使用Python爬取大嘴巴巴网站

Anonymous驻中国办事处主任，私下搞了一个叫做“大嘴巴巴”的色*情网站。
http://dazui88.com/

这个网站烂的一逼，大家没事可以搞一搞它。今天我们试着爬取一下网站内容，回头交给网监×××姐。

1.首先我们观察大嘴巴巴最大的色请板块“轻松一刻”的URL

2.发现下面规律

3.然后编辑下面代码

##-*- coding:utf-8 -*-
import urllib2

def load_page(url):
    '''
    send url 
    return html_page
    '''
    user_agent = "User-Agent:Mozilla/5.0(compatible;MSIE9.0;WindowsNT6.1;Trident/5.0;"

    headers = {"User-Agent":user_agent}

    req = urllib2.Request(url,headers = headers)

    response = urllib2.urlopen(req)

    html = response.read()

    return html

def write_to_file(file_name,txt):
    '''
    put txt into file_name
    '''
    print "writing file" + file_name
    f = open(file_name,'w')
    f.write(txt)
    f.close

def tiaba_spider(url,begin_page,end_page):
    '''
    fuck dazuibaba
    '''
    for i in range(begin_page,end_page + 1):
        pn = 442870 - i
        '''
        http://dazui88.com/qsyk/20180102442869.html
        http://dazui88.com/qsyk/20180102442868.html
        http://dazui88.com/qsyk/20180102442867.html
        ........
        i = 1 ,pn = 442870 -1 = 442869
        '''
        dazui88_url = url +  str(pn) + '.html'
        #print "dazui88'url:"
        #print dazui88_url
        html = load_page(dazui88_url)
        #print "================%d==================" %(i)
        #print html
        #print "===================================="
        file_name = str(i) + ".html"
        write_to_file(file_name,html)

#main
if __name__ == "__main__":
    url = raw_input("please input dazui88'URL:")
    #print url
    begin_page = int(raw_input("please input begin_page:"))
    end_page = int(raw_input("please input end_page:"))
    #print begin_page
    #print end_page
    tiaba_spider(url,begin_page,end_page)

4.然后执行python fuck-dazui88.py测试一下

5.成功爆夏主任菊花一次，可以愉快的去找网警×××姐举报他了：）

本文转自文东会博客51CTO博客，原文链接http://blog.51cto.com/hackerwang/2057398如需转载请自行联系原作者

谢文东666