Files
task-2-1-data-collection/20260324,2509165013.py
2509165013 e72f5e189d 作业
2026-03-24 11:34:34 +08:00

22 lines
593 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/109.0.0.0 Safari/537.36'}
url = 'https://www.douban.com/doulist/3936288/'
response = requests.get(url, headers=headers,timeout=10)
response.enconding = 'utf-8'
soup = BeautifulSoup(response.txt, 'html.parser')
movies = []
for a in soup.find_all('a'):
href = a.get('href','')
if '/subject' in href:
title = a.get_text(strip=True)
print(title)
movies.appenf(title)
print('----------')
print(movies)