aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/youku.py
blob: e081cfc198124944a0804bbc97786ea9a79dbdb2 (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 itertools
import random
import re
import string
import time

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    get_element_by_class,
    js_to_json,
    strip_jsonp,
    urljoin,
)


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',
            'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
            'ext': 'mp4',
        }
    }, {
        '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',
            'ext': 'mp4',
            'title': '武媚娘传奇 85',
        },
    }, {
        'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
        'info_dict': {
            'id': 'XMTI1OTczNDM5Mg',
            'ext': 'mp4',
            'title': '花千骨 04',
        },
    }, {
        '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',
        },
        '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',
            'ext': 'mp4',
            'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
        },
    }]

    @staticmethod
    def get_ysuid():
        return '%d%s' % (int(time.time()), ''.join([
            random.choice(string.ascii_letters) for i in range(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': '0401',
            'client_ip': '192.168.1.1',
            'utid': cna,
            'client_ts': time.time() / 1000,
        }

        video_password = self._downloader.params.get('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 += ': ' + error_note
                raise ExtractorError(msg)

        # get video title
        title = data['video']['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']
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
        }


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

    _TEST = {
        'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
        'info_dict': {
            'id': 'zc7c670be07ff11e48b3f',
            'title': '花千骨 未删减版',
            'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
        },
        'playlist_count': 50,
    }

    _PAGE_SIZE = 40

    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)
        for idx in itertools.count(0):
            if idx == 0:
                playlist_data_url = 'http://list.youku.com/show/module'
                query = {'id': page_config['showid'], 'tab': 'point'}
            else:
                playlist_data_url = 'http://list.youku.com/show/point'
                query = {
                    'id': page_config['showid'],
                    'stage': 'reload_%d' % (self._PAGE_SIZE * idx + 1),
                }
            query['callback'] = 'cb'
            playlist_data = self._download_json(
                playlist_data_url, show_id, query=query,
                note='Downloading playlist data page %d' % (idx + 1),
                transform_source=lambda s: js_to_json(strip_jsonp(s)))['html']
            video_urls = re.findall(
                r'<div[^>]+class="p-thumb"[^<]+<a[^>]+href="([^"]+)"',
                playlist_data)
            new_entries = [
                self.url_result(urljoin(url, video_url), YoukuIE.ie_key())
                for video_url in video_urls]
            entries.extend(new_entries)
            if len(new_entries) < self._PAGE_SIZE:
                break

        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)