28 lines
748 B
Python
28 lines
748 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',
|
||
}
|
||
for page in range(10):
|
||
|
||
url =f'https://www.douban.com/doulist/3936288/?start={page*25}&filter='
|
||
print(f"正在爬取第{page+1}页 ： {url}")
|
||
|
||
response = response.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('herf','')
|
||
if '/subject' in href:
|
||
title = a.get_text(strip=True)
|
||
print(title)
|
||
movies.append(title)
|
||
print('---------')
|
||
print(movies) |