]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/douyutv.py
Update changelog.
[youtubedl] / youtube_dl / extractor / douyutv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import hashlib
5 import time
6 from .common import InfoExtractor
7 from ..utils import (ExtractorError, unescapeHTML)
8 from ..compat import (compat_str, compat_basestring)
9
10
11 class DouyuTVIE(InfoExtractor):
12 _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
13 _TESTS = [{
14 'url': 'http://www.douyutv.com/iseven',
15 'info_dict': {
16 'id': '17732',
17 'display_id': 'iseven',
18 'ext': 'flv',
19 '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}$',
20 'description': 'md5:c93d6692dde6fe33809a46edcbecca44',
21 'thumbnail': 're:^https?://.*\.jpg$',
22 'uploader': '7师傅',
23 'uploader_id': '431925',
24 'is_live': True,
25 },
26 'params': {
27 'skip_download': True,
28 }
29 }, {
30 'url': 'http://www.douyutv.com/85982',
31 'info_dict': {
32 'id': '85982',
33 'display_id': '85982',
34 'ext': 'flv',
35 '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}$',
36 'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
37 'thumbnail': 're:^https?://.*\.jpg$',
38 'uploader': 'douyu小漠',
39 'uploader_id': '3769985',
40 'is_live': True,
41 },
42 'params': {
43 'skip_download': True,
44 }
45 }]
46
47 def _real_extract(self, url):
48 video_id = self._match_id(url)
49
50 if video_id.isdigit():
51 room_id = video_id
52 else:
53 page = self._download_webpage(url, video_id)
54 room_id = self._html_search_regex(
55 r'"room_id"\s*:\s*(\d+),', page, 'room id')
56
57 prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
58 room_id, int(time.time()))
59
60 auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
61 config = self._download_json(
62 'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
63 video_id)
64
65 data = config['data']
66
67 error_code = config.get('error', 0)
68 if error_code is not 0:
69 error_desc = 'Server reported error %i' % error_code
70 if isinstance(data, (compat_str, compat_basestring)):
71 error_desc += ': ' + data
72 raise ExtractorError(error_desc, expected=True)
73
74 show_status = data.get('show_status')
75 # 1 = live, 2 = offline
76 if show_status == '2':
77 raise ExtractorError(
78 'Live stream is offline', expected=True)
79
80 base_url = data['rtmp_url']
81 live_path = data['rtmp_live']
82
83 title = self._live_title(unescapeHTML(data['room_name']))
84 description = data.get('show_details')
85 thumbnail = data.get('room_src')
86
87 uploader = data.get('nickname')
88 uploader_id = data.get('owner_uid')
89
90 multi_formats = data.get('rtmp_multi_bitrate')
91 if not isinstance(multi_formats, dict):
92 multi_formats = {}
93 multi_formats['live'] = live_path
94
95 formats = [{
96 'url': '%s/%s' % (base_url, format_path),
97 'format_id': format_id,
98 'preference': 1 if format_id == 'live' else 0,
99 } for format_id, format_path in multi_formats.items()]
100 self._sort_formats(formats)
101
102 return {
103 'id': room_id,
104 'display_id': video_id,
105 'title': title,
106 'description': description,
107 'thumbnail': thumbnail,
108 'uploader': uploader,
109 'uploader_id': uploader_id,
110 'formats': formats,
111 'is_live': True,
112 }