From 00bc332a2f28af7cb5bf9c3104a0f4f0869662ff Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E7=BD=97=E8=89=BA=E6=AC=A3?=
 <2509165020@student.example.com>
Date: Sun, 5 Jul 2026 17:38:32 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20q2=5F1=5Fcrawler?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 q2_1_crawler/电影爬取.txt | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 q2_1_crawler/电影爬取.txt

diff --git a/q2_1_crawler/电影爬取.txt b/q2_1_crawler/电影爬取.txt
new file mode 100644
index 0000000..8ae53fa
--- /dev/null
+++ b/q2_1_crawler/电影爬取.txt
@@ -0,0 +1,36 @@
+import requests
+import re
+from bs4 import BeautifulSoup as bs
+import json
+
+header = {'User-Agent':'Mozilla/5.0'}
+url = 'https://exam.detr.top/exam-b/movies'
+
+html = requests.get(url, headers=header).text
+# print(html)
+open('movies.html','w',encoding='utf-8').write(html)
+# print(html)
+# print('============')
+# fd = bs(html, 'html.parser').find('p', class_='meta')
+fd = re.search(r'exam_fingerprint:\s*(\S+)',html).group(1)
+# print(fd)
+
+resp = bs(html, 'html.parser').find_all('tr', class_='item-row')
+# print(resp)
+movies = []
+for i in resp:
+    c = []
+    for r in i.find_all('td'):
+        c.append(r.text.strip())
+    movies.append({
+        'id':int(c[0]),
+        'title':c[1],
+        'director':c[2],
+        'year':int(c[3]),
+        'rating':float(c[4]),
+        'duration':int(c[5]),
+        'genre':c[6],
+        'actors_count':int(c[7])
+    })
+
+json.dump({"ID": fd, "movies":movies}, open('movies.json', 'w', encoding='utf-8'), ensure_ascii=False, indent=2)
\ No newline at end of file