Python爬蟲抓取 實現代碼

最近在做淘寶U站，因為參加一個比賽，每天看自己的票數太麻煩，干脆寫了一個抓取程序，下面的程序是抓取的代碼
 

# -*- coding: utf-8 -*-
#!/usr/bin/python
# Filename : uz.py
import re
import urllib2,string
import thread, time
import sys   
reload(sys) 
sys.setdefaultencoding('utf-8') 

class Spider(object):
	"""docstring for Spider"""
	def __init__(self):
		super(Spider, self).__init__()
		self.enale = True
		self.page = 1
		self.url = 'http://display.taobao.com/chengling/voteusitemr.htm?perPageSize=12&currentRand=95&toPage='
		self.post = ''

	def getPage(self,num):
		global Allitems
		url = self.url+str(num)
		response = urllib2.urlopen(url)
		responsePage = response.read()
		unicodePage = responsePage.decode('utf-8')

		myItems = re.findall('
.*?.*?.*?.*?.*?(.*?).*?.*?.*?',unicodePage,re.S)
		
		#print myItems
		items = []
		for item in myItems:
		    # item 分別對應是url,名稱，票數
		    Allitems.append([item[0].replace("\n",""),item[1].replace("\n",""),item[2].replace("\n","")])
		#return items


	def loadPage(self,num):
		global lock
		lock.acquire() #獲取瑣
		print u"正在加載第%d頁內容請稍候..." % num 
		self.post = self.getPage(num)
		lock.release() #釋放瑣

	def Start(self):
		for x in xrange(1,29):
			#print x
			thread.start_new_thread(self.loadPage,(x,))
			time.sleep(1)



print u'開始統計：'
Allitems=[]
lock = thread.allocate_lock() #創建一個瑣對象
Spider = Spider()
Spider.Start()

print u'正在排序請稍等...'
time.sleep(1)
Allitems = sorted(Allitems, key=lambda items : items[2],reverse=True)
#f=open('uz.html','w+')
key = 1
for item in Allitems:
	if int(item[2]) >=100:
		#f.write('第'+str(key)+'名:'+item[2]+'票--'+item[1]+item[0]+"\n")		
		print u'第'+str(key)+'名:'+item[2]+'票--'+item[1]+item[0]
		key +=1
#f.close()  	
print len(Allitems)
print u'按回車退出'
raw_input(' ')