From 3afeb83aeaadd5cd392ac667b80831f5907636d1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9D=8E=E9=9B=84=E5=A2=9E?=
 <2509165048@student.example.com>
Date: Sun, 5 Jul 2026 23:29:08 +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/q2_1.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 q2_1_crawler/q2_1.py

diff --git a/q2_1_crawler/q2_1.py b/q2_1_crawler/q2_1.py
new file mode 100644
index 0000000..03aea6b
--- /dev/null
+++ b/q2_1_crawler/q2_1.py
@@ -0,0 +1,31 @@
+import re
+import requests
+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