python 简单采集测试

#coding:utf8
import requests,re,sys

#防止 编码问题
reload(sys)
sys.setdefaultencoding('utf8')


for i in range(1,400000):
    res = requests.get('http://www.yangtuobaobei.cn/?'+str(i))
    if res.status_code==200:
        userFile = open('user.txt','a')
        #多行匹配,拿到用户名
        user = re.compile('<h2 class="mt">\n(.*?)</h2>', re.S)
        myUser= user.findall(res.text)
        if(len(myUser)>=1):
            print str(i)+"--"+myUser[0]
            myStr = str(i)+"   --------   "+myUser[0]+"\n"
            userFile.write(myStr)

    else:
        print "无法找到该网页"