]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/douyutv.py
2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
17 class DouyuTVIE(InfoExtractor
):
19 _VALID_URL
= r
'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)'
21 'url': 'http://www.douyutv.com/iseven',
24 'display_id': 'iseven',
26 'title': 're:^清晨醒脑!根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
27 'description': r
're:.*m7show@163\.com.*',
28 'thumbnail': r
're:^https?://.*\.jpg$',
33 'skip_download': True,
36 'url': 'http://www.douyutv.com/85982',
39 'display_id': '85982',
41 '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}$',
42 'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
43 'thumbnail': r
're:^https?://.*\.jpg$',
44 'uploader': 'douyu小漠',
48 'skip_download': True,
50 'skip': 'Room not found',
52 'url': 'http://www.douyutv.com/17732',
55 'display_id': '17732',
57 'title': 're:^清晨醒脑!根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
58 'description': r
're:.*m7show@163\.com.*',
59 'thumbnail': r
're:^https?://.*\.jpg$',
64 'skip_download': True,
67 'url': 'http://www.douyu.com/xiaocang',
68 'only_matching': True,
71 'url': 'http://www.douyu.com/t/lpl',
72 'only_matching': True,
75 def _real_extract(self
, url
):
76 video_id
= self
._match
_id
(url
)
78 if video_id
.isdigit():
81 page
= self
._download
_webpage
(url
, video_id
)
82 room_id
= self
._html
_search
_regex
(
83 r
'"room_id\\?"\s*:\s*(\d+),', page
, 'room id')
85 # Grab metadata from mobile API
86 room
= self
._download
_json
(
87 'http://m.douyu.com/html5/live?roomId=%s' % room_id
, video_id
,
88 note
='Downloading room info')['data']
90 # 1 = live, 2 = offline
91 if room
.get('show_status') == '2':
92 raise ExtractorError('Live stream is offline', expected
=True)
94 # Grab the URL from PC client API
95 # The m3u8 url from mobile API requires re-authentication every 5 minutes
97 signContent
= 'lapi/live/thirdPart/getPlay/%s?aid=pcclient&rate=0&time=%d9TUk5fjjUjg9qIMH3sdnh' % (room_id
, tt
)
98 sign
= hashlib
.md5(signContent
.encode('ascii')).hexdigest()
99 video_url
= self
._download
_json
(
100 'http://coapi.douyucdn.cn/lapi/live/thirdPart/getPlay/' + room_id
,
101 video_id
, note
='Downloading video URL info',
102 query
={'rate': 0}, headers
={
106 })['data']['live_url']
108 title
= self
._live
_title
(unescapeHTML(room
['room_name']))
109 description
= room
.get('show_details')
110 thumbnail
= room
.get('room_src')
111 uploader
= room
.get('nickname')
115 'display_id': video_id
,
118 'description': description
,
119 'thumbnail': thumbnail
,
120 'uploader': uploader
,
125 class DouyuShowIE(InfoExtractor
):
126 _VALID_URL
= r
'https?://v(?:mobile)?\.douyu\.com/show/(?P<id>[0-9a-zA-Z]+)'
129 'url': 'https://v.douyu.com/show/rjNBdvnVXNzvE2yw',
130 'md5': '0c2cfd068ee2afe657801269b2d86214',
132 'id': 'rjNBdvnVXNzvE2yw',
134 'title': '陈一发儿:砒霜 我有个室友系列!04-01 22点场',
136 'thumbnail': r
're:^https?://.*\.jpg$',
138 'uploader_id': 'XrZwYelr5wbK',
139 'uploader_url': 'https://v.douyu.com/author/XrZwYelr5wbK',
140 'upload_date': '20170402',
143 'url': 'https://vmobile.douyu.com/show/rjNBdvnVXNzvE2yw',
144 'only_matching': True,
147 def _real_extract(self
, url
):
148 url
= url
.replace('vmobile.', 'v.')
149 video_id
= self
._match
_id
(url
)
151 webpage
= self
._download
_webpage
(url
, video_id
)
153 room_info
= self
._parse
_json
(self
._search
_regex
(
154 r
'var\s+\$ROOM\s*=\s*({.+});', webpage
, 'room info'), video_id
)
158 for trial
in range(5):
159 # Sometimes Douyu rejects our request. Let's try it more times
161 video_info
= self
._download
_json
(
162 'https://vmobile.douyu.com/video/getInfo', video_id
,
163 query
={'vid': video_id
},
166 'x-requested-with': 'XMLHttpRequest',
169 except ExtractorError
:
170 self
._sleep
(1, video_id
)
173 raise ExtractorError('Can\'t fetch video info')
175 formats
= self
._extract
_m
3u8_formats
(
176 video_info
['data']['video_url'], video_id
,
177 entry_protocol
='m3u8_native', ext
='mp4')
179 upload_date
= unified_strdate(self
._html
_search
_regex
(
180 r
'<em>上传时间:</em><span>([^<]+)</span>', webpage
,
181 'upload date', fatal
=False))
183 uploader
= uploader_id
= uploader_url
= None
185 r
'(?m)<a[^>]+href="/author/([0-9a-zA-Z]+)".+?<strong[^>]+title="([^"]+)"',
188 uploader_id
, uploader
= mobj
.groups()
189 uploader_url
= urljoin(url
, '/author/' + uploader_id
)
193 'title': room_info
['name'],
195 'duration': room_info
.get('duration'),
196 'thumbnail': room_info
.get('pic'),
197 'upload_date': upload_date
,
198 'uploader': uploader
,
199 'uploader_id': uploader_id
,
200 'uploader_url': uploader_url
,