From 69020fce24639b61485e0475d50e7388175aacd5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=B5=96=E6=AC=A3=E8=8C=B9?=
 <2509165049@student.example.com>
Date: Tue, 31 Mar 2026 11:14:11 +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

---
 import requests.rb | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 import requests.rb

diff --git a/import requests.rb b/import requests.rb
new file mode 100644
index 0000000..d49471a
--- /dev/null
+++ b/import requests.rb	
@@ -0,0 +1,44 @@
+import requests
+import re
+import json
+
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+}
+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>'
+quote_pattern = r'<span class="inq">([^<]+)</span>'
+
+titles = re.findall(title_pattern, html)
+ratings = re.findall(rating_pattern, html)
+quotes = re.findall(quote_pattern, html)
+
+movies = []
+title_index = 0
+for i in range(10):
+    # 跳过英文名（带/的）
+    while title_index < len(titles) and titles[title_index].startswith('/'):
+        title_index += 1
+    
+    movie = {
+        'rank': i + 1,
+        'title': titles[title_index] if title_index < len(titles) else '',
+        'en_title': '',
+        'rating': ratings[i] if i < len(ratings) else '',
+        'quote': quotes[i] if i < len(quotes) else ''
+    }
+    # 检查下一个是不是英文名
+    if title_index + 1 < len(titles) and titles[title_index + 1].startswith('/'):
+        movie['en_title'] = titles[title_index + 1].replace('/ ', '')
+    
+    movies.append(movie)
+    title_index += 1
+
+with open('movies.json', 'w', encoding='utf-8') as f:
+    json.dump(movies, f, ensure_ascii=False, indent=2)
+
+print('已保存到 movies.json')