"""python爬取昆明天气信息"""
import requests
import time
import csv
import random
import bs4
from bs4 import BeautifulSoup
def get_content(url,data=None):
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'
}
timeout=random.choice(range(10,60))
rep=requests.get(url=url,headers=headers,timeout=timeout)
rep.encoding='utf-8'
return rep.text
def get_data(html_text):
final=[]
bs=BeautifulSoup(html_text,"html.parser")
body=bs.body
data=body.find('div',attrs={'id':'7d'})
#data=body.find('div',{'id':'7d'})
print(type(data))
ul=data.find('ul')
li=ul.find_all('li')
for day in li:
temp=[]
date=day.find('h1').string
temp.append(date)
info=day.find_all('p')
title=day.find('p',attrs={'class':'wea'})
temp.append(title.text)
if info[1].find('span') is None:
temperature_hightest=None
else:
temperature_hightest=info[1].find('span').string
temperature_hightest=temperature_hightest.replace("℃","")
temperature_lowest=info[1].find('i').string
temperature_lowest=temperature_lowest.replace("℃","")
temp.append(temperature_hightest)
temp.append(temperature_lowest)
final.append(temp)
return final
def write_date(data,name):
file_name=name
with open(file_name,'w',errors='ignore',newline='') as f:
f_csv=csv.writer(f)
f_csv.writerow(['日期','天气情况','最高温度','最低温度'])
f_csv.writerows(data)
if __name__=='__main__':
url='http://www.weather.com.cn/weather/101290101.shtml'
html=get_content(url)
result=get_data(html)
write_date(result,'weather.csv')
