From d17df9bc785dd760603097f03f20bab0062e88d4 Mon Sep 17 00:00:00 2001
From: 2509165015 <2509165015@student.edu.cn>
Date: Tue, 24 Mar 2026 11:33:39 +0800
Subject: [PATCH] =?UTF-8?q?=E7=BD=91=E7=BB=9C=E6=95=B0=E6=8D=AE=E9=87=87?=
 =?UTF-8?q?=E9=9B=86=EF=BC=88=E7=88=AC=E8=99=AB=E5=9F=BA=E7=A1=80=EF=BC=89?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 260324+2509165015/douban.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 260324+2509165015/douban.py

diff --git a/260324+2509165015/douban.py b/260324+2509165015/douban.py
new file mode 100644
index 0000000..48d4848
--- /dev/null
+++ b/260324+2509165015/douban.py
@@ -0,0 +1,30 @@
+import requests
+from bs4 import BeautifulSoup
+import time
+BASE_URL = "https://xxx.com/list?page="  
+START_PAGE = 1                           
+END_PAGE = 100                           
+HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+}
+
+def crawl_page(page):
+    url = f"{BASE_URL}{page}"
+    try:
+        resp = requests.get(url, headers=HEADERS, timeout=10)
+        resp.raise_for_status()
+        soup = BeautifulSoup(resp.text, "html.parser")
+        items = soup.find_all("div", class_="item")
+        for item in items:
+            title = item.find("h3").get_text(strip=True)
+            print(title)
+
+        print(f"第 {page} 页爬取完成")
+
+    except Exception as e:
+        print(f"第 {page} 页出错：{e}")
+
+if __name__ == "__main__":
+    for page in range(START_PAGE, END_PAGE + 1):
+        crawl_page(page)
+        time.sleep(1)  
\ No newline at end of file