简单小爬虫

 1 import urllib2,time
 2 vio=0
 3 f=open(r'f:\\aa.txt','w')
 4 while vio<10:
 5     ph=-1
 6     beg=0
 7     i=0
 8     mmurl="http://121.42.142.123/JudgeOnline/problemstatus.php?id=1154"
 9     mmurl+="&page="+str(vio)
10     vio+=1
11     up=urllib2.urlopen(mmurl)
12     const=up.read()
13     leng=len(const)
14     #print "---------------------------------------"
15     while True:
16         i+=1
17         head="156310"
18         tail="</a></td><td>"
19         ph=const.find(head,beg+20)
20         if ph==-1:
21             break
22         beg=ph
23         f.write(const[ph:ph+11]+'\n')
24         print const[ph:ph+11]
25 #print "---------------------------------------\n"
26 f.close()
27 time.sleep(2002)

 

转载于:https://www.cnblogs.com/A-FM/p/5603801.html