韩寒的博客文章---爬虫

# -*- coding: utf-8 -*-
"""
@author: vincent
#/usr/bin/python
#http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html
"""
<a title="" target="_blank" href="http://blog.sina.com.cn/s/blog_4701280b0102eo83.html">《论电影的七个元素》——关于我对电…</a>
<a title="" target="_blank" href="http://blog.sina.com.cn/s/blog_4701280b0102eb8d.html">碎片</a></span> 
"""

import urllib

mystr='<a title="" target="_blank" href="http://blog.sina.com.cn/s/blog_4701280b0102eo83.html">《论电影的七个元素》——关于我对电…</a>'

title=mystr.find(r'<a title=')
href=mystr.find(r'href="')
html=mystr.find(r'.html')
url=mystr[href+6:html+5]
f_start=url.find(r'blog_')
filename=url[f_start:]
print url
print filename
content=urllib.urlopen(url).read()
fobj=open(r'D:\sublime codes\python\web_crawler'+'\/'+filename,'w')
fobj.write(content)
fobj.close()
#print content

-------------------------------------------------------~~~~~~~~~~进一步~~~~~~------------------------------------------------------------------------------------------

# -*- coding: utf-8 -*-

import urllib
import time
url=['']*100

con=urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html').read()
#print con
title=con.find(r'<a title=')
href=con.find(r'href="',title)
html=con.find(r'.html',href)
length=0;
#url[0]=con[href+6:html+5]
for i in range(0,100):
    if title !=-1 and href != -1 and html !=-1:
        url[i]=con[href+6:html+5]
        title=con.find(r'<a title=',html)
        href=con.find(r'href="',title)
        html=con.find(r'.html',href)
        length+=1
    else:
        print "url find over~~~~" 
        break     
url=url[0:length]
for j in range(0,50):
    tmp=url[j]
    print tmp
    content=urllib.urlopen(tmp).read()
    f_start=tmp.find(r'blog_')
    f_name=tmp[f_start:]
    fobj=open(r'D:\sublime codes\python\web_crawler'+'\/'+f_name,'w')
    fobj.write(content)
    fobj.close()
    time.sleep(3)

-------------------------------------------------------~~~~~~~~~~最终的结果！！！~~~~~~----------------------------------------------------------------

# -*- coding: utf-8 -*-
import urllib
import time
url=['']*350
length=0;
for page in range(1,8):
    con=urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_'+str(page)+'.html').read()
    title=con.find(r'<a title=')
    href=con.find(r'href="',title)
    html=con.find(r'.html',href)
    for i in range(0,100):
        if title !=-1 and href != -1 and html !=-1:
            url[length]=con[href+6:html+5]
            title=con.find(r'<a title=',html)
            href=con.find(r'href="',title)
            html=con.find(r'.html',href)
            length+=1
        else:
            break
print '-----get url end ~~~~-----'        
url=url[0:length]
print 'length= ',str(length)
for j in range(0,length):
    tmp=url[j]
    print tmp
    content=urllib.urlopen(tmp).read()
    f_start=tmp.find(r'blog_')
    f_name=tmp[f_start:]
    fobj=open(r'D:\sublime codes\python\web_crawler'+'\/'+f_name,'w')
    fobj.write(content)
    fobj.close()
    time.sleep(1)