爬虫学习（三）用beautiful 解析html

安装库

import  requests
from bs4 import BeautifulSoup
headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"}
for start_num in range(0,250,25):response = requests.get(f"https://movie.douban.com/top250?start={start_num}",headers = headers)html = response.textsoup = BeautifulSoup(html,"html.parser")all_title = soup.findAll("span",attrs={"class":"title"})for title in all_title:title_string = title.stringif "/" not in title_string:print(title_string)