爬取天气信息（我的第一个爬虫）增加简单的tkinter
本帖最后由 Cool_Breeze 于 2020-7-27 11:21 编辑tkinter
#coding=utf-8
import tkinter as tk
import time
from tianqi import main
def home_mian():
font = 'Consolas', 11
home = tk.Tk()
home.title('天气查询 by cool_breeze')
home.geometry('800x600')
var = tk.StringVar()
varL = []
for n in range(1,18):
varL.append(tk.StringVar()) #将对象放入列表
Llist = []
for n in range(1,18):
Llist.append(tk.Label(home, textvariable=varL, bg ='honeydew', font=font))
L0 = tk.Label(home, textvariable=var, bg ='honeydew', font=font)
for n in Llist:
n.pack(fill=tk.X, side=tk.TOP)
L0.pack(fill=tk.X, side=tk.TOP)
def tishi():
var.set('正在获取网页信息...')
home.update() #更新窗口
def zigong(n):
tishi()
res = main(n)
for i,j in enumerate(varL):
j.set(res)
var.set('')
def exit_():
exit()
zg_bt = tk.Button(home,text='自流井',font=font,bg = 'ivory',width=10,height=1,command=lambda:zigong(1)).pack(side='left')
cd_bt = tk.Button(home,text='成都',font=font,bg = 'ivory',width=10,height=1,command=lambda:zigong(2)).pack(side='left')
dg_bt = tk.Button(home,text='东莞',font=font,bg = 'ivory',width=10,height=1,command=lambda:zigong(3)).pack(side='left')
ex_bt = tk.Button(home,text='退出',font=font,bg = 'ivory',width=10,height=1,command=exit_).pack(side='left')
home.mainloop()
if __name__ == '__main__':
home_mian()
爬虫#coding=utf-8
import urllib.request,urllib.error
from bs4 import BeautifulSoup as bfs
import os
import re
def main(number):
city_list = [
'positionCityID=59289; positionCityPinyin=zigong; lastCountyId=71992; lastCountyPinyin=ziliujing',
'lastCountyId=56294; lastCountyPinyin=chengdu; lastCountyTime=1591617161',
'lastCountyId=59289; lastCountyPinyin=dongguan; lastCountyTime=1591612281',
]
url = 'http://tianqi.2345.com/'
html = askurl(url, city_list)
data = getdata(html)
return data
def format(string):
str_len = len(string)
max_len = 13
if str_len >= 1 and str_len <= max_len:
return string.center(max_len - str_len)
else:
return string
def askurl(url,cookkey):
head = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cookie': 'qd_dz_ct=59289; sts=1; theme=-1; wc=59289; lc=59289; lc2=59289; wc_n=%25u4E1C%25u839E; ' + cookkey,
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3641.400 QQBrowser/10.4.3284.400'
}
req = urllib.request.Request(url=url, headers=head)
try:
response = urllib.request.urlopen(req)
if response.chunked:
print('访问：{} 失败！\n请检查网络是否可以正确的访问Internet！'.format(url))
exit()
except urllib.error.URLError as err:
print('\n网络连接失败！\n请检查网络连接！', err)
input('按任意键退出！')
exit()
html = bfs(response,'html.parser') #解析html
# print(html)
return html
def getdata(html):
datalist = []
datalist.append(html.find('em', class_="location-city location-font1").string)
date_temp = html.find('p', class_="date").contents
datalist.append(date_temp.string + ' ' + date_temp.string)
datalist.append(date_temp.string)
datalist.append(date_temp.string)
#天气情况
weather = html.find('a', class_="wea-info-index")
datalist.append(weather.span.string + weather.b.string)
datalist.append(html.find('a', class_="wea-other-a-we").string)
datalist.append('空气质量：' + html.find('a', class_="wea-aqi-tip-index").em.string)
weather = html.find('ul', class_="wea-info-tip").find_all('li')
datalist.append(weather.span.string + ' : ' + weather.em.string)
datalist.append(weather.span.string + ' : ' + weather.em.string)
datalist.append(weather.span.string + ' : ' + weather.em.string)
# print(datalist)
#获取未来六天的天气数据
tomorrow = [[],[],[],[],[],[]]
def get_tomorrw(htmlobj, index): #相应数据
temp = htmlobj.contents
tomorrow.append(format(temp.text + ' ' + temp.text))
tomorrow.append(format(temp.text))
tomorrow.append(format(temp.text + ' ' + temp.text))
tomorrow.append(format('空气质量：' + temp.text))
info_tomorrow = html.find('ul', class_="weaday7 wea-white-icon")
a_list = info_tomorrow.find_all('a')
for day, index in zip(range(2,14,2),range(6)):
get_tomorrw(a_list, index)
#温度
script = html.findAll('script')[-1]
H = re.compile('var day7DataHight = \[(.*)\]')
L = re.compile('var day7DataLow = \[(.*)\]')
H_list = re.findall(H,str(script)).split(',')
L_list = re.findall(L,str(script)).split(',')
n = 0
for i,j in zip(L_list, H_list):
if not n:
n+=1;continue
tomorrow.insert(3, format(i + ' ~ ' + j))
n+=1
# print(datalist + tomorrow)
return datalist + tomorrow
if __name__ == '__main__':
print(main(3))
能改变城市吗？没有我所在的城市啊 本帖最后由 Cool_Breeze 于 2020-6-9 09:49 编辑
myhic 发表于 2020-6-9 00:09
能改变城市吗？没有我所在的城市啊
可以自己添加城市的，将Cookie添加到列表就好了！
页:
[1]