22 lines
794 B
Python
22 lines
794 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://www.douban.com/doulist/3936288/?start=0&sort=time&playable=0&sub_type='
|
|
response = requests.get(url, headers=headers, timeout=10)
|
|
response.encoding = 'utf-8'
|
|
soup = BeautifulSoup(response.text, '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.append(title)
|
|
print('-----------')
|
|
print(movies)
|
|
print(f"第{page+1}页：{title}")
|
|
print(f"1 第{page+1}页爬取完成，共{len(movies)}条数据\n")
|
|
print(f"错第{page+1}页爬取失败：{e}")
|