aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/youku.py
blob: 147608ebebbbe8b71dda64e2daf974362868c50c (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
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
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
# coding: utf-8
from __future__ import unicode_literals

import base64
import itertools
import random
import re
import string
import time

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse_urlencode,
    compat_ord,
)
from ..utils import (
    ExtractorError,
    get_element_by_attribute,
    sanitized_Request,
)


class YoukuIE(InfoExtractor):
    IE_NAME = 'youku'
    IE_DESC = '优酷'
    _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 = [{
        # MD5 is unstable
        'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
        '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,
        'skip': 'Available in China only',
    }, {
        'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
        'info_dict': {
            'id': 'XMTI1OTczNDM5Mg',
            'title': '花千骨 04',
        },
        'playlist_count': 13,
    }, {
        'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
        'note': 'Video protected with password',
        'info_dict': {
            'id': 'XNjA1NzA2Njgw',
            'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
        },
        'playlist_count': 19,
        'params': {
            'videopassword': '100600',
        },
    }, {
        # /play/get.json contains streams with "channel_type":"tail"
        'url': 'http://v.youku.com/v_show/id_XOTUxMzg4NDMy.html',
        'info_dict': {
            'id': 'XOTUxMzg4NDMy',
            'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
        },
        'playlist_count': 6,
    }]

    def construct_video_urls(self, data):
        # 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(data['security']['encrypt_string'].encode('ascii'))
        ).decode('ascii').split('_')

        # get oip
        oip = data['security']['ip']

        fileid_dict = {}
        for stream in data['stream']:
            if stream.get('channel_type') == 'tail':
                continue
            format = stream.get('stream_type')
            fileid = stream['stream_fileid']
            fileid_dict[format] = fileid

        def get_fileid(format, n):
            number = hex(int(str(n), 10))[2:].upper()
            if len(number) == 1:
                number = '0' + number
            streamfileids = fileid_dict[format]
            fileid = streamfileids[0:8] + number + streamfileids[10:]
            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 stream in data['stream']:
            if stream.get('channel_type') == 'tail':
                continue
            format = stream.get('stream_type')
            video_urls = []
            for dt in stream['segs']:
                n = str(stream['segs'].index(dt))
                param = {
                    'K': dt['key'],
                    'hd': self.get_hd(format),
                    'myp': 0,
                    '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 + \
                    '_00' + \
                    '/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

    @staticmethod
    def get_ysuid():
        return '%d%s' % (int(time.time()), ''.join([
            random.choice(string.ascii_letters) for i in range(3)]))

    def get_hd(self, fm):
        hd_id_dict = {
            '3gp': '0',
            '3gphd': '1',
            'flv': '0',
            'flvhd': '0',
            'mp4': '1',
            'mp4hd': '1',
            'mp4hd2': '1',
            'mp4hd3': '1',
            'hd2': '2',
            'hd3': '3',
        }
        return hd_id_dict[fm]

    def parse_ext_l(self, fm):
        ext_dict = {
            '3gp': 'flv',
            '3gphd': 'mp4',
            'flv': 'flv',
            'flvhd': 'flv',
            'mp4': 'mp4',
            'mp4hd': 'mp4',
            'mp4hd2': 'flv',
            'mp4hd3': 'flv',
            'hd2': 'flv',
            'hd3': 'flv',
        }
        return ext_dict[fm]

    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[fm]

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

        self._set_cookie('youku.com', '__ysuid', self.get_ysuid())

        def retrieve_data(req_url, note):
            headers = {
                'Referer': req_url,
            }
            self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
            req = sanitized_Request(req_url, headers=headers)

            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
            if cn_verification_proxy:
                req.add_header('Ytdl-request-proxy', cn_verification_proxy)

            raw_data = self._download_json(req, video_id, note=note)

            return raw_data['data']

        video_password = self._downloader.params.get('videopassword')

        # request basic data
        basic_data_url = 'http://play.youku.com/play/get.json?vid=%s&ct=12' % video_id
        if video_password:
            basic_data_url += '&pwd=%s' % video_password

        data = retrieve_data(basic_data_url, 'Downloading JSON metadata')

        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 += ': ' + error_note
                raise ExtractorError(msg)

        # get video title
        title = data['video']['title']

        # generate video_urls_dict
        video_urls_dict = self.construct_video_urls(data)

        # construct info
        entries = [{
            'id': '%s_part%d' % (video_id, i + 1),
            'title': title,
            'formats': [],
            # some formats are not available for all parts, we have to detect
            # which one has all
        } for i in range(max(len(v.get('segs')) for v in data['stream']))]
        for stream in data['stream']:
            if stream.get('channel_type') == 'tail':
                continue
            fm = stream.get('stream_type')
            video_urls = video_urls_dict[fm]
            for video_url, seg, entry in zip(video_urls, stream['segs'], entries):
                entry['formats'].append({
                    'url': video_url,
                    'format_id': self.get_format_name(fm),
                    'ext': self.parse_ext_l(fm),
                    'filesize': int(seg['size']),
                    'width': stream.get('width'),
                    'height': stream.get('height'),
                })

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


class YoukuShowIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?youku\.com/show_page/id_(?P<id>[0-9a-z]+)\.html'
    IE_NAME = 'youku:show'

    _TEST = {
        'url': 'http://www.youku.com/show_page/id_zc7c670be07ff11e48b3f.html',
        'info_dict': {
            'id': 'zc7c670be07ff11e48b3f',
            'title': '花千骨 未删减版',
            'description': 'md5:578d4f2145ae3f9128d9d4d863312910',
        },
        'playlist_count': 50,
    }

    _PAGE_SIZE = 40

    def _find_videos_in_page(self, webpage):
        videos = re.findall(
            r'<li><a[^>]+href="(?P<url>https?://v\.youku\.com/[^"]+)"[^>]+title="(?P<title>[^"]+)"', webpage)
        return [
            self.url_result(video_url, YoukuIE.ie_key(), title)
            for video_url, title in videos]

    def _real_extract(self, url):
        show_id = self._match_id(url)
        webpage = self._download_webpage(url, show_id)

        entries = self._find_videos_in_page(webpage)

        playlist_title = self._html_search_regex(
            r'<span[^>]+class="name">([^<]+)</span>', webpage, 'playlist title', fatal=False)
        detail_div = get_element_by_attribute('class', 'detail', webpage) or ''
        playlist_description = self._html_search_regex(
            r'<span[^>]+style="display:none"[^>]*>([^<]+)</span>',
            detail_div, 'playlist description', fatal=False)

        for idx in itertools.count(1):
            episodes_page = self._download_webpage(
                'http://www.youku.com/show_episode/id_%s.html' % show_id,
                show_id, query={'divid': 'reload_%d' % (idx * self._PAGE_SIZE + 1)},
                note='Downloading episodes page %d' % idx)
            new_entries = self._find_videos_in_page(episodes_page)
            entries.extend(new_entries)
            if len(new_entries) < self._PAGE_SIZE:
                break

        return self.playlist_result(entries, show_id, playlist_title, playlist_description)