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
290
|
import random
import re
import string
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
get_element_by_class,
js_to_json,
str_or_none,
strip_jsonp,
)
class YoukuIE(InfoExtractor):
IE_NAME = 'youku'
IE_DESC = '优酷'
_VALID_URL = r'''(?x)
(?:
https?://(
(?:v|play(?:er)?)\.(?:youku|tudou)\.com/(?:v_show/id_|player\.php/sid/)|
video\.tudou\.com/v/)|
youku:)
(?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
'''
_TESTS = [{
'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
'only_matching': True,
}, {
'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
'note': 'Video protected with password',
'info_dict': {
'id': 'XNjA1NzA2Njgw',
'ext': 'mp4',
'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
'duration': 7264.5,
'thumbnail': r're:^https?://.*',
'uploader': 'FoxJin1006',
'uploader_id': '322014285',
'uploader_url': 'http://i.youku.com/u/UMTI4ODA1NzE0MA==',
'tags': list,
},
'params': {
'videopassword': '100600',
},
'skip': '404',
}, {
# /play/get.json contains streams with "channel_type":"tail"
'url': 'http://v.youku.com/v_show/id_XOTUxMzg4NDMy.html',
'info_dict': {
'id': 'XOTUxMzg4NDMy',
'ext': 'mp4',
'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
'duration': 702.08,
'thumbnail': r're:^https?://.*',
'uploader': '明月庄主moon',
'uploader_id': '38465621',
'uploader_url': 'https://www.youku.com/profile/index/?uid=UMTUzODYyNDg0',
'tags': list,
},
}, {
'url': 'https://v.youku.com/v_show/id_XNTA2NTA0MjA1Mg==.html',
'info_dict': {
'id': 'XNTA2NTA0MjA1Mg',
'ext': 'mp4',
'title': 'Minecraft我的世界：建造超大巨型航空飞机，菜鸟vs高手vs黑客',
'duration': 542.13,
'thumbnail': r're:^https?://.*',
'uploader': '波哥游戏解说',
'uploader_id': '156688084',
'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjI2NzUyMzM2',
'tags': list,
},
}, {
'url': 'https://v.youku.com/v_show/id_XNTE1MzczOTg4MA==.html',
'info_dict': {
'id': 'XNTE1MzczOTg4MA',
'ext': 'mp4',
'title': '国产超A特工片',
'duration': 362.97,
'thumbnail': r're:^https?://.*',
'uploader': '陈晓娟说历史',
'uploader_id': '1640913339',
'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjU2MzY1MzM1Ng==',
'tags': list,
},
}, {
'url': 'https://play.tudou.com/v_show/id_XNjAxNjI2OTU3Ng==.html?',
'info_dict': {
'id': 'XNjAxNjI2OTU3Ng',
'ext': 'mp4',
'title': '阿斯塔意识到哈里杀了人，自己被骗了',
'thumbnail': 'https://m.ykimg.com/0541010164F732752794D4D7B70331D1',
'uploader_id': '88758207',
'tags': [],
'uploader_url': 'https://www.youku.com/profile/index/?uid=UMzU1MDMyODI4',
'uploader': '英美剧场',
'duration': 72.91,
},
}]
@staticmethod
def get_ysuid():
return '%d%s' % (int(time.time()), ''.join(
random.choices(string.ascii_letters, k=3)))
def get_format_name(self, fm):
_dict = {
'3gp': 'h6',
'3gphd': 'h5',
'flv': 'h4',
'flvhd': 'h4',
'mp4': 'h3',
'mp4hd': 'h3',
'mp4hd2': 'h4',
'mp4hd3': 'h4',
'hd2': 'h2',
'hd3': 'h1',
}
return _dict.get(fm)
def _real_extract(self, url):
video_id = self._match_id(url)
self._set_cookie('youku.com', '__ysuid', self.get_ysuid())
self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
_, urlh = self._download_webpage_handle(
'https://log.mmstat.com/eg.js', video_id, 'Retrieving cna info')
# The etag header is '"foobar"'; let's remove the double quotes
cna = urlh.headers['etag'][1:-1]
# request basic data
basic_data_params = {
'vid': video_id,
'ccode': '0524',
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,
}
video_password = self.get_param('videopassword')
if video_password:
basic_data_params['password'] = video_password
headers = {
'Referer': url,
}
headers.update(self.geo_verification_headers())
data = self._download_json(
'https://ups.youku.com/ups/get.json', video_id,
'Downloading JSON metadata',
query=basic_data_params, headers=headers)['data']
error = data.get('error')
if error:
error_note = error.get('note')
if error_note is not None and '因版权原因无法观看此视频' in error_note:
raise ExtractorError(
'Youku said: Sorry, this video is available in China only', expected=True)
elif error_note and '该视频被设为私密' in error_note:
