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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
|
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_request
)
from ..utils import (
sanitize_url_path_consecutive_slashes,
ExtractorError,
)
class SohuIE(InfoExtractor):
_VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
_TESTS = [{
'note': 'This video is available only in Mainland China',
'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
'md5': '29175c8cadd8b5cc4055001e85d6b372',
'info_dict': {
'id': '382479172',
'ext': 'mp4',
'title': 'MV：Far East Movement《The Illest》',
},
'skip': 'On available in China',
}, {
'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
'md5': '699060e75cf58858dd47fb9c03c42cfb',
'info_dict': {
'id': '409385080',
'ext': 'mp4',
'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》',
}
}, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
'md5': '9bf34be48f2f4dadcb226c74127e203c',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【爱范品】第31期：MWC见不到的奇葩手机',
}
}, {
'note': 'Multipart video',
'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
'info_dict': {
'id': '78910339',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
},
'playlist': [{
'md5': 'bdbfb8f39924725e6589c146bc1883ad',
'info_dict': {
'id': '78910339_part1',
'ext': 'mp4',
'duration': 294,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
'info_dict': {
'id': '78910339_part2',
'ext': 'mp4',
'duration': 300,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
'md5': '8407e634175fdac706766481b9443450',
'info_dict': {
'id': '78910339_part3',
'ext': 'mp4',
'duration': 150,
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}]
}, {
'note': 'Video with title containing dash',
'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
'info_dict': {
'id': '78932792',
'ext': 'mp4',
'title': 'youtube-dl testing video',
},
'params': {
'skip_download': True
}
}]
def _real_extract(self, url):
def _fetch_data(vid_id, mytv=False):
if mytv:
base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
else:
base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
req = compat_urllib_request.Request(base_data_url + vid_id)
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
if cn_verification_proxy:
req.add_header('Ytdl-request-proxy', cn_verification_proxy)
return self._download_json(
req, video_id,
'Downloading JSON data for %s' % vid_id)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mytv = mobj.group('mytv') is not None
webpage = self._download_webpage(url, video_id)
title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage))
vid = self._html_search_regex(
r'var vid ?= ?["\'](\d+)["\']',
webpage, 'video path')
vid_data = _fetch_data(vid, mytv)
if vid_data['play'] != 1:
if vid_data.get('status') == 12:
raise ExtractorError(
'Sohu said: There\'s something wrong in the video.',
expected=True)
else:
raise ExtractorError(
'Sohu said: The video is only licensed to users in Mainland China.',
expected=True)
formats_json = {}
for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
vid_id = vid_data['data'].get('%sVid' % format_id)
if not vid_id:
continue
vid_id = compat_str(vid_id)
formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv)
part_count = vid_data['data']['totalBlocks']
playlist = []
for i in range(part_count):
formats = []
for format_id, format_data in formats_json.items():
allot = format_data['allot']
prot = format_data['prot']
data = format_data['data']
clips_url = data['clipsURL']
su = data['su']
part_str = self._download_webpage(
'http://%s/?prot=%s&file=%s&new=%s' %
(allot, prot, clips_url[i], su[i]),
video_id,
'Downloading %s video URL part %d of %d'
% (format_id, i + 1, part_count))
part_info = part_str.split('|')
video_url = sanitize_url_path_consecutive_slashes(
'%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
formats.append({
'url': video_url,
'format_id': format_id,
'filesize': data['clipsBytes'][i],
'width': data['width'],
'height': data['height'],
'fps': data['fps'],
})
self._sort_formats(formats)
playlist.append({
'id': '%s_part%d' % (video_id, i + 1),
'title': title,
'duration': vid_data['data']['clipsDuration'][i],
'formats': formats,
})
if len(playlist) == 1:
info = playlist[0]
info['id'] = video_id
else:
info = {
'_type': 'multi_video',
'entries': playlist,
'id': video_id,
'title': title,
}
return info
|
