aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bilibili.py
blob: b17047b399b6630fe2334aa24f0a5e97aed8506f (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
# coding: utf-8
from __future__ import unicode_literals

import calendar
import datetime
import re

from .common import InfoExtractor
from ..compat import (
    compat_etree_fromstring,
    compat_str,
    compat_parse_qs,
    compat_xml_parse_error,
)
from ..utils import (
    ExtractorError,
    int_or_none,
    float_or_none,
    xpath_text,
)


class BiliBiliIE(InfoExtractor):
    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'

    _TESTS = [{
        'url': 'http://www.bilibili.tv/video/av1074402/',
        'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
        'info_dict': {
            'id': '1554319',
            'ext': 'flv',
            'title': '【金坷垃】金泡沫',
            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
            'duration': 308.067,
            'timestamp': 1398012660,
            'upload_date': '20140420',
            'thumbnail': 're:^https?://.+\.jpg',
            'uploader': '菊子桑',
            'uploader_id': '156160',
        },
    }, {
        'url': 'http://www.bilibili.com/video/av1041170/',
        'info_dict': {
            'id': '1041170',
            'title': '【BD1080P】刀语【诸神&异域】',
            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦!~',
        },
        'playlist_count': 9,
    }, {
        'url': 'http://www.bilibili.com/video/av4808130/',
        'info_dict': {
            'id': '4808130',
            'title': '【长篇】哆啦A梦443【钉铛】',
            'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉,又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
        },
        'playlist': [{
            'md5': '55cdadedf3254caaa0d5d27cf20a8f9c',
            'info_dict': {
                'id': '4808130_part1',
                'ext': 'flv',
                'title': '【长篇】哆啦A梦443【钉铛】',
                'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉,又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
                'timestamp': 1464564180,
                'upload_date': '20160529',
                'uploader': '喜欢拉面',
                'uploader_id': '151066',
            },
        }, {
            'md5': '926f9f67d0c482091872fbd8eca7ea3d',
            'info_dict': {
                'id': '4808130_part2',
                'ext': 'flv',
                'title': '【长篇】哆啦A梦443【钉铛】',
                'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉,又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
                'timestamp': 1464564180,
                'upload_date': '20160529',
                'uploader': '喜欢拉面',
                'uploader_id': '151066',
            },
        }, {
            'md5': '4b7b225b968402d7c32348c646f1fd83',
            'info_dict': {
                'id': '4808130_part3',
                'ext': 'flv',
                'title': '【长篇】哆啦A梦443【钉铛】',
                'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉,又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
                'timestamp': 1464564180,
                'upload_date': '20160529',
                'uploader': '喜欢拉面',
                'uploader_id': '151066',
            },
        }, {
            'md5': '7b795e214166501e9141139eea236e91',
            'info_dict': {
                'id': '4808130_part4',
                'ext': 'flv',
                'title': '【长篇】哆啦A梦443【钉铛】',
                'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉,又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
                'timestamp': 1464564180,
                'upload_date': '20160529',
                'uploader': '喜欢拉面',
                'uploader_id': '151066',
            },
        }],
    }, {
        # Missing upload time
        'url': 'http://www.bilibili.com/video/av1867637/',
        'info_dict': {
            'id': '2880301',
            'ext': 'flv',
            'title': '【HDTV】【喜剧】岳父岳母真难当 (2014)【法国票房冠军】',
            'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫,老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人,结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
            'uploader': '黑夜为猫',
            'uploader_id': '610729',
        },
        'params': {
            # Just to test metadata extraction
            'skip_download': True,
        },
        'expected_warnings': ['upload time'],
    }]

    # BiliBili blocks keys from time to time. The current key is extracted from
    # the Android client
    # TODO: find the sign algorithm used in the flash player
    _APP_KEY = '86385cdc024c0f6c'

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')

        webpage = self._download_webpage(url, video_id)

        params = compat_parse_qs(self._search_regex(
            [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
             r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
            webpage, 'player parameters'))
        cid = params['cid'][0]

        info_xml_str = self._download_webpage(
            'http://interface.bilibili.com/v_cdn_play',
            cid, query={'appkey': self._APP_KEY, 'cid': cid},
            note='Downloading video info page')

        err_msg = None
        durls = None
        info_xml = None
        try:
            info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8'))
        except compat_xml_parse_error:
            info_json = self._parse_json(info_xml_str, video_id, fatal=False)
            err_msg = (info_json or {}).get('error_text')
        else:
            err_msg = xpath_text(info_xml, './message')

        if info_xml is not None:
            durls = info_xml.findall('./durl')
        if not durls:
            if err_msg:
                raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True)
            else:
                raise ExtractorError('No videos found!')

        entries = []

        for durl in durls:
            size = xpath_text(durl, ['./filesize', './size'])
            formats = [{
                'url': durl.find('./url').text,
                'filesize': int_or_none(size),
            }]
            for backup_url in durl.findall('./backup_url/url'):
                formats.append({
                    'url': backup_url.text,
                    # backup URLs have lower priorities
                    'preference': -2 if 'hd.mp4' in backup_url.text else -3,
                })

            self._sort_formats(formats)

            entries.append({
                'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
                'duration': int_or_none(xpath_text(durl, './length'), 1000),
                'formats': formats,
            })

        title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
        description = self._html_search_meta('description', webpage)
        datetime_str = self._html_search_regex(
            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
        timestamp = None
        if datetime_str:
            timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())

        # TODO 'view_count' requires deobfuscating Javascript
        info = {
            'id': compat_str(cid),
            'title': title,
            'description': description,
            'timestamp': timestamp,
            'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
            'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000),
        }

        uploader_mobj = re.search(
            r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
            webpage)
        if uploader_mobj:
            info.update({
                'uploader': uploader_mobj.group('name'),
                'uploader_id': uploader_mobj.group('id'),
            })

        for entry in entries:
            entry.update(info)

        if len(entries) == 1:
            return entries[0]
        else:
            for idx, entry in enumerate(entries):
                entry['id'] = '%s_part%d' % (video_id, (idx + 1))

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