From 2bd96675c00541f0bc7ab2bb0b2c6d7fb8ef8d39 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=BC=A0=E5=85=B4=E5=AE=87?=
 <2505155046@student.example.com>
Date: Thu, 2 Apr 2026 16:04:48 +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

---
 260402 2505155046.py | 48 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 260402 2505155046.py

diff --git a/260402 2505155046.py b/260402 2505155046.py
new file mode 100644
index 0000000..7d243cb
--- /dev/null
+++ b/260402 2505155046.py	
@@ -0,0 +1,48 @@
+import requests
+import re
+import time
+
+def crawl_douban_top250_regex_with_quote():
+    base_url = "https://movie.douban.com/top250"
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+    }
+    
+    movies = []
+    
+    for start in range(0, 250, 25):
+        url = f"{base_url}?start={start}&filter="
+        
+        response = requests.get(url, headers=headers)
+        html = response.text
+        
+        pattern = re.compile(
+            r'<em class="">(\d+)</em>.+?'
+            r'<span class="title">([^&]+?)</span>.+?'
+            r'<span class="rating_num" property="v:average">(\d\.\d)</span>.+?'
+            r'<p class="quote">(.+?)</p>',
+            re.S 
+        )
+        
+        
+        items = pattern.findall(html)
+        
+        for item in items:
+            rank = item[0]
+            title = item[1]
+            rating = item[2]
+            quote = item[3].strip()  
+            
+            movies.append({
+                "rank": rank,
+                "title": title,
+                "rating": rating,
+                "quote": quote 
+            })
+        
+    
+    return movies
+
+if __name__ == "__main__":
+
+    top250 = crawl_douban_top250_regex_with_quote()
\ No newline at end of file