第一个网络爬虫——简单的抓取网页

import urllib2
import re
from bs4 import BeautifulSoup

content = urllib2.urlopen("http://www.cnblogs.com/ly941122/").read();
soup=BeautifulSoup(content)
siteUrls = soup.findAll(‘div‘,{‘class‘:‘postTitle‘})
tag=re.compile(‘</?\w+[^>]*>‘)
print siteUrls 
file=open(‘res.txt‘,‘wb‘)
try:
    for i in siteUrls:
        str1=re.sub(tag,‘ ‘,str(i))
        str1=str1[1:]
        # print str1
        str2=str(i).split(‘ ‘)
        html = str2[2][6:-1]
        file.write(str1+html+‘\n‘)
except Exception,e:
    print e
file.close()
raw_input()