From 59ddd4fab6e6f4aaf6f1f26b72d4929ba0ffffb4 Mon Sep 17 00:00:00 2001
From: 2509165046 <2509165046@student.edu.cn>
Date: Tue, 24 Mar 2026 20:05:47 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AE=8C=E6=88=90=E4=BD=9C=E4=B8=9A=E4=BA=8C?=
 =?UTF-8?q?=E5=92=8C=E4=B8=89?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 爬虫.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 爬虫.py

diff --git a/爬虫.py b/爬虫.py
new file mode 100644
index 0000000..fad8824
--- /dev/null
+++ b/爬虫.py
@@ -0,0 +1,31 @@
+import requests 
+from bs4 import BeautifulSoup as bs
+url = 'https://www.baidu.com'
+params = {'key': 'value'}
+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}")
+print(response.status_code)
+print('-------------')
+html_content = response.text
+print('--------')
+soup = bs(html_content,'lxml')
+print(soup)
+print('===========')
+title = soup.find('title').string
+print(title)
+print('===========')
+links = soup.find_all('a')
+print(links)
+print("============")
+for link in links:
+    # print("11111111")
+    print("链接:",link.get('href'))
+div_elements = soup.select('div.di')
+print(div_elements)
+for div in div_elements:
+    print('div:',div.text)
+    
\ No newline at end of file