{var%20f='http://v.t.sina.com.cn/share/share.php?appkey=1515056452',u=z||d.location,p=['&url=',e(u),'&title=',e(t||d.title),'&source=',e(r),'&sourceUrl=',e(l),'&content=',c||'gb2312','&pic=',e(p||'')].join('');function%20a(){if(!window.open([f,p].join(''),'mb',['toolbar=0,status=0,resizable=1,width=440,height=430,left=',(s.width-440)/2,',top=',(s.height-430)/2].join('')))u.href=[f,p].join('');};if(/Firefox/.test(navigator.userAgent))setTimeout(a,0);else%20a();})(screen,document,encodeURIComponent,'','','https://www.xiaopingtou.cn//data/attach/topic/topicKPo7gB.jpg', '推荐 qq0901001 的文章《【python】爬虫1——下载博客文章》','https://www.xiaopingtou.net/article-54100.html','页面编码gb2312|utf-8默认gb2312'));){kind=link}
data/attach/1904/sznpgtch7kbc9uh0d7uhvzsynm5azlli.jpgdata/attach/1904/sg5jjxktzy28ztea593a83nv4aimp68s.jpgdata/attach/1904/f1y369uqa8g92m45vco29gqjuhdby3ku.jpg
1.查找url
![]()
![]()
![]()
#! /usr/bin/env python
#coding=utf-8
#《论电影的七个元素》——关于我对电…
from urllib import urlopen
str0 = 'blabla《论电影的七个元素》——关于我对电…'
title = str0.find(' #得到href所在位置为142
print href
html = str0.find(r'.html') #得到html所在位置为142
print html
url = str0[href+6:html+5] #得到url：http://blog.sina.com.cn/s/blog_4701280b0102eo83.html
print url
content = urlopen(url).read()
#print content
filename = url[-26:] #得到文件名blog_4701280b0102eo83.html
print filename
open(filename,'w').write(content)
1.查找url