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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
xpath_text,
find_xpath_attr,
determine_ext,
int_or_none,
unified_strdate,
xpath_element,
ExtractorError,
determine_protocol,
)
class RadioCanadaIE(InfoExtractor):
IE_NAME = 'radiocanada'
_VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'
_TEST = {
'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
'info_dict': {
'id': '7184272',
'ext': 'mp4',
'title': 'Le parcours du tireur capté sur vidéo',
'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
'upload_date': '20141023',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
app_code, video_id = re.match(self._VALID_URL, url).groups()
device_types = ['ipad', 'android']
if app_code != 'toutv':
device_types.append('flash')
formats = []
# TODO: extract f4m formats
# f4m formats can be extracted using flashhd device_type but they produce unplayable file
for device_type in device_types:
v_data = self._download_xml(
'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx',
video_id, note='Downloading %s XML' % device_type, query={
'appCode': app_code,
'idMedia': video_id,
'connectionType': 'broadband',
'multibitrate': 'true',
'deviceType': device_type,
# paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
'paysJ391wsHjbOJwvCs26toz': 'CA',
'bypasslock': 'NZt5K62gRqfc',
}, fatal=False)
v_url = xpath_text(v_data, 'url')
if not v_url:
continue
if v_url == 'null':
raise ExtractorError('%s said: %s' % (
self.IE_NAME, xpath_text(v_data, 'message')), expected=True)
ext = determine_ext(v_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
v_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
v_url, video_id, f4m_id='hds', fatal=False))
else:
ext = determine_ext(v_url)
bitrates = xpath_element(v_data, 'bitrates')
for url_e in bitrates.findall('url'):
tbr = int_or_none(url_e.get('bitrate'))
if not tbr:
continue
f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
protocol = determine_protocol({'url': f_url})
formats.append({
'format_id': '%s-%d' % (protocol, tbr),
'url': f_url,
'ext': 'flv' if protocol == 'rtmp' else ext,
'protocol': protocol,
'width': int_or_none(url_e.get('width')),
'height': int_or_none(url_e.get('height')),
'tbr': tbr,
})
if protocol == 'rtsp':
base_url = self._search_regex(
r'rtsp://([^?]+)', f_url, 'base url', default=None)
if base_url:
base_url = 'http://' + base_url
formats.extend(self._extract_m3u8_formats(
base_url + '/playlist.m3u8', video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
formats.extend(self._extract_f4m_formats(
base_url + '/manifest.f4m', video_id,
f4m_id='hds', fatal=False))
self._sort_formats(formats)
metadata = self._download_xml(
'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
video_id, note='Downloading metadata XML', query={
'appCode': app_code,
'idMedia': video_id,
})
def get_meta(name):
el = find_xpath_attr(metadata, './/Meta', 'name', name)
return el.text if el is not None else None
return {
'id': video_id,
'title': get_meta('Title'),
'description': get_meta('Description') or get_meta('ShortDescription'),
'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
'duration': int_or_none(get_meta('length')),
'series': get_meta('Emission'),
'season_number': int_or_none('SrcSaison'),
'episode_number': int_or_none('SrcEpisode'),
'upload_date': unified_strdate(get_meta('Date')),
'formats': formats,
}
class RadioCanadaAudioVideoIE(InfoExtractor):
'radiocanada:audiovideo'
_VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P<id>[0-9]+)'
_TEST = {
'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam',
'info_dict': {
'id': '7527184',
'ext': 'mp4',
'title': 'Barack Obama au Vietnam',
'description': 'Les États-Unis lèvent l\'embargo sur la vente d\'armes qui datait de la guerre du Vietnam',
'upload_date': '20160523',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
return self.url_result('radiocanada:medianet:%s' % self._match_id(url))
|
