学习python期间,自己写的一个小的爬虫文件,从360应用市场下载接近两千个app,代码放在
github里
# -*- coding: utf-8 -*-
"""
Created on Fri May 12 11:30:11 2017
@author: GXW
"""
import re
import urllib
import os
#response=urllib.urlopen('http://zhushou.360.cn/list/index/cid/1?page=1')
#html=response.read()
#link_list=re.findall(r"(?<=&url=).*?apk",html)
#for url in link_list:
# print url
class testClass:
def __init__(self):
self.urllist=[]
self.k=111
self.baseurl='http://zhushou.360.cn/list/index/cid/1?page='
def geturl(self,pageindex):
for i in range(1,pageindex+1):
self.urllist.append(self.baseurl+str(i))
def spider(self):
for i in range(len(self.urllist)):
response