2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import ExtractorError
12 compat_urllib_request,
16 class YoukuIE(InfoExtractor):
21 http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
23 (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
27 'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
28 'md5': '5f3af4192eabacc4501508d54a8cabd7',
30 'id': 'XMTc1ODE5Njcy_part1',
31 'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
35 'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
36 'only_matching': True,
38 'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
40 'id': 'XODgxNjg1Mzk2',
45 'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
47 'id': 'XMTI1OTczNDM5Mg',
51 'skip': 'Available in China only',
54 def construct_video_urls(self, data1, data2):
60 t = (t + ls[i] + compat_ord(s1[i % len(s1)])) % 256
61 ls[i], ls[t] = ls[t], ls[i]
64 for i in range(len(s2)):
67 ls[x], ls[y] = ls[y], ls[x]
68 s.append(compat_ord(s2[i]) ^ ls[(ls[x] + ls[y]) % 256])
72 b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
73 ).decode('ascii').split('_')
80 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
81 shuffled_string_ls = []
85 seed = (seed * 0xd3 + 0x754f) % 0x10000
86 idx = seed * len(string_ls) // 0x10000
87 shuffled_string_ls.append(string_ls[idx])
91 for format in data1['streamtypes']:
93 int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
95 [shuffled_string_ls[i] for i in streamfileid])
96 fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
98 def get_fileid(format, n):
99 fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
103 def generate_ep(format, n):
104 fileid = get_fileid(format, n)
107 ('%s_%s_%s' % (sid, fileid, token)).encode('ascii')
109 ep = base64.b64encode(ep_t).decode('ascii')
112 # generate video_urls
114 for format in data1['streamtypes']:
116 for dt in data1['segs'][format]:
117 n = str(int(dt['no']))
120 'hd': self.get_hd(format),
128 'ep': generate_ep(format, n)
131 'http://k.youku.com/player/getFlvPath/' + \
133 '_' + str(int(n) + 1).zfill(2) + \
134 '/st/' + self.parse_ext_l(format) + \
135 '/fileid/' + get_fileid(format, n) + '?' + \
136 compat_urllib_parse.urlencode(param)
137 video_urls.append(video_url)
138 video_urls_dict[format] = video_urls
140 return video_urls_dict
142 def get_hd(self, fm):
151 return hd_id_dict[fm]
153 def parse_ext_l(self, fm):
164 def get_format_name(self, fm):
175 def _real_extract(self, url):
176 video_id = self._match_id(url)
178 def retrieve_data(req_url, note):
179 req = compat_urllib_request.Request(req_url)
181 cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
182 if cn_verification_proxy:
183 req.add_header('Ytdl-request-proxy', cn_verification_proxy)
185 raw_data = self._download_json(req, video_id, note=note)
186 return raw_data['data'][0]
189 data1 = retrieve_data(
190 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id,
191 'Downloading JSON metadata 1')
192 data2 = retrieve_data(
193 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
194 'Downloading JSON metadata 2')
196 error_code = data1.get('error_code')
198 error = data1.get('error')
199 if error is not None and '因版权原因无法观看此视频' in error:
200 raise ExtractorError(
201 'Youku said: Sorry, this video is available in China only', expected=True)
203 msg = 'Youku server reported error %i' % error_code
204 if error is not None:
206 raise ExtractorError(msg)
208 title = data1['title']
210 # generate video_urls_dict
211 video_urls_dict = self.construct_video_urls(data1, data2)
215 'id': '%s_part%d' % (video_id, i + 1),
218 # some formats are not available for all parts, we have to detect
220 } for i in range(max(len(v) for v in data1['segs'].values()))]
221 for fm in data1['streamtypes']:
222 video_urls = video_urls_dict[fm]
223 for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries):
224 entry['formats'].append({
226 'format_id': self.get_format_name(fm),
227 'ext': self.parse_ext_l(fm),
228 'filesize': int(seg['size']),
232 '_type': 'multi_video',