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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
|
import base64
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
traverse_obj,
try_get,
unified_timestamp,
url_or_none,
urljoin,
)
class SohuIE(InfoExtractor):
_VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
# Sohu videos give different MD5 sums on Travis CI and my machine
_TESTS = [{
'note': 'This video is available only in Mainland China',
'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
'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',
'info_dict': {
'id': '409385080',
'ext': 'mp4',
'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》',
},
'skip': 'no longer available',
}, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【爱范品】第31期：MWC见不到的奇葩手机',
'uploader': '爱范儿视频',
'duration': 213,
'timestamp': 1425519600,
'upload_date': '20150305',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M10/83/FA/MTAuMTAuODguODA=/6_14cbccdde5eg104SysCutcloud_78693464_7_0b.jpg',
'tags': ['爱范儿', '爱范品', 'MWC', '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',
'uploader': '小苍cany',
'duration': 744.0,
'timestamp': 1426269360,
'upload_date': '20150313',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M11/89/57/MTAuMTAuODguODA=/6_14cea022a1dg102SysCutcloud_78910339_8_0b.jpg',
'tags': ['小苍MM', '英雄联盟', '实战秘籍'],
},
'playlist': [{
'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',
},
}, {
'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',
},
}, {
'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',
'duration': 360,
'timestamp': 1426348620,
'upload_date': '20150314',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M02/8A/00/MTAuMTAuODguNzk=/6_14cee1be192g102SysCutcloud_78932792_7_7b.jpg',
'tags': [],
},
'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='
return self._download_json(
base_data_url + vid_id, video_id,
f'Downloading JSON data for {vid_id}',
headers=self.geo_verification_headers())
mobj = self._match_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'( - 高清正版在线观看)? - 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(
f'{self.IE_NAME} said: There\'s something wrong in the video.',
expected=True)
else:
self.raise_geo_restricted(
f'{self.IE_NAME} said: The video is only licensed to users in Mainland China.')
formats_json = {}
for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
vid_id = vid_data['data'].get(f'{format_id}Vid')
if not vid_id:
continue
vid_id = 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']
data = format_data['data']
clip_url = traverse_obj(data, (('clipsURL', 'mp4PlayUrl'), i, {url_or_none}), get_all=False)
if not clip_url:
raise ExtractorError(f'Unable to extract url for clip {i}')
su = data['su']
video_url = 'newflv.sohu.ccgslb.net'
cdn_id = None
retries = 0
while 'newflv.sohu.ccgslb.net' in video_url:
params = {
'prot': 9,
'file': clip_url,
'new': su[i],
'prod': 'h5n',
'rb': 1,
}
if cdn_id is not None:
params['idc'] = cdn_id
download_note = f'Downloading {format_id} video URL part {i + 1} of {part_count}'
if retries > 0:
download_note += f' (retry #{retries})'
part_info = self._parse_json(self._download_webpage(
f'http://{allot}/?{urllib.parse.urlencode(params)}',
video_id, download_note), video_id)
video_url = part_info['url']
cdn_id = part_info.get('nid')
retries += 1
if retries > 5:
raise ExtractorError('Failed to get video URL')
formats.append({
'url': video_url,
'format_id': format_id,
'filesize': int_or_none(
try_get(data, lambda x: x['clipsBytes'][i])),
'width': int_or_none(data.get('width')),
'height': int_or_none(data.get('height')),
'fps': int_or_none(data.get('fps')),
})
playlist.append({
'id': f'{video_id}_part{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,
'duration': traverse_obj(vid_data, ('data', 'totalDuration', {float_or_none})),
}
if mytv:
publish_time = unified_timestamp(self._search_regex(
r'publishTime:\s*["\'](\d+-\d+-\d+ \d+:\d+)["\']', webpage, 'publish time', fatal=False))
else:
publish_time = traverse_obj(vid_data, ('tv_application_time', {unified_timestamp}))
return {
'timestamp': publish_time - 8 * 3600 if publish_time else None,
**traverse_obj(vid_data, {
'alt_title': ('data', 'subName', {str}),
'uploader': ('wm_data', 'wm_username', {str}),
'thumbnail': ('data', 'coverImg', {url_or_none}),
'tags': ('data', 'tag', {str.split}),
}),
**info,
}
class SohuVIE(InfoExtractor):
_VALID_URL = r'https?://tv\.sohu\.com/v/(?P<id>[\w=-]+)\.html(?:$|[#?])'
_TESTS = [{
'note': 'Multipart video',
'url': 'https://tv.sohu.com/v/MjAyMzA2MTQvbjYwMTMxNTE5Mi5zaHRtbA==.html',
'info_dict': {
'id': '601315192',
'title': '《淬火丹心》第1集',
'alt_title': '“点天灯”发生事故',
'duration': 2701.692,
'timestamp': 1686758040,
'upload_date': '20230614',
'thumbnail': 'http://photocdn.tv.sohu.com/img/20230614/vrsa_hor_1686738763256_454010551.jpg',
},
'playlist_mincount': 9,
'skip': 'Only available in China',
}, {
'url': 'https://tv.sohu.com/v/dXMvMjMyNzk5ODg5Lzc4NjkzNDY0LnNodG1s.html',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【爱范品】第31期：MWC见不到的奇葩手机',
'uploader': '爱范儿视频',
'duration': 213,
'timestamp': 1425519600,
'upload_date': '20150305',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M10/83/FA/MTAuMTAuODguODA=/6_14cbccdde5eg104SysCutcloud_78693464_7_0b.jpg',
'tags': ['爱范儿', '爱范品', 'MWC', '手机'],
},
}, {
'note': 'Multipart video',
'url': 'https://tv.sohu.com/v/dXMvMjQyNTYyMTYzLzc4OTEwMzM5LnNodG1s.html?src=pl',
'info_dict': {
'id': '78910339',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
'uploader': '小苍cany',
'duration': 744.0,
'timestamp': 1426269360,
'upload_date': '20150313',
'thumbnail': 'http://e3f49eaa46b57.cdn.sohucs.com//group1/M11/89/57/MTAuMTAuODguODA=/6_14cea022a1dg102SysCutcloud_78910339_8_0b.jpg',
'tags': ['小苍MM', '英雄联盟', '实战秘籍'],
},
'playlist_mincount': 3,
}]
def _real_extract(self, url):
encoded_id = self._match_id(url)
path = base64.urlsafe_b64decode(encoded_id).decode()
subdomain = 'tv' if re.match(r'\d+/n\d+\.shtml', path) else 'my.tv'
return self.url_result(urljoin(f'http://{subdomain}.sohu.com/', path), SohuIE)
|
