#coding=utf-8
from __future__ import print_function
from bs4 import BeautifulSoup
import urllib2
import sys
import string
reload(sys)
sys.setdefaultencoding("gbk")
filename="top500.csv"
f=open(filename,'w')
f.write('num,name,country,address,indroduce'+'\n')
a=1
for ye in range(0,20):
    url="http://www.alexa.com/topsites/global;"+str(ye)
    page=urllib2.urlopen(url)
    soup=BeautifulSoup(page)
    nameLists=soup.findAll(attrs={"class":"site-listing"})
    for names in nameLists:
        name=names.find('a').text
        print(name)
        siteUrl="http://www.alexa.com/siteinfo/"+name
        ipUrl="http://www.ip.cn/index.php?ip=www."+name
        print(siteUrl)
        #获取网站所在国家
        pageSite=urllib2.urlopen(siteUrl)
        soup=BeautifulSoup(pageSite)
        titleLists=soup.findAll(attrs={"class":"metrics-title"})
        country=titleLists[1].find('a').text
        print(country)
        #获取网站服务器所在位置
        ipSite=urllib2.urlopen(ipUrl)
        soup=BeautifulSoup(ipSite)
        addressList=soup.find(attrs={"class":"well"})
        addresses=addressList.findAll('p')
        address=addresses[1].text
        address=address.replace(',',' ')#替换掉','
        print(address)
        name1="www."+name
        print(name1)
        introduce=names.find(attrs={"class":"description"}).text
        introduce=introduce.replace('... More','')
        introduce=introduce.replace(',','.')#替换掉','
        paiming=str(a)
        f.write(paiming+','+name+','+country+','+address+','+introduce.encode('gbk','ignore')+'\n')
        a=string.atoi(paiming)+1
f.close()
print("\nover")

贴出代码，爬到第四个数据就爬不动了，光标一直闪没有继续下去，请教一下是因为打开的url太多了么，并且有循环嵌套，不是的话是什么原因呢，说明一下我的是10M宽带应该不是网速的问题吧。