aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/youku.py
blob: d5b73ebcef71ae52dc9c39367240a908249966a9 (plain)
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
# coding: utf-8
from __future__ import unicode_literals

import base64

from .common import InfoExtractor
from ..utils import ExtractorError

from ..compat import (
    compat_urllib_parse,
    compat_ord,
)


class YoukuIE(InfoExtractor):
    IE_NAME = 'youku'
    _VALID_URL = r'''(?x)
        (?:
            http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
            youku:)
        (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
    '''

    _TESTS = [{
        'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
        'md5': '5f3af4192eabacc4501508d54a8cabd7',
        'info_dict': {
            'id': 'XMTc1ODE5Njcy_part1',
            'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
            'ext': 'flv'
        }
    }, {
        'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
        'only_matching': True,
    }, {
        'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
        'info_dict': {
            'id': 'XODgxNjg1Mzk2',
            'title': '武媚娘传奇 85',
        },
        'playlist_count': 11,
    }]

    def construct_video_urls(self, data1, data2):
        # get sid, token
        def yk_t(s1, s2):
            ls = list(range(256))
            t = 0
            for i in range(256):
                t = (t + ls[i] + compat_ord(s1[i % len(s1)])) % 256
                ls[i], ls[t] = ls[t], ls[i]
            s = bytearray()
            x, y = 0, 0
            for i in range(len(s2)):
                y = (y + 1) % 256
                x = (x + ls[y]) % 256
                ls[x], ls[y] = ls[y], ls[x]
                s.append(compat_ord(s2[i]) ^ ls[(ls[x] + ls[y]) % 256])
            return bytes(s)

        sid, token = yk_t(
            b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
        ).decode('ascii').split('_')

        # get oip
        oip = data2['ip']

        # get fileid
        string_ls = list(
            'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
        shuffled_string_ls = []
        seed = data1['seed']
        N = len(string_ls)
        for ii in range(N):
            seed = (seed * 0xd3 + 0x754f) % 0x10000
            idx = seed * len(string_ls) // 0x10000
            shuffled_string_ls.append(string_ls[idx])
            del string_ls[idx]

        fileid_dict = {}
        for format in data1['streamtypes']:
            streamfileid = [
                int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
            fileid = ''.join(
                [shuffled_string_ls[i] for i in streamfileid])
            fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]

        def get_fileid(format, n):
            fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
            return fileid

        # get ep
        def generate_ep(format, n):
            fileid = get_fileid(format, n)
            ep_t = yk_t(
                b'bf7e5f01',
                ('%s_%s_%s' % (sid, fileid, token)).encode('ascii')
            )
            ep = base64.b64encode(ep_t).decode('ascii')
            return ep

        # generate video_urls
        video_urls_dict = {}
        for format in data1['streamtypes']:
            video_urls = []
            for dt in data1['segs'][format]:
                n = str(int(dt['no']))
                param = {
                    'K': dt['k'],
                    'hd': self.get_hd(format),
                    'myp': 0,
                    'ts': dt['seconds'],
                    'ypp': 0,
                    'ctype': 12,
                    'ev': 1,
                    'token': token,
                    'oip': oip,
                    'ep': generate_ep(format, n)
                }
                video_url = \
                    'http://k.youku.com/player/getFlvPath/' + \
                    'sid/' + sid + \
                    '_' + str(int(n) + 1).zfill(2) + \
                    '/st/' + self.parse_ext_l(format) + \
                    '/fileid/' + get_fileid(format, n) + '?' + \
                    compat_urllib_parse.urlencode(param)
                video_urls.append(video_url)
            video_urls_dict[format] = video_urls

        return video_urls_dict

    def get_hd(self, fm):
        hd_id_dict = {
            'flv': '0',
            'mp4': '1',
            'hd2': '2',
            'hd3': '3',
            '3gp': '0',
            '3gphd': '1'
        }
        return hd_id_dict[fm]

    def parse_ext_l(self, fm):
        ext_dict = {
            'flv': 'flv',
            'mp4': 'mp4',
            'hd2': 'flv',
            'hd3': 'flv',
            '3gp': 'flv',
            '3gphd': 'mp4'
        }
        return ext_dict[fm]

    def get_format_name(self, fm):
        _dict = {
            '3gp': 'h6',
            '3gphd': 'h5',
            'flv': 'h4',
            'mp4': 'h3',
            'hd2': 'h2',
            'hd3': 'h1'
        }
        return _dict[fm]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        # request basic data
        data1_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id
        data2_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id

        raw_data1 = self._download_json(data1_url, video_id)
        raw_data2 = self._download_json(data2_url, video_id)
        data1 = raw_data1['data'][0]
        data2 = raw_data2['data'][0]

        error_code = data1.get('error_code')
        if error_code:
            # -8 means blocked outside China.
            # Chinese and English, separated by newline.
            error = data1.get('error')
            raise ExtractorError(
                error or 'Server reported error %i' %
                error_code,
                expected=True)

        title = data1['title']

        # generate video_urls_dict
        video_urls_dict = self.construct_video_urls(data1, data2)

        # construct info
        entries = []
        for fm in data1['streamtypes']:
            video_urls = video_urls_dict[fm]
            for i in range(len(video_urls)):
                if len(entries) < i + 1:
                    entries.append({'formats': []})
                entries[i]['formats'].append(
                    {
                        'url': video_urls[i],
                        'format_id': self.get_format_name(fm),
                        'ext': self.parse_ext_l(fm),
                        'filesize': int(data1['segs'][fm][i]['size'])
                    }
                )

        for i in range(len(entries)):
            entries[i].update(
                {
                    'id': '%s_part%d' % (video_id, i + 1),
                    'title': title,
                }
            )

        return {
            '_type': 'multi_video',
            'id': video_id,
            'title': title,
            'entries': entries,
        }