#coding=utf-8
import requests
import threading
import time
import os
def check(i,total):
global eu
#os.system("title Spider,Current threads: %d,URLs left: %d,URLs
exists:%d" %(threading.active_count(),total,eu))
try:
r = requests.get(i+'/',timeout=10) #链接后缀，如果没有可以
不加，timeout是超时时间
status=r.content.count('指定文字')
except:
print i,'超时'
status = 0
if status !=0: #通过标题判断
r = 0
print i,'成功!!!!!'
eu+=1
f = open("成功的文件保存.txt", 'a')
f.write(i+'
')
f.close()
def main():
global eu
eu = 0
total=len(open('等待过滤的链接.txt','rU').readlines())
print 'Total URLs:%d' %total
for i in open("等待过滤的链接.txt").readlines():
i=i.strip('
')
t=threading.Thread(target=check, args=(i,total))
t.setDaemon(True)
total-=1
while True:
if(threading.active_count() == 1 and total == 0 ):
print 'All Done at %s' %time.strftime
("%Y-%m-%d[%H.%M.%S]")
break
elif (threading.active_count() < 200):
if (total == 0):
time.sleep(10) #10秒之后回到上一个
if判断线程是否全部结束
else:
os.system("title Spider,Current
threads: %d,URLs left: %d,URLs exists:%d" %(threading.active_count
(),total,eu))
t.start() #加载该线程
break
if __name__ == '__main__':
main()