APK 批量爬取脚本（应用宝和360市场）

• python脚本批量下载apk文件（应用宝和360市场）
  360安卓市场下载 2000个，应用宝2000个
• 代码中的下载路径自行更改

• 运行截图

  
  image.png

• 代码如下

# -*- coding: utf-8 -*-
 
import re
import urllib
import os


class class_360:
    def __init__(self):
        self.urllist=[]
        self.baseurl='http://zhushou.360.cn/list/index/cid/1?page='
    def geturl(self,pageindex):
        for i in range(35,pageindex):
            self.urllist.append(self.baseurl+str(i))
    def spider(self):
        for i in range(len(self.urllist)):
            response=urllib.urlopen(self.urllist[i])
            html=response.read()
            link_list=re.findall(r"(?<=&url=).*?apk",html)
            for url in link_list:
                file_name = url.split('/')[-1]
                # print file_name

                file_path=os.path.join("/tmp",file_name)
                print 'DOWNLOADING : ' + file_path
                urllib.urlretrieve(url,file_path)

    def start(self):
        self.geturl(40)
        self.spider()
        
class class_YYB:
    def __init__(self):
        self.urllist=[]
        self.baseurl='https://android.myapp.com/myapp/category.htm?orgame=1&categoryId='
    def geturl(self,pageindex):
        for i in range(100,pageindex):
            self.urllist.append(self.baseurl+str(i))
    def spider(self):
        for i in range(len(self.urllist)):
            response=urllib.urlopen(self.urllist[i])
            html=response.readlines()
            link_list = []
            for i in range(len(html)):
                if 'ex_url' in html[i]:
                    tmp = html[i].split('ex_url="')[1]
                    tmp = tmp.split('"')[0]
                    link_list.append(tmp)

            for url in link_list:
                file_name = url.split('=')[1]
                file_name = file_name.split('&')[0]
                # print file_name

                file_path=os.path.join("/tmp",file_name)
                print 'DOWNLOADING : ' + file_path
                urllib.urlretrieve(url,file_path)

    def start(self):
        self.geturl(122)
        self.spider()
        
if __name__ == '__main__':

    # # 360 应用市场
    # a=class_360()
    # a.start()

    # 应用宝
    b=class_YYB()
    b.start()