python3爬虫--抓取天气信息

来源：互联网发布：12306网络订餐配送工编辑：程序博客网时间：2024/05/01 05:16

抓取中国天气网上的数据并打出

Version:Python3.5 Os:win10

import urllib.request
import re
import time
if __name__=='__main__':
url = 'http://www.weather.com.cn/weather/101010100.shtml'
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req=urllib.request.Request(url=url,headers=header)
webPage=urllib.request.urlopen(req)
data = webPage.read()
data = data.decode('utf-8')
date=time.strftime("%Y-%m-%d %H:%M %p", time.localtime())
regzone='<a href="http://bj.weather.com.cn" target="_blank">(.*?)</a>'
regdis=''
reg='\n(.*?)/\n(.*?)'
w=re.compile(reg).findall(data)
wz=re.compile(regzone).findall(data)
wdis=re.compile(regdis).findall(data)
print(date,wz[0],w[0],wdis[0])

顺便写个gui界面：

from tkinter import *
import urllib.request
import re
import time
url = 'http://www.weather.com.cn/weather/101010100.shtml'
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req=urllib.request.Request(url=url,headers=header)
webPage=urllib.request.urlopen(req)
data = webPage.read()
data = data.decode('utf-8')
date=time.strftime("%Y-%m-%d %H:%M %p", time.localtime())
regzone='<a href="http://bj.weather.com.cn" target="_blank">(.*?)</a>'
regdis=''
reg='\n(.*?)/\n(.*?)'
w=re.compile(reg).findall(data)
wz=re.compile(regzone).findall(data)
wdis=re.compile(regdis).findall(data)
class Application(Frame):
def __init__(self, master=None):
Frame.__init__(self, master)
self.pack()
self.createWidgets()
def createWidgets(self):
self.helloLabel = Label(self, text=date+' '+wz[0]+'\n'+wdis[0]+'\n'+'气温范围'+str(w[0]))
self.helloLabel.pack()
app = Application()
# 设置窗口标题:
app.master.title('实时温度')
# 主消息循环:
app.mainloop()

0 0