Files
task-2-1-data-collection/260324.py
2026-03-24 11:26:09 +08:00

21 lines
600 B
Python

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/120.0.0.0 Safari/537.36',
}
url = 'https://movie.douban.com/top250'
reponse =requests.get(url,headers=headers,timeout=10)
reponse.encoding = 'utf-8'
soup = BeautifulSoup(reponse.text,'html.parser')
movies = []
for a in soup.find_all('a'):
herf = a.get('herf','')
if '/subject' in herf:
title = a.get_text(strip=True)
if title:
print(title)
movies.append(title)