aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/bilibili.py
blob: 1e57310d657fee2c47cb8e63a9868a36724f0f6a (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
# coding: utf-8
from __future__ import unicode_literals

import hashlib
import re

from .common import InfoExtractor
from ..compat import (
    compat_parse_qs,
    compat_urlparse,
)
from ..utils import (
    ExtractorError,
    int_or_none,
    float_or_none,
    parse_iso8601,
    smuggle_url,
    strip_jsonp,
    unified_timestamp,
    unsmuggle_url,
    urlencode_postdata,
)


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

    _TESTS = [{
        'url': 'http://www.bilibili.tv/video/av1074402/',
        'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
        'info_dict': {
            'id': '1074402',
            'ext': 'mp4',
            'title': '【金坷垃】金泡沫',
            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
            'duration': 308.315,
            'timestamp': 1398012660,
            'upload_date': '20140420',
            'thumbnail': r're:^https?://.+\.jpg',
            'uploader': '菊子桑',
            'uploader_id': '156160',
        },
    }, {
        # Tested in BiliBiliBangumiIE
        'url': 'http://bangumi.bilibili.com/anime/1869/play#40062',
        'only_matching': True,
    }, {
        'url': 'http://bangumi.bilibili.com/anime/5802/play#100643',
        'md5': '3f721ad1e75030cc06faf73587cfec57',
        'info_dict': {
            'id': '100643',
            'ext': 'mp4',
            'title': 'CHAOS;CHILD',
            'description': '如果你是神明,并且能够让妄想成为现实。那你会进行怎么样的妄想?是淫靡的世界?独裁社会?毁灭性的制裁?还是……2015年,涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...',
        },
        'skip': 'Geo-restricted to China',
    }, {
        # Title with double quotes
        'url': 'http://www.bilibili.com/video/av8903802/',
        'info_dict': {
            'id': '8903802',
            'ext': 'mp4',
            'title': '阿滴英文|英文歌分享#6 "Closer',
            'description': '滴妹今天唱Closer給你聽! 有史以来,被推最多次也是最久的歌曲,其实歌词跟我原本想像差蛮多的,不过还是好听! 微博@阿滴英文',
            'uploader': '阿滴英文',
            'uploader_id': '65880958',
            'timestamp': 1488382620,
            'upload_date': '20170301',
        },
        'params': {
            'skip_download': True,  # Test metadata only
        },
    }]

    _APP_KEY = '84956560bc028eb7'
    _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'

    def _report_error(self, result):
        if 'message' in result:
            raise ExtractorError('%s said: %s' % (self.IE_NAME, result['message']), expected=True)
        elif 'code' in result:
            raise ExtractorError('%s returns error %d' % (self.IE_NAME, result['code']), expected=True)
        else:
            raise ExtractorError('Can\'t extract Bangumi episode ID')

    def _real_extract(self, url):
        url, smuggled_data = unsmuggle_url(url, {})

        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        anime_id = mobj.group('anime_id')
        webpage = self._download_webpage(url, video_id)

        if 'anime/' not in url:
            cid = compat_parse_qs(self._search_regex(
                [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
                 r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
                webpage, 'player parameters'))['cid'][0]
        else:
            if 'no_bangumi_tip' not in smuggled_data:
                self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run youtube-dl with %s' % (
                    video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
            headers = {
                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
            }
            headers.update(self.geo_verification_headers())

            js = self._download_json(
                'http://bangumi.bilibili.com/web_api/get_source', video_id,
                data=urlencode_postdata({'episode_id': video_id}),
                headers=headers)
            if 'result' not in js:
                self._report_error(js)
            cid = js['result']['cid']

        payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
        sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()

        video_info = self._download_json(
            'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
            video_id, note='Downloading video info page',
            headers=self.geo_verification_headers())

        if 'durl' not in video_info:
            self._report_error(video_info)

        entries = []

        for idx, durl in enumerate(video_info['durl']):
            formats = [{
                'url': durl['url'],
                'filesize': int_or_none(durl['size']),
            }]
            for backup_url in durl.get('backup_url', []):
                formats.append({
                    'url': backup_url,
                    # backup URLs have lower priorities
                    'preference': -2 if 'hd.mp4' in backup_url else -3,
                })

            for a_format in formats:
                a_format.setdefault('http_headers', {}).update({
                    'Referer': url,
                })

            self._sort_formats(formats)

            entries.append({
                'id': '%s_part%s' % (video_id, idx),
                'duration': float_or_none(durl.get('length'), 1000),
                'formats': formats,
            })

        title = self._html_search_regex('<h1[^>]*>([^<]+)</h1>', webpage, 'title')
        description = self._html_search_meta('description', webpage)
        timestamp = unified_timestamp(self._html_search_regex(
            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None))
        thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)

        # TODO 'view_count' requires deobfuscating Javascript
        info = {
            'id': video_id,
            'title': title,
            'description': description,
            'timestamp': timestamp,
            'thumbnail': thumbnail,
            'duration': float_or_none(video_info.get('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,
            }


class BiliBiliBangumiIE(InfoExtractor):
    _VALID_URL = r'https?://bangumi\.bilibili\.com/anime/(?P<id>\d+)'

    IE_NAME = 'bangumi.bilibili.com'
    IE_DESC = 'BiliBili番剧'

    _TESTS = [{
        'url': 'http://bangumi.bilibili.com/anime/1869',
        'info_dict': {
            'id': '1869',
            'title': '混沌武士',
            'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
        },
        'playlist_count': 26,
    }, {
        'url': 'http://bangumi.bilibili.com/anime/1869',
        'info_dict': {
            'id': '1869',
            'title': '混沌武士',
            'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
        },
        'playlist': [{
            'md5': '91da8621454dd58316851c27c68b0c13',
            'info_dict': {
                'id': '40062',
                'ext': 'mp4',
                'title': '混沌武士',
                'description': '故事发生在日本的江户时代。风是一个小酒馆的打工女。一日,酒馆里来了一群恶霸,虽然他们的举动令风十分不满,但是毕竟风只是一届女流,无法对他们采取什么行动,只能在心里嘟哝。这时,酒家里又进来了个“不良份子...',
                'timestamp': 1414538739,
                'upload_date': '20141028',
                'episode': '疾风怒涛 Tempestuous Temperaments',
                'episode_number': 1,
            },
        }],
        'params': {
            'playlist_items': '1',
        },
    }]

    @classmethod
    def suitable(cls, url):
        return False if BiliBiliIE.suitable(url) else super(BiliBiliBangumiIE, cls).suitable(url)

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

        # Sometimes this API returns a JSONP response
        season_info = self._download_json(
            'http://bangumi.bilibili.com/jsonp/seasoninfo/%s.ver' % bangumi_id,
            bangumi_id, transform_source=strip_jsonp)['result']

        entries = [{
            '_type': 'url_transparent',
            'url': smuggle_url(episode['webplay_url'], {'no_bangumi_tip': 1}),
            'ie_key': BiliBiliIE.ie_key(),
            'timestamp': parse_iso8601(episode.get('update_time'), delimiter=' '),
            'episode': episode.get('index_title'),
            'episode_number': int_or_none(episode.get('index')),
        } for episode in season_info['episodes']]

        entries = sorted(entries, key=lambda entry: entry.get('episode_number'))

        return self.playlist_result(
            entries, bangumi_id,
            season_info.get('bangumi_title'), season_info.get('evaluate'))