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
|
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
InAdvancePagedList,
float_or_none,
unescapeHTML,
)
class TudouIE(InfoExtractor):
IE_NAME = 'tudou'
_VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P<id>[\w-]{11})'
_TESTS = [{
'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
'md5': '140a49ed444bd22f93330985d8475fcb',
'info_dict': {
'id': '159448201',
'ext': 'f4v',
'title': '卡马乔国足开大脚长传冲吊集锦',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1372113489000,
'description': '卡马乔卡家军，开大脚先进战术不完全集锦！',
'duration': 289.04,
'view_count': int,
'filesize': int,
}
}, {
'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
'info_dict': {
'id': '117049447',
'ext': 'f4v',
'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1349207518000,
'description': 'md5:294612423894260f2dcd5c6c04fe248b',
'duration': 5478.33,
'view_count': int,
'filesize': int,
}
}]
_PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
def _url_for_id(self, video_id, quality=None):
info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)
if quality:
info_url += '&hd' + quality
xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page')
final_url = xml_data.text
return final_url
def _real_extract(self, url):
video_id = self._match_id(url)
item_data = self._download_json(
'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id)
youku_vcode = item_data.get('vcode')
if youku_vcode:
return self.url_result('youku:' + youku_vcode, ie='Youku')
title = unescapeHTML(item_data['kw'])
description = item_data.get('desc')
thumbnail_url = item_data.get('pic')
view_count = int_or_none(item_data.get('playTimes'))
timestamp = int_or_none(item_data.get('pt'))
segments = self._parse_json(item_data['itemSegs'], video_id)
# It looks like the keys are the arguments that have to be passed as
# the hd field in the request url, we pick the higher
# Also, filter non-number qualities (see issue #3643).
quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
key=lambda k: int(k))[-1]
parts = segments[quality]
len_parts = len(parts)
if len_parts > 1:
self.to_screen('%s: found %s parts' % (video_id, len_parts))
def part_func(partnum):
part = parts[partnum]
part_id = part['k']
final_url = self._url_for_id(part_id, quality)
ext = (final_url.split('?')[0]).split('.')[-1]
return [{
'id': '%s' % part_id,
'url': final_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail_url,
'description': description,
'view_count': view_count,
'timestamp': timestamp,
'duration': float_or_none(part.get('seconds'), 1000),
'filesize': int_or_none(part.get('size')),
'http_headers': {
'Referer': self._PLAYER_URL,
},
}]
entries = InAdvancePagedList(part_func, len_parts, 1)
return {
'_type': 'multi_video',
'entries': entries,
'id': video_id,
'title': title,
}
class TudouPlaylistIE(InfoExtractor):
IE_NAME = 'tudou:playlist'
_VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P<id>[\w-]{11})\.html'
_TESTS = [{
'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html',
'info_dict': {
'id': 'zzdE77v6Mmo',
},
'playlist_mincount': 209,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
playlist_data = self._download_json(
'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id)
entries = [self.url_result(
'http://www.tudou.com/programs/view/%s' % item['icode'],
'Tudou', item['icode'],
item['kw']) for item in playlist_data['items']]
return self.playlist_result(entries, playlist_id)
class TudouAlbumIE(InfoExtractor):
IE_NAME = 'tudou:album'
_VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P<id>[\w-]{11})'
_TESTS = [{
'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html',
'info_dict': {
'id': 'v5qckFJvNJg',
},
'playlist_mincount': 45,
}]
def _real_extract(self, url):
album_id = self._match_id(url)
album_data = self._download_json(
'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id)
entries = [self.url_result(
'http://www.tudou.com/programs/view/%s' % item['icode'],
'Tudou', item['icode'],
item['kw']) for item in album_data['items']]
return self.playlist_result(entries, album_id)
|
