aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/douyutv.py
blob: bcb670945d27b31802bf27390feb4f6cbd53cd6f (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
# coding: utf-8
from __future__ import unicode_literals

import hashlib
import time
from .common import InfoExtractor
from ..utils import (ExtractorError, unescapeHTML)
from ..compat import (compat_str, compat_basestring)


class DouyuTVIE(InfoExtractor):
    IE_DESC = '斗鱼'
    _VALID_URL = r'https?://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
    _TESTS = [{
        'url': 'http://www.douyutv.com/iseven',
        'info_dict': {
            'id': '17732',
            'display_id': 'iseven',
            'ext': 'flv',
            'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'description': 'md5:f34981259a03e980a3c6404190a3ed61',
            'thumbnail': 're:^https?://.*\.jpg$',
            'uploader': '7师傅',
            'uploader_id': '431925',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://www.douyutv.com/85982',
        'info_dict': {
            'id': '85982',
            'display_id': '85982',
            'ext': 'flv',
            'title': 're:^小漠从零单排记!——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
            'thumbnail': 're:^https?://.*\.jpg$',
            'uploader': 'douyu小漠',
            'uploader_id': '3769985',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
        'skip': 'Romm not found',
    }, {
        'url': 'http://www.douyutv.com/17732',
        'info_dict': {
            'id': '17732',
            'display_id': '17732',
            'ext': 'flv',
            'title': 're:^清晨醒脑!T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'description': 'md5:f34981259a03e980a3c6404190a3ed61',
            'thumbnail': 're:^https?://.*\.jpg$',
            'uploader': '7师傅',
            'uploader_id': '431925',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }]

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

        if video_id.isdigit():
            room_id = video_id
        else:
            page = self._download_webpage(url, video_id)
            room_id = self._html_search_regex(
                r'"room_id"\s*:\s*(\d+),', page, 'room id')

        prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
            room_id, int(time.time()))

        auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
        config = self._download_json(
            'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
            video_id)

        data = config['data']

        error_code = config.get('error', 0)
        if error_code is not 0:
            error_desc = 'Server reported error %i' % error_code
            if isinstance(data, (compat_str, compat_basestring)):
                error_desc += ': ' + data
            raise ExtractorError(error_desc, expected=True)

        show_status = data.get('show_status')
        # 1 = live, 2 = offline
        if show_status == '2':
            raise ExtractorError(
                'Live stream is offline', expected=True)

        base_url = data['rtmp_url']
        live_path = data['rtmp_live']

        title = self._live_title(unescapeHTML(data['room_name']))
        description = data.get('show_details')
        thumbnail = data.get('room_src')

        uploader = data.get('nickname')
        uploader_id = data.get('owner_uid')

        multi_formats = data.get('rtmp_multi_bitrate')
        if not isinstance(multi_formats, dict):
            multi_formats = {}
        multi_formats['live'] = live_path

        formats = [{
            'url': '%s/%s' % (base_url, format_path),
            'format_id': format_id,
            'preference': 1 if format_id == 'live' else 0,
        } for format_id, format_path in multi_formats.items()]
        self._sort_formats(formats)

        return {
            'id': room_id,
            'display_id': video_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'formats': formats,
            'is_live': True,
        }