基python实现多线程网页爬虫

#!/usr/bin/env python
#coding=utf-8
import threading
import urllib
import re
import time
g_mutex=threading.Condition()
g_pages=[] #从中解析所有url链接
g_queueURL=[] #等待爬取的url链接列表
g_existURL=[] #已经爬取过的url链接列表
g_failedURL=[] #下载失败的url链接列表
g_totalcount=0 #下载过的页面数
class Crawler:
 def __init__(self,crawlername,url,threadnum):
 self.crawlername=crawlername
 self.url=url
 self.threadnum=threadnum
 self.threadpool=[]
 self.logfile=file("log.txt",'w')
 def craw(self):
 global g_queueURL
 g_queueURL.append(url) 
 depth=0
 print self.crawlername+" 启动..."
 while(len(g_queueURL)!=0):
 depth+=1
 print 'Searching depth ',depth,'...

'
 self.logfile.write("URL:"+g_queueURL[0]+"........")
 self.downloadAll()
 self.updateQueueURL()
 content='
>>>Depth '+str(depth)+':
'
 self.logfile.write(content)
 i=0
 while i'+g_queueURL[i]+'
'
 self.logfile.write(content)
 i+=1
 def downloadAll(self):
 global g_queueURL
 global g_totalcount
 i=0
 while i