import requests
from bs4 import BeautifulSoup
def getsorce(url):
# proxy = {'http':'175.42.123.28: 9999'}
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'
}
rep = requests.get(url, headers=headers)
resorce = rep.content.decode('utf-8')
return resorce
def setsorce(resorce):
soup = BeautifulSoup(resorce,'lxml')
tage = soup.find('div', class_='conMidtab')
table = tage.find_all('table')
for tables in table:
tr = tables.find_all('tr')[2:]
for index,trs in enumerate(tr):
td = trs.find_all('td')
city_td = td[0]
weather_td = td[1]
if index ==0:
city_td = td[1]
weather_td = td[2]
city = list(city_td.stripped_strings)[0]
weather = list(weather_td.stripped_strings)[0]
print('城市:',city,'天气:',weather)
def main():
url = 'http://www.weather.com.cn/textFC/db.shtml'
resorce = getsorce(url)
return setsorce(resorce)
if __name__=='__main__':
main()
bs4爬取中国天气网(城市和天气)
最新推荐文章于 2023-02-24 17:53:30 发布