From aaba8c49853532abf6ad1bcecf1c0d4acdcb0afe Mon Sep 17 00:00:00 2001
From: 2509165005 <2509165005@student.edu.cn>
Date: Tue, 31 Mar 2026 11:32:51 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AE=8C=E6=88=90=E4=BD=9C=E4=B8=9A6?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 2026.3.31..05.py | 54 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
 create mode 100644 2026.3.31..05.py

diff --git a/2026.3.31..05.py b/2026.3.31..05.py
new file mode 100644
index 0000000..ddd6f03
--- /dev/null
+++ b/2026.3.31..05.py
@@ -0,0 +1,54 @@
+
+import re
+import csv
+
+
+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
+
+pattern = r'<span class="title">([^<&]+)</span>'
+titles = re.findall(pattern, html)
+
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+top10 = chinese_titles[:10]
+
+rating_pattern = r'<span class="rating_num"[^>]*>(\d+\.?\d*)</span>'
+
+ratings = re.findall(rating_pattern, html)
+
+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())
+
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+print('电影名称(前10部):')
+for i, title in enumerate(chinese_titles[:10], 1):
+    print(f'{i}. {title}')
\ No newline at end of file