Files
task-2-1-data-collection/260324 2505155046.py
2026-03-26 16:12:54 +08:00

24 lines
883 B
Python

import requests
from bs4 import BeautifulSoup
url = f'https://www.douban.com/doulist/3936288/?start=0&sort=time&playable=0&sub_type='
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'}
for page in range(10):
a = page*25
url = f'https://www.douban.com/doulist/3936288/?start=0&sort=time&playable=0&sub_type='
print('爬取第{c}页内容'.format(c=page+1))
response =requests.get(url,headers=headers,timeout=10)
response.encoding = 'utf-8'
#print(response.status_code)
soup = BeautifulSoup(response.text,'html.parser')
print(soup)
#movies = []
#for b in soup.find_all('a'):
# href = b.get('href','')
# if '/subject' in href:
# title = b.get_text(strip=True)
# print(title)
# movies.append(title)
#print('----------------')
#print(movies)