raise ExtractorError(
'Youku said: Sorry, this video is private', expected=True)
else:
msg = 'Youku server reported error %i' % error.get('code')
if error_note is not None:
msg += ': ' + clean_html(error_note)
raise ExtractorError(msg)
# get video title
video_data = data['video']
title = video_data['title']
formats = [{
'url': stream['m3u8_url'],
'format_id': self.get_format_name(stream.get('stream_type')),
'ext': 'mp4',
'protocol': 'm3u8_native',
'filesize': int(stream.get('size')),
'width': stream.get('width'),
'height': stream.get('height'),
} for stream in data['stream'] if stream.get('channel_type') != 'tail']
return {
'id': video_id,
'title': title,
'formats': formats,
'duration': video_data.get('seconds'),
'thumbnail': video_data.get('logo'),
'uploader': video_data.get('username'),
'uploader_id': str_or_none(video_data.get('userid')),
'uploader_url': data.get('uploader', {}).get('homepage'),
'tags': video_data.get('tags'),
}
class YoukuShowIE(InfoExtractor):
_VALID_URL = r'https?://list\.youku\.com/show/id_(?P<id>[0-9a-z]+)\.html'
IE_NAME = 'youku:show'
_TESTS = [{
'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
'info_dict': {
'id': 'zc7c670be07ff11e48b3f',
'title': '花千骨 DVD版',
'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
},
'playlist_count': 50,
}, {
# Episode number not starting from 1
'url': 'http://list.youku.com/show/id_zefbfbd70efbfbd780bef.html',
'info_dict': {
'id': 'zefbfbd70efbfbd780bef',
'title': '超级飞侠3',
'description': 'md5:275715156abebe5ccc2a1992e9d56b98',
},
'playlist_count': 24,
}, {
# Ongoing playlist. The initial page is the last one
'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
'only_matching': True,
}, {
# No data-id value.
'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html',
'only_matching': True,
}, {
# Wrong number of reload_id.
'url': 'http://list.youku.com/show/id_z20eb4acaf5c211e3b2ad.html',
'only_matching': True,
}]
def _extract_entries(self, playlist_data_url, show_id, note, query):
query['callback'] = 'cb'
playlist_data = self._download_json(
playlist_data_url, show_id, query=query, note=note,
transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
if playlist_data is None:
return [None, None]
drama_list = (get_element_by_class('p-drama-grid', playlist_data)
or get_element_by_class('p-drama-half-row', playlist_data))
if drama_list is None:
raise ExtractorError('No episodes found')
video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
return playlist_data, [
self.url_result(self._proto_relative_url(video_url, 'http:'), YoukuIE.ie_key())
for video_url in video_urls]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
entries = []
page_config = self._parse_json(self._search_regex(
r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
show_id, transform_source=js_to_json)
first_page, initial_entries = self._extract_entries(
'http://list.youku.com/show/module', show_id,
note='Downloading initial playlist data page',
query={
'id': page_config['showid'],
'tab': 'showInfo',
})
first_page_reload_id = self._html_search_regex(
r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
# The first reload_id has the same items as first_page
reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
entries.extend(initial_entries)
for idx, reload_id in enumerate(reload_ids):
if reload_id == first_page_reload_id:
continue
_, new_entries = self._extract_entries(
'http://list.youku.com/show/episode', show_id,
note='Downloading playlist data page %d' % (idx + 1),
query={
'id': page_config['showid'],
'stage': reload_id,
})
if new_entries is not None:
entries.extend(new_entries)
desc = self._html_search_meta('description', webpage, fatal=False)
playlist_title = desc.split(',')[0] if desc else None
detail_li = get_element_by_class('p-intro', webpage)
playlist_description = get_element_by_class(
'intro-more', detail_li) if detail_li else None
return self.playlist_result(
entries, show_id, playlist_title, playlist_description)
|
