From 89df5438eb7677d93e4a7420aca19f3fed66b9ce Mon Sep 17 00:00:00 2001
From: 2509165016 <2509165016@student.edu.cn>
Date: Tue, 24 Mar 2026 11:32:21 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AE=8C=E6=88=90=E4=BD=9C=E4=B8=9A=E4=BA=8C?=
 =?UTF-8?q?=EF=BC=9A=E7=AC=AC=E4=B8=89=E6=AC=A1=E7=88=AC=E8=99=ABpy?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 爬虫3.py.txt | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)
 create mode 100644 爬虫3.py.txt

diff --git a/爬虫3.py.txt b/爬虫3.py.txt
new file mode 100644
index 0000000..bb0b733
--- /dev/null
+++ b/爬虫3.py.txt
@@ -0,0 +1,26 @@
+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',
+}
+
+url = 'https://www.douban.com/doulist/3936288/?start=25&sort=time&playable=0&sub_type='
+response = requests.get(url, headers=headers, timeout=10)
+response.encoding = 'utf-8'
+for page in range(10):
+        url = f'https://movie.douban.com/top250?start={page*25}'
+        print(f'正在爬取第 {page+1} 页：{url}')
+        
+# print(response.status_code)
+soup = BeautifulSoup(response.text, 'html.parser')
+
+movies = []
+
+for a in soup.find_all('a'):
+    href = a.get('href', '')
+    if '?' in href:
+        title = a.get_text(strip=True)
+        print(title)
+        movies.append(title)
+         
\ No newline at end of file