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
|
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
HEADRequest,
unified_strdate,
url_basename,
qualities,
)
class CanalplusIE(InfoExtractor):
IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
_VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
_SITE_ID_MAP = {
'canalplus.fr': 'cplus',
'piwiplus.fr': 'teletoon',
'd8.tv': 'd8',
'itele.fr': 'itele',
}
_TESTS = [{
'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
'md5': 'b3481d7ca972f61e37420798d0a9d934',
'info_dict': {
'id': '1263092',
'ext': 'flv',
'title': 'Le Zapping - 13/05/15',
'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
'upload_date': '20150513',
},
}, {
'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
'info_dict': {
'id': '1108190',
'ext': 'flv',
'title': 'Le labyrinthe - Boing super ranger',
'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
'upload_date': '20140724',
},
'skip': 'Only works from France',
}, {
'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
'info_dict': {
'id': '966289',
'ext': 'flv',
'title': 'Campagne intime - Documentaire exceptionnel',
'description': 'md5:d2643b799fb190846ae09c61e59a859f',
'upload_date': '20131108',
},
'skip': 'videos get deleted after a while',
}, {
'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
'info_dict': {
'id': '1213714',
'ext': 'flv',
'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
'description': 'md5:8216206ec53426ea6321321f3b3c16db',
'upload_date': '20150211',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.groupdict().get('id')
site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
# Beware, some subclasses do not define an id group
display_id = url_basename(mobj.group('path'))
if video_id is None:
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
doc = self._download_xml(info_url, video_id, 'Downloading video XML')
video_info = [video for video in doc if video.find('ID').text == video_id][0]
media = video_info.find('MEDIA')
infos = video_info.find('INFOS')
preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
fmt_url = next(iter(media.find('VIDEOS'))).text
if '/geo' in fmt_url.lower():
response = self._request_webpage(
HEADRequest(fmt_url), video_id,
'Checking if the video is georestricted')
if '/blocage' in response.geturl():
raise ExtractorError(
'The video is not available in your country',
expected=True)
formats = []
for fmt in media.find('VIDEOS'):
format_url = fmt.text
if not format_url:
continue
format_id = fmt.tag
if format_id == 'HLS':
hls_formats = self._extract_m3u8_formats(format_url, video_id, 'mp4')
for fmt in hls_formats:
fmt['preference'] = preference(format_id)
formats.extend(hls_formats)
elif format_id == 'HDS':
hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
for fmt in hds_formats:
fmt['preference'] = preference(format_id)
formats.extend(hds_formats)
else:
formats.append({
'url': format_url,
'format_id': format_id,
'preference': preference(format_id),
})
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
infos.find('TITRAGE/SOUS_TITRE').text),
'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
'thumbnail': media.find('IMAGES/GRAND').text,
'description': infos.find('DESCRIPTION').text,
'view_count': int(infos.find('NB_VUES').text),
'like_count': int(infos.find('NB_LIKES').text),
'comment_count': int(infos.find('NB_COMMENTS').text),
'formats': formats,
}
|
