aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bilibili.py
blob: 7ca835e31f3477f8e46c74804aea36ecfe789686 (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
# coding: utf-8
from __future__ import unicode_literals

import re
import itertools

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    unified_strdate,
    ExtractorError,
)


class BiliBiliIE(InfoExtractor):
    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'

    _TESTS = [{
        'url': 'http://www.bilibili.tv/video/av1074402/',
        'md5': '2c301e4dab317596e837c3e7633e7d86',
        'info_dict': {
            'id': '1074402_part1',
            'ext': 'flv',
            'title': '【金坷垃】金泡沫',
            'duration': 308,
            'upload_date': '20140420',
            'thumbnail': 're:^https?://.+\.jpg',
        },
    }, {
        'url': 'http://www.bilibili.com/video/av1041170/',
        'info_dict': {
            'id': '1041170',
            'title': '【BD1080P】刀语【诸神&异域】',
        },
        'playlist_count': 9,
    }]

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

        if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None):
            raise ExtractorError('The video does not exist or was deleted', expected=True)
        video_code = self._search_regex(
            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')

        title = self._html_search_meta(
            'media:title', video_code, 'title', fatal=True)
        duration_str = self._html_search_meta(
            'duration', video_code, 'duration')
        if duration_str is None:
            duration = None
        else:
            duration_mobj = re.match(
                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
                duration_str)
            duration = (
                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
                int(duration_mobj.group('minutes')) * 60 +
                int(duration_mobj.group('seconds')))
        upload_date = unified_strdate(self._html_search_meta(
            'uploadDate', video_code, fatal=False))
        thumbnail = self._html_search_meta(
            'thumbnailUrl', video_code, 'thumbnail', fatal=False)

        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')

        entries = []

        lq_doc = self._download_xml(
            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
            video_id,
            note='Downloading LQ video info'
        )
        lq_durls = lq_doc.findall('./durl')

        hq_doc = self._download_xml(
            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
            video_id,
            note='Downloading HQ video info',
            fatal=False,
        )
        hq_durls = hq_doc.findall('./durl') if hq_doc is not False else itertools.repeat(None)

        assert len(lq_durls) == len(hq_durls)

        i = 1
        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
            formats = [{
                'format_id': 'lq',
                'quality': 1,
                'url': lq_durl.find('./url').text,
                'filesize': int_or_none(
                    lq_durl.find('./size'), get_attr='text'),
            }]
            if hq_durl:
                formats.append({
                    'format_id': 'hq',
                    'quality': 2,
                    'ext': 'flv',
                    'url': hq_durl.find('./url').text,
                    'filesize': int_or_none(
                        hq_durl.find('./size'), get_attr='text'),
                })
            self._sort_formats(formats)

            entries.append({
                'id': '%s_part%d' % (video_id, i),
                'title': title,
                'formats': formats,
                'duration': duration,
                'upload_date': upload_date,
                'thumbnail': thumbnail,
            })

            i += 1

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