历史天气爬虫

# coding: utf-8
import re
from bs4 import BeautifulSoup
import requests


def main(city='zhengzhou', ymonth='202301'):

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
    }

    url = F'http://www.tianqihoubao.com/lishi/{city}/month/{ymonth}.html'
    content = requests.get(url=url, headers=headers)
    soup = BeautifulSoup(content.text, 'lxml')
    weather = soup.find_all('tr')

    # 逐日处理
    for info in weather:
        info = str(info).replace(' ', '').replace('\r\n', '')
        info = info.replace('\n', '')
        info = re.sub(r'<[^>]+>', ' ', info)
        info = re.sub(r' {2,}', ' ', info.strip())
        print(info)