From 18cd09b6d235e632981dffa5458cc935649da3cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9E=97=E8=B4=B5=E7=8F=8D?=
 <2509165009@student.example.com>
Date: Tue, 23 Jun 2026 11:06:07 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=A0=E9=99=A4=2026062309.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 26062309.py | 50 --------------------------------------------------
 1 file changed, 50 deletions(-)
 delete mode 100644 26062309.py

diff --git a/26062309.py b/26062309.py
deleted file mode 100644
index 3ff21ab..0000000
--- a/26062309.py
+++ /dev/null
@@ -1,50 +0,0 @@
-import requests
-import json
-from bs4 import BeautifulSoup
-
-# 请求检测头（题目硬性要求）
-headers = {
-    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
-}
-url = "https://exam.detr.top/exam-b/movies"
-
-response = requests.get(url, headers=headers)
-response.raise_for_status()
-response.encoding = "utf-8"
-
-# 保存网页源码
-with open("movies.html", "w", encoding="utf-8") as f:
-    f.write(response.text)
-
-# 解析表格数据
-soup = BeautifulSoup(response.text, "html.parser")
-table = soup.find("table")
-tr_rows = table.find_all("tr")[1:]
-
-movie_list = []
-for row in tr_rows:
-    cell = row.find_all("td")
-    info = {
-        "id": int(cell[0].text.strip()),
-        "title": cell[1].text.strip(),
-        "director": cell[2].text.strip(),
-        "year": int(cell[3].text.strip()),
-        "rating": float(cell[4].text.strip()),
-        "duration": int(cell[5].text.strip()),
-        "genre": cell[6].text.strip(),
-        "actors_count": int(cell[7].text.strip())
-    }
-    movie_list.append(info)
-
-# 提取页面数据编号
-data_code = soup.find("code").get_text(strip=True)
-result = {
-    "data_id": data_code,
-    "movies": movie_list
-}
-
-# 写入JSON文件
-with open("movies.json", "w", encoding="utf-8") as f:
-    json.dump(result, f, ensure_ascii=False, indent=4)
-
-print("✅ 爬取完成，两个文件已正常生成")
\ No newline at end of file