1 from __future__ import unicode_literals
5 from .common import InfoExtractor
20 class RaiTVIE(InfoExtractor):
21 _VALID_URL = r'http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+media/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
24 'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
25 'md5': '96382709b61dd64a6b88e0f791e6df4c',
27 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
29 'title': 'Report del 07/04/2014',
30 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
31 'upload_date': '20140407',
36 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
37 'md5': 'd9751b78eac9710d62c2447b224dea39',
39 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
41 'title': 'TG PRIMO TEMPO',
42 'upload_date': '20140612',
47 'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
48 'md5': '35cf7c229f22eeef43e48b5cf923bef0',
50 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
52 'title': 'State of the Net, Antonella La Carpia: regole virali',
53 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
54 'upload_date': '20140613',
59 'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
61 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
63 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
64 'description': 'Edizione delle ore 20:30 ',
66 'skip': 'invalid urls',
69 'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
70 'md5': '496ab63e420574447f70d02578333437',
72 'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
74 'title': 'Il Candidato - Primo episodio: "Le Primarie"',
75 'description': 'md5:364b604f7db50594678f483353164fb8',
76 'upload_date': '20140923',
82 def _real_extract(self, url):
83 video_id = self._match_id(url)
84 media = self._download_json(
85 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % video_id,
86 video_id, 'Downloading video JSON')
89 for image_type in ('image', 'image_medium', 'image_300'):
90 thumbnail_url = media.get(image_type)
98 media_type = media['type']
99 if 'Audio' in media_type:
101 'format_id': media.get('formatoAudio'),
102 'url': media['audioUrl'],
103 'ext': media.get('formatoAudio'),
105 elif 'Video' in media_type:
107 return xml.replace(' tag elementi', '').replace('>/', '</')
109 relinker = self._download_xml(
110 media['mediaUri'] + '&output=43', video_id, transform_source=fix_xml)
114 for element in relinker.findall('element'):
115 media_url = xpath_text(element, 'url')
116 ext = determine_ext(media_url)
117 content_type = xpath_text(element, 'content-type')
119 formats.extend(self._extract_m3u8_formats(
120 media_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls',
123 formats.extend(self._extract_f4m_formats(
124 media_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
125 video_id, f4m_id='hds', fatal=False))
128 elif content_type.startswith('video/'):
129 bitrate = int_or_none(xpath_text(element, 'bitrate'))
132 'tbr': bitrate if bitrate > 0 else None,
133 'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
135 elif content_type.startswith('image/'):
140 self._sort_formats(formats)
143 webpage = self._download_webpage(url, video_id)
144 subtitles = self._get_subtitles(video_id, webpage)
146 raise ExtractorError('not a media file')
150 'title': media['name'],
151 'description': media.get('desc'),
152 'thumbnails': thumbnails,
153 'uploader': media.get('author'),
154 'upload_date': unified_strdate(media.get('date')),
155 'duration': parse_duration(media.get('length')),
157 'subtitles': subtitles,
160 def _get_subtitles(self, video_id, webpage):
162 m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
164 captions = m.group('captions')
167 if captions.endswith(STL_EXT):
168 captions = captions[:-len(STL_EXT)] + SRT_EXT
171 'url': 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions),
176 class RaiIE(InfoExtractor):
177 _VALID_URL = r'http://(?:.+?\.)?(?: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'
180 'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
181 'md5': 'e0e7a8a131e249d1aa0ebf270d1d8db7',
183 'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
186 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
187 'upload_date': '20141221',
193 def suitable(cls, url):
194 return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)
196 def _real_extract(self, url):
197 video_id = self._match_id(url)
198 webpage = self._download_webpage(url, video_id)
200 iframe_url = self._search_regex(
201 [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
202 r'drawMediaRaiTV\(["\'](.+?)["\']'],
204 if not iframe_url.startswith('http'):
205 iframe_url = compat_urlparse.urljoin(url, iframe_url)
206 return self.url_result(iframe_url)