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
|
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
determine_ext,
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'):
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())
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
class RaiPlayIE(RaiBaseIE):
_VALID_URL = r'https?://(?:www\.)?raiplay\.it/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.html'
_TESTS = [{
'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter',
'md5': '340aa3b7afb54bfd14a8c11786450d76',
'info_dict': {
'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66',
'ext': 'mp4',
'title': 'La Casa Bianca',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': r're:^Rai.+',
'description': 're:^[A-Za-z]+'
}
}, {
'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
'md5': 'ed4da3d70ccf8129a33ab16b34d20ab8',
'info_dict': {
'id': 'efebe701-969c-4593-92f3-285f0d1ce750',
'ext': 'mp4',
'title': 'Gazebo - #gazebotraindesi',
'thumbnail': r're:^https?://.*\.png$',
'uploader': r're:^Rai.+',
'description': r're:^[A-Za-z]+'
}
}, {
'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 - Report del 07/04/2014',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': r're:^Rai.+',
'description': r're:^[A-Za-z]+'
}
}]
_RESOLUTION = '600x400'
def _real_extract(self, url):
video_id = self._match_id(url)
# remove query and fragment part from url
canonical_url = compat_urlparse.urljoin(url, compat_urlparse.urlparse(url).path)
webpage = self._download_webpage(canonical_url, video_id)
media = self._download_json('%s?json' % canonical_url,
video_id, 'Downloading video JSON')
thumbnails = []
if 'images' in media:
for _, value in media.get('images').items():
if value:
thumbnails.append({
'url': value.replace('[RESOLUTION]', self._RESOLUTION)
})
if 'video' not in media:
raise ExtractorError('No video found')
video = media.get('video')
duration = parse_duration(video.get('duration')),
formats = self._extract_relinker_formats(video.get('contentUrl'), video_id)
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage).replace(' - video - RaiPlay', ''),
'description': self._og_search_description(webpage),
'uploader': media.get('channel'),
'duration': duration,
'thumbnails': thumbnails,
'formats': formats
}
class RaiIE(RaiBaseIE):
_VALID_URL = r'https?://.+\.(?:rai|rainews)\.it/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
_TESTS = [{
# subdomain test case
'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
'info_dict': {
'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
'ext': 'mp4',
'title': 'TG PRIMO TEMPO',
'upload_date': '20140612',
'duration': 1758,
'thumbnail': r're:^https?://.*\.jpg$'
}
}, {
# rainews test case
'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\" ',
'upload_date': '20161103',
'thumbnail': r're:^https?://.*\.png$',
'description': r're:^[A-Za-z]+'
}
}, {
# with media information
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
'md5': '11959b4e44fa74de47011b5799490adf',
'info_dict': {
'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
'ext': 'mp4',
'title': 'TG1 ore 20:00 del 03/11/2016',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20161103',
'description': r're:^[A-Za-z]+'
}
}, {
# drawMediaRaiTV test case
'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',
},
}, {
# Embedded content item ID
'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
'info_dict': {
'id': 'd80d4b70-3812-4501-a888-92edec729f00',
'ext': 'mp4',
'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
'upload_date': r're:\d{8}',
'description': r're:.+',
},
}, {
'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': 'mp4',
'title': 'La diretta di Rainews24',
},
}]
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)
try:
return self._extract_from_content_id(video_id, url)
except ExtractorError:
# no media data, only direct relinker
pass
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,
}
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')
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),
})
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,
}
|
