From 92b30f5682adfdfcf79bfdbf0ba3bfc172554895 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=AE=B8=E6=96=87=E7=90=B3?=
 <2509165042@student.example.com>
Date: Tue, 31 Mar 2026 11:27:18 +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

---
 XWL.py | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 XWL.py

diff --git a/XWL.py b/XWL.py
new file mode 100644
index 0000000..9a95726
--- /dev/null
+++ b/XWL.py
@@ -0,0 +1,39 @@
+import requests
+import re
+import csv
+import time
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+}
+all_movies=[]
+for page in range(10):
+  url = 'https://movie.douban.com/top250'
+  response = requests.get(url, headers=headers)
+  html = response.text
+  title_pattern = r'<span class="title">([^<&]+)</span>'
+  rating_pattern = r'<span class="rating_num"[^>]*>(\d+\.?\d*)</span>'
+  titles = re.findall(title_pattern, html)
+  ratings = re.findall(rating_pattern, html)
+  for i in range(min(25,len(ratings))):
+      title =titles[i*2]if i*2<len(titles)else""
+      en_title=titles[i*2+1].replace('/',").strip() if(i*2+1)<len(titles)else""
+      movies = []
+for i in range(min(10, len(titles))):
+    title = titles[i] if not titles[i].startswith('/') else ''
+    en_title = titles[i+1] if i+1 < len(titles) and titles[i+1].startswith('/') else ''
+    en_title = en_title.replace('/ ', '') if en_title else ''
+    movie = {
+        'rank': i + 1,
+        'title': title,
+        'en_title': en_title,
+        'rating': ratings[i] if i < len(ratings) else ''
+    }
+    movies.append(movie)
+with open('movies.csv', 'w', encoding='utf-8', newline='') as f:
+    writer = csv.DictWriter(f, fieldnames=['rank', 'title', 'en_title', 'rating'])
+    writer.writeheader()
+    writer.writerows(movies)
+print('已保存到 movies.csv')
+with open('movies.csv', 'r', encoding='utf-8') as f:
+    for line in f:
+        print(line.strip())