From cb700f4e9a154dc33d89b4f684fcccc58a3120b8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=99=88=E9=92=A6=E7=87=95?=
 <2509165038@student.example.com>
Date: Sat, 4 Jul 2026 02:46:57 +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

---
 1.py     | 30 ++++++++++++++++++++++++++++++
 q4_1.py  | 19 +++++++++++++++++++
 q4_2.py  | 17 +++++++++++++++++
 q4_3a.py | 14 ++++++++++++++
 q4_3b.py | 14 ++++++++++++++
 5 files changed, 94 insertions(+)
 create mode 100644 1.py
 create mode 100644 q4_1.py
 create mode 100644 q4_2.py
 create mode 100644 q4_3a.py
 create mode 100644 q4_3b.py

diff --git a/1.py b/1.py
new file mode 100644
index 0000000..f319e96
--- /dev/null
+++ b/1.py
@@ -0,0 +1,30 @@
+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)
diff --git a/q4_1.py b/q4_1.py
new file mode 100644
index 0000000..b329ba7
--- /dev/null
+++ b/q4_1.py
@@ -0,0 +1,19 @@
+import json
+import matplotlib.pyplot as plt
+
+movies = json.load(open('movies.json', encoding='utf-8'))['movies']
+# print(movies)
+genres = {}
+for m in movies:
+    g = m['genre']
+    if g in genres:
+        genres[g] = genres[g] + 1 
+    else:
+        genres[g] = 1
+print(genres)
+plt.figure(figsize=(8,5))
+plt.bar(genres.keys(), genres.values())
+plt.title('类型电影数量分布')
+plt.xlabel('类型')
+plt.ylabel('数量')
+plt.savefig('q4_1_bar.png', dpi=150)
\ No newline at end of file
diff --git a/q4_2.py b/q4_2.py
new file mode 100644
index 0000000..ec9d996
--- /dev/null
+++ b/q4_2.py
@@ -0,0 +1,17 @@
+import json
+import matplotlib.pyplot as plt
+
+movies = json.load(open('movies.json', encoding='utf-8'))['movies']
+# print(movies)
+ratings = []
+durations = []
+for m in movies:
+    ratings.append(m['rating'])
+    durations.append(m['duration'])
+
+plt.figure(figsize=(8,5))
+plt.scatter(durations,ratings,color='red',alpha=0.6)
+plt.title('时长与评分关系散点图')
+plt.xlabel('duration')
+plt.ylabel('rating')
+plt.savefig('q4_2_scatter.png', dpi=150)
\ No newline at end of file
diff --git a/q4_3a.py b/q4_3a.py
new file mode 100644
index 0000000..ff6357c
--- /dev/null
+++ b/q4_3a.py
@@ -0,0 +1,14 @@
+import json
+import matplotlib.pyplot as plt
+
+movies = json.load(open('movies.json', encoding='utf-8'))['movies']
+# print(movies)
+ratings = []
+durations = []
+for m in movies:
+    ratings.append(m['rating'])
+    durations.append(m['duration'])
+
+plt.figure(figsize=(8,5))
+plt.hist(ratings, bins=5,color='blue')
+plt.savefig('q4_3a_hist.png',dpi=150)
diff --git a/q4_3b.py b/q4_3b.py
new file mode 100644
index 0000000..2e12382
--- /dev/null
+++ b/q4_3b.py
@@ -0,0 +1,14 @@
+import json
+import matplotlib.pyplot as plt
+
+movies = json.load(open('movies.json', encoding='utf-8'))['movies']
+# print(movies)
+ratings = []
+durations = []
+for m in movies:
+    ratings.append(m['rating'])
+    durations.append(m['duration'])
+
+plt.figure(figsize=(8,5))
+plt.hist(durations, bins=5,color='blue')
+plt.savefig('q4_3b_hist.png',dpi=150)
\ No newline at end of file