From f897af5fd484857dc04e56d2f7fe2cc5fdb8748e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E4=BD=99=E5=AD=90=E5=B0=8A?=
 <2509165011@student.example.com>
Date: Tue, 24 Mar 2026 11:44:12 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20/?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 260324 2509165011.py | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100644 260324 2509165011.py

diff --git a/260324 2509165011.py b/260324 2509165011.py
new file mode 100644
index 0000000..1296b81
--- /dev/null
+++ b/260324 2509165011.py	
@@ -0,0 +1,29 @@
+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',
+}
+
+ur1 = 'https://www.douban.com/doulist/3936288/'
+# for page in range(0.250,25):
+#     url = base_url.format(page)
+#     print(f"正在爬取第{page//25+1}页: {url}")
+
+
+
+response = requests.get(ur1, headers=headers,timeout=10)
+response.encoding = 'utf-8'
+
+soup = BeautifulSoup(response.text, 'html.parser')
+
+movies = []
+
+for s in soup.find_all('a'):
+    href = s.get('href', '')
+    if '/subject' in href:
+        title = s.get_text(strip=True)
+        print(title)
+        movies.append(title)
+print('---------------')
+print(movies)
\ No newline at end of file