29 lines
756 B
Python
29 lines
756 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',
|
|
}
|
|
|
|
ur1 = 'https://www.douban.com/doulist/3936288/'
|
|
# for page in range(0.250,25):
|
|
# url = base_url.format(page)
|
|
# print(f"正在爬取第{page//25+1}页: {url}")
|
|
|
|
|
|
|
|
response = requests.get(ur1, headers=headers,timeout=10)
|
|
response.encoding = 'utf-8'
|
|
|
|
soup = BeautifulSoup(response.text, 'html.parser')
|
|
|
|
movies = []
|
|
|
|
for s in soup.find_all('a'):
|
|
href = s.get('href', '')
|
|
if '/subject' in href:
|
|
title = s.get_text(strip=True)
|
|
print(title)
|
|
movies.append(title)
|
|
print('---------------')
|
|
print(movies) |