(?P=q1)',
            webpage, 'content item ID', group='content_id', default=None)
        if content_item_id:
            return self._extract_from_content_id(content_item_id, url)

        relinker_url = compat_urlparse.urljoin(url, self._search_regex(
            r'(?:var\s+videoURL|mediaInfo\.mediaUri)\s*=\s*(?P<q1>[\'"])(?P<url>(https?:)?//mediapolis\.rai\.it/relinker/relinkerServlet\.htm\?cont=\d+)(?P=q1)',
            webpage, 'relinker URL', group='url'))
        formats = self._extract_relinker_formats(relinker_url, video_id)
        self._sort_formats(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)

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
        }