python google play_python google play

#!/usr/env python

#-*- coding: utf-8 -*-

import urllib

import urllib2

import random

import requests

import os,sys

import MySQLdb

from sgmllib import SGMLParser

from BeautifulSoup import BeautifulSoup

import re

num=0

def main():

try:

conn=MySQLdb.connect(host='localhost',user='root',passwd='123456',db='googlemarket',charset="utf8")

conn.query("set names utf8")

except Exception,e:

print e

sys.exit()

cursor=conn.cursor()

category=['PERSONALIZATION','TRANSPORTATION','SPORTS','HEALTH_AND_FITNESS','APP_WALLPAPER','COMICS','MEDICAL','BUSINESS','BOOKS_AND_REFERENCE','WEATHER','ENTERTAINMENT','MEDIA_AND_VIDEO','APP_WIDGETS','TOOLS','PHOTOGRAPHY','PRODUCTIVITY','EDUCATION','NEWS_AND_MAGAZINES','TRAVEL_AND_LOCAL','LIFESTYLE','SOCIAL','FINANCE','SHOPPING','LIBRARIES_AND_DEMO','COMMUNICATION','MUSIC_AND_AUDIO','GAME']

for k in range(0,27):

t="https://play.google.com/store/apps/category/"+category[k]

html=requests.get(t)

preresult=html.content

soup=BeautifulSoup(preresult)

result=soup.prettify("utf-8")

pattern=re.compile('

dataresult=re.findall(pattern,result)

dataresult=list(set(dataresult))

for i in dataresult:

url="https://play.google.com"+i

print url

#url="https://play.google.com/store/apps/details?id=com.androidesk&hl=zh_CNhttps%3A%2F%2Fplay.google.com%2Fstore%2Fapps%2Fdetails%3Fid%3Dcom.androidesk"

html=requests.get(url)

preresult=html.content

soup=BeautifulSoup(preresult)

result=soup.prettify("utf-8")

#名称

pattern=re.compile('

')

data2=re.findall(pattern,result)

print data2[0]

#更新时间

pattern=re.compile('itemprop="datePublished">([\s\S]*?)

')
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值