35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
|
base_url = "https://www.douban.com/doulist/3936287/?start={}&sort=time&playable=0&sub_type="
|
|
|
|
headers = {
|
|
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36',
|
|
'Referer': 'https://www.douban.com/' }
|
|
|
|
for page in range(10):
|
|
|
|
start = page * 25
|
|
url = base_url.format(start)
|
|
|
|
try:
|
|
|
|
response = requests.get(url, headers=headers, timeout=10)
|
|
response.encoding = 'utf-8'
|
|
|
|
|
|
soup = BeautifulSoup(response.text, 'html.parser')
|
|
|
|
items = soup.find_all('div', class_='doulist-item')
|
|
|
|
print(f"===== 第 {page+1} 页 =====")
|
|
for item in items:
|
|
|
|
title_tag = item.find('div', class_='title')
|
|
if title_tag and title_tag.a:
|
|
movie_title = title_tag.a.get_text(strip=True)
|
|
print(movie_title)
|
|
|
|
except Exception as e:
|
|
print(f"第 {page+1} 页请求失败：{str(e)}") |