]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/weibo.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
10 from ..compat
import (
21 class WeiboIE(InfoExtractor
):
22 _VALID_URL
= r
'https?://(?:www\.)?weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)'
24 'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment',
28 'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博',
32 def _real_extract(self
, url
):
33 video_id
= self
._match
_id
(url
)
34 # to get Referer url for genvisitor
35 webpage
, urlh
= self
._download
_webpage
_handle
(url
, video_id
)
37 visitor_url
= urlh
.geturl()
39 if 'passport.weibo.com' in visitor_url
:
41 visitor_data
= self
._download
_json
(
42 'https://passport.weibo.com/visitor/genvisitor', video_id
,
43 note
='Generating first-visit data',
44 transform_source
=strip_jsonp
,
45 headers
={'Referer': visitor_url
},
46 data
=urlencode_postdata({
50 'browser': 'Gecko57,0,0,0',
52 'screenInfo': '1440*900*24',
57 tid
= visitor_data
['data']['tid']
58 cnfd
= '%03d' % visitor_data
['data']['confidence']
60 self
._download
_webpage
(
61 'https://passport.weibo.com/visitor/visitor', video_id
,
62 note
='Running first-visit callback',
70 '_rand': random
.random(),
73 webpage
= self
._download
_webpage
(
74 url
, video_id
, note
='Revisiting webpage')
76 title
= self
._html
_search
_regex
(
77 r
'<title>(.+?)</title>', webpage
, 'title')
79 video_formats
= compat_parse_qs(self
._search
_regex
(
80 r
'video-sources=\\\"(.+?)\"', webpage
, 'video_sources'))
83 supported_resolutions
= (480, 720)
84 for res
in supported_resolutions
:
85 vid_urls
= video_formats
.get(compat_str(res
))
86 if not vid_urls
or not isinstance(vid_urls
, list):
95 self
._sort
_formats
(formats
)
97 uploader
= self
._og
_search
_property
(
98 'nick-name', webpage
, 'uploader', default
=None)
103 'uploader': uploader
,
108 class WeiboMobileIE(InfoExtractor
):
109 _VALID_URL
= r
'https?://m\.weibo\.cn/status/(?P<id>[0-9]+)(\?.+)?'
111 'url': 'https://m.weibo.cn/status/4189191225395228?wm=3333_2001&sourcetype=weixin&featurecode=newtitle&from=singlemessage&isappinstalled=0',
113 'id': '4189191225395228',
115 'title': '午睡当然是要甜甜蜜蜜的啦',
120 def _real_extract(self
, url
):
121 video_id
= self
._match
_id
(url
)
122 # to get Referer url for genvisitor
123 webpage
= self
._download
_webpage
(url
, video_id
, note
='visit the page')
125 weibo_info
= self
._parse
_json
(self
._search
_regex
(
126 r
'var\s+\$render_data\s*=\s*\[({.*})\]\[0\]\s*\|\|\s*{};',
127 webpage
, 'js_code', flags
=re
.DOTALL
),
128 video_id
, transform_source
=js_to_json
)
130 status_data
= weibo_info
.get('status', {})
131 page_info
= status_data
.get('page_info')
132 title
= status_data
['status_title']
133 uploader
= status_data
.get('user', {}).get('screen_name')
138 'uploader': uploader
,
139 'url': page_info
['media_info']['stream_url']