网络爬虫初涉——用python爬取天气

代码如下：

import requests
from bs4 import BeautifulSoup

class get_weather(object):
    def __init__(self):
        self.server = "https://m.tianqi.com/"
        self.target = "https://m.tianqi.com/beijing/"

        #加入header是把爬虫伪装成浏览器进行访问
        self.header = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36"}

    def get_it(self):
        req = requests.get(url=self.target, headers=self.header)
        req.encoding = 'UTF-8'
        html = req.text
        #print(html)
        html_bf = BeautifulSoup(html, 'lxml')
        #city = html_bf.find('div', class_='hhx_index_newHead_l')
        city = html_bf.select('.hhx_index_newHead_l text')
        print(city[0].get_text())
        html_bf1 = html_bf.find_all('div', class_='city_weather cbg_b1 citydt')
        for x in html_bf1:
            print(x.get_text())
        #print(html_bf1.get_text())
        time24 = html_bf.find_all('p', class_='hhx_newAllDayTit')
        time_24 = html_bf.find_all('ul', class_='hhx_newAllDayUl')
        print(time24[0].a.get_text())
        for y in time_24:
            print(y.get_text())
        #print(time_24[0].li)



if __name__ == "__main__":
    dl = get_weather()
    dl.get_it()

参考

python爬虫
python爬取天气预报
关于Header的参考博文
查看浏览器Header