python爬虫练习5——新闻联播

提取新闻联播相关文字并输出

网址：新闻联播 (cctv.com)

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33

import requests import re       url = 'https://tv.cctv.com/lm/xwlb/' ua = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59'} r = requests.get(url , headers = ua ,timeout = 30) r.encoding = r.apparent_encoding   pat1 = '<li><a href="(.*?)" target'       url = re.compile(pat1,re.S).findall(r.text)[2]   r = requests.get(url , headers = ua ,timeout = 30) r.encoding = r.apparent_encoding     pat2 = 'description content="(.*?)<meta name' lst = re.compile(pat2,re.S).findall(r.text) print(lst)     pat3 = '<p><strong>(.*?)</div>' body = re.compile(pat3,re.S).findall(r.text) print(body)     path='C:/Users/Administrator/Desktop/xwlb.txt'   with open (path,'w') as f:         s = str(body)         f.write(s)                f.close()        print('文件保存成功')

　　

 

 

目前只能单条爬取，如何多条爬取输出，还望各位指点，另外，输出内容不能分行，不太美观，还希望各位改进指正