一个爬虫例子，抓取糗百笑话。

标签：

# -*- coding: utf-8 -*-
import re
import urllib2
def getimage(pagenum):
    url = ‘http://m.qiushibaike.com/text/page/%s?s=4784059‘ % pagenum
    req = urllib2.Request(url,headers={‘User-Agent‘:‘Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)‘})
    res = urllib2.urlopen(req)
    c = res.read().decode(‘utf-8‘)
    p = re.compile(r‘<div class="content">(.*?)</div>‘,re.S)
    l = re.findall(p,c)
    return l
def getinfo():
    f = open(‘E:\\qiubai.txt‘,‘w‘)
    num = 35
    slen = 0
    for page in range(1,num+1):
        list = getimage(page)
        slen += len(list)
        for line in list:
            f.write(line.encode(‘utf-8‘))
    f.close()
    print ‘total download [%d] ‘ % slen
getinfo()

一个爬虫例子，抓取糗百笑话。

标签：

原文地址：http://www.cnblogs.com/xiewb/p/4600445.html