历史天气爬虫 

 1 # coding: utf-8
 2 import re
 3 from bs4 import BeautifulSoup
 4 import requests
 5 
 6 
 7 def main(city='zhengzhou', ymonth='202301'):
 8 
 9     headers = {
10         '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'
11     }
12 
13     url = F'http://www.tianqihoubao.com/lishi/{city}/month/{ymonth}.html'
14     content = requests.get(url=url, headers=headers)
15     soup = BeautifulSoup(content.text, 'lxml')
16     weather = soup.find_all('tr')
17 
18     # 逐日处理
19     for info in weather:
20         info = str(info).replace(' ', '').replace('\r\n', '')
21         info = info.replace('\n', '')
22         info = re.sub(r'<[^>]+>', ' ', info)
23         info = re.sub(r' {2,}', ' ', info.strip())
24         print(info)

 

posted @ 2024-12-13 15:05  ddzhen  阅读(34)  评论(0)    收藏  举报