| 123456789101112131415 |
- import random
- import time
- import requests
- from bs4 import BeautifulSoup
- for page in range(10):
- resp = requests.get(
- url=f'https://movie.douban.com/top250?start={25 * page}',
- headers={'User-Agent': 'BaiduSpider'}
- )
- soup = BeautifulSoup(resp.text, "lxml")
- for elem in soup.select('a > span.title:nth-child(1)'):
- print(elem.text)
- time.sleep(random.random() * 5)
|
