19 lines
658 B
Plaintext
19 lines
658 B
Plaintext
import requests
|
|
from bs4 import BeautifulSoup
|
|
url = 'https://movie.douban.com/top250'
|
|
params = {'start': '0', 'filter': ''}
|
|
response = requests.get(url, params=params)
|
|
if response.status_code == 200:
|
|
html_content = response.text
|
|
print("请求成功，获取到 HTML 内容")
|
|
else:
|
|
print(f"请求失败，状态码: {response.status_code}")
|
|
soup = BeautifulSoup(html_content, 'lxml')
|
|
title = soup.find('title').string
|
|
print("页面标题:", title)
|
|
links = soup.find_all('a')
|
|
for link in links:
|
|
print("链接地址:", link.get('href'))
|
|
div_elements = soup.select('div.item')
|
|
for div in div_elements:
|
|
print("电影条目内容:", div.text) |