From 16102b329cd5ead44176f687265ddf6c31ed484d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=BF=9E=E5=85=B4=E6=9D=B0?=
 <2509165004@student.example.com>
Date: Tue, 31 Mar 2026 11:28:24 +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

---
 260331-2509165004.py | Bin 0 -> 1024 bytes
 lxj.py               |  33 +++++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)
 create mode 100644 260331-2509165004.py
 create mode 100644 lxj.py

diff --git a/260331-2509165004.py b/260331-2509165004.py
new file mode 100644
index 0000000000000000000000000000000000000000..06d7405020018ddf3cacee90fd4af10487da3d20
GIT binary patch
literal 1024
ScmZQz7zLvtFd70QH3R?z00031

literal 0
HcmV?d00001

diff --git a/lxj.py b/lxj.py
new file mode 100644
index 0000000..8e0810d
--- /dev/null
+++ b/lxj.py
@@ -0,0 +1,33 @@
+import requests
+import re
+
+# 1. 发送请求获取页面
+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
+
+# 2. 用正则表达式提取电影名称
+# 电影名称在 <span class="title"> 中
+pattern = r'<span class="title">([^<&]+)</span>'
+titles = re.findall(pattern, html)
+
+# 3. 过滤掉英文名（只保留中文名）
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+# 取前10个
+top10 = chinese_titles[:10]
+
+# 4. 保存到文本文件
+with open('movies.txt', 'w', encoding='utf-8') as f:
+    for i, title in enumerate(top10, 1):
+        f.write(f'{i}. {title}\n')
+
+print('已保存前10部电影到 movies.txt')
+
+# 显示内容验证
+with open('movies.txt', 'r', encoding='utf-8') as f:
+    print(f.read())
\ No newline at end of file