26 lines
1003 B
Python
26 lines
1003 B
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
headers = {
|
|
'User-Agent':'Mozilla/5.0(Windows NT 10.0;win64; x64)AppleWekit/537.36(KHRML,like Gecko) Cheome/120.0.0.0 Safari/537.36'
|
|
}
|
|
url = 'https://www.douban.com/doulist/3936288/'
|
|
|
|
response = requests.get(url,headers=headers)
|
|
if response.status_code ==200:
|
|
html_content = response.text
|
|
print("请求成功,获取到HTML内容")
|
|
soup = BeautifulSoup(html_content,'html.parser')
|
|
title = soup.find('title').string
|
|
print("页面标题：",title)
|
|
links = soup.find_all('a')
|
|
for link in links:
|
|
href = link.get('href')
|
|
if href:
|
|
print("链接地址:",href)
|
|
book_items = soup.select('div.doulist-item')
|
|
for item in book_items:
|
|
book_title = item.select_one('div.title a').get_text(strip=True)
|
|
book_author =item.select_one('div.subject-cast').get_text(strip=True)
|
|
print(f"书名:{book_title}|作者：{book_author}")
|
|
else:
|
|
print(f"请求失败，状态码：{response.status_code}") |