27 lines
799 B
Python
27 lines
799 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='
|
|
for page in range(0,250,25):
|
|
url = url.format(start=page)
|
|
print(f'正在爬取第{page//25+1}页:{url}')
|
|
|
|
|
|
response =requests.get(url,headers=headers,timeout=10)
|
|
response.encoding = 'utf-8'
|
|
|
|
#print(response.status_code)
|
|
|
|
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) |