2 from __future__ import unicode_literals
6 from .common import InfoExtractor
20 class RadioCanadaIE(InfoExtractor):
21 IE_NAME = 'radiocanada'
22 _VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'
24 'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
28 'title': 'Le parcours du tireur capté sur vidéo',
29 'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
30 'upload_date': '20141023',
34 'skip_download': True,
38 def _real_extract(self, url):
39 url, smuggled_data = unsmuggle_url(url, {})
40 app_code, video_id = re.match(self._VALID_URL, url).groups()
42 metadata = self._download_xml(
43 'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
44 video_id, note='Downloading metadata XML', query={
50 el = find_xpath_attr(metadata, './/Meta', 'name', name)
51 return el.text if el is not None else None
53 if get_meta('protectionType'):
54 raise ExtractorError('This video is DRM protected.', expected=True)
56 device_types = ['ipad']
58 device_types.append('flash')
59 device_types.append('android')
63 # TODO: extract f4m formats
64 # f4m formats can be extracted using flashhd device_type but they produce unplayable file
65 for device_type in device_types:
66 validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx'
70 'connectionType': 'broadband',
71 'multibitrate': 'true',
72 'deviceType': device_type,
75 validation_url = 'https://services.radio-canada.ca/media/validation/v2/'
76 query.update(smuggled_data)
79 # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
80 'paysJ391wsHjbOJwvCs26toz': 'CA',
81 'bypasslock': 'NZt5K62gRqfc',
83 v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False)
84 v_url = xpath_text(v_data, 'url')
88 error = xpath_text(v_data, 'message')
90 ext = determine_ext(v_url)
92 formats.extend(self._extract_m3u8_formats(
93 v_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
95 formats.extend(self._extract_f4m_formats(
96 v_url, video_id, f4m_id='hds', fatal=False))
98 ext = determine_ext(v_url)
99 bitrates = xpath_element(v_data, 'bitrates')
100 for url_e in bitrates.findall('url'):
101 tbr = int_or_none(url_e.get('bitrate'))
104 f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
105 protocol = determine_protocol({'url': f_url})
107 'format_id': '%s-%d' % (protocol, tbr),
109 'ext': 'flv' if protocol == 'rtmp' else ext,
110 'protocol': protocol,
111 'width': int_or_none(url_e.get('width')),
112 'height': int_or_none(url_e.get('height')),
115 mobj = re.match(r'(?P<url>rtmp://[^/]+/[^/]+)/(?P<playpath>[^?]+)(?P<auth>\?.+)', f_url)
118 'url': mobj.group('url') + mobj.group('auth'),
119 'play_path': mobj.group('playpath'),
122 if protocol == 'rtsp':
123 base_url = self._search_regex(
124 r'rtsp://([^?]+)', f_url, 'base url', default=None)
126 base_url = 'http://' + base_url
127 formats.extend(self._extract_m3u8_formats(
128 base_url + '/playlist.m3u8', video_id, 'mp4',
129 'm3u8_native', m3u8_id='hls', fatal=False))
130 formats.extend(self._extract_f4m_formats(
131 base_url + '/manifest.f4m', video_id,
132 f4m_id='hds', fatal=False))
133 if not formats and error:
134 raise ExtractorError(
135 '%s said: %s' % (self.IE_NAME, error), expected=True)
136 self._sort_formats(formats)
139 closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5')
140 if closed_caption_url:
142 'url': closed_caption_url,
143 'ext': determine_ext(closed_caption_url, 'vtt'),
148 'title': get_meta('Title'),
149 'description': get_meta('Description') or get_meta('ShortDescription'),
150 'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
151 'duration': int_or_none(get_meta('length')),
152 'series': get_meta('Emission'),
153 'season_number': int_or_none('SrcSaison'),
154 'episode_number': int_or_none('SrcEpisode'),
155 'upload_date': unified_strdate(get_meta('Date')),
156 'subtitles': subtitles,
161 class RadioCanadaAudioVideoIE(InfoExtractor):
162 'radiocanada:audiovideo'
163 _VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P<id>[0-9]+)'
165 'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam',
169 'title': 'Barack Obama au Vietnam',
170 'description': 'Les États-Unis lèvent l\'embargo sur la vente d\'armes qui datait de la guerre du Vietnam',
171 'upload_date': '20160523',
175 'skip_download': True,
179 def _real_extract(self, url):
180 return self.url_result('radiocanada:medianet:%s' % self._match_id(url))