From 490fd747ccf931cb647139693d70ed9d4f2a2fd4 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, 31 Mar 2026 11:22:15 +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
---
26331,09test.py | 26 ++++++++++++++++++++++++++
26331,09test1.py | 41 +++++++++++++++++++++++++++++++++++++++++
26331,09test2.py | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
26331,09test3.py | 18 ++++++++++++++++++
26331,09test4.py | 18 ++++++++++++++++++
5 files changed, 151 insertions(+)
create mode 100644 26331,09test.py
create mode 100644 26331,09test1.py
create mode 100644 26331,09test2.py
create mode 100644 26331,09test3.py
create mode 100644 26331,09test4.py
diff --git a/26331,09test.py b/26331,09test.py
new file mode 100644
index 0000000..77bd010
--- /dev/null
+++ b/26331,09test.py
@@ -0,0 +1,26 @@
+import requests
+import re
+
+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'([^<&]+)'
+titles = re.findall(pattern, html)
+
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+top10 = chinese_titles[:10]
+
+with open('movies.txt', 'w', encoding='utf-8') as f:
+ for i, title in enumerate(top10, 1):
+ f.write(f'{i}. {title}\n')
+
+print('已保存前10部电影到 movies.txt')
+
+with open('movies.txt', 'r', encoding='utf-8') as f:
+ print(f.read())
\ No newline at end of file
diff --git a/26331,09test1.py b/26331,09test1.py
new file mode 100644
index 0000000..0f91053
--- /dev/null
+++ b/26331,09test1.py
@@ -0,0 +1,41 @@
+import requests
+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
+
+title_pattern = r'([^<&]+)'
+rating_pattern = r']*>(\d+\.?\d*)'
+
+titles = re.findall(title_pattern, html)
+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())
\ No newline at end of file
diff --git a/26331,09test2.py b/26331,09test2.py
new file mode 100644
index 0000000..a43670f
--- /dev/null
+++ b/26331,09test2.py
@@ -0,0 +1,48 @@
+import requests
+import re
+import json
+
+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
+
+title_pattern = r'([^<&]+)'
+rating_pattern = r']*>(\d+\.?\d*)'
+quote_pattern = r'([^<]+)'
+
+titles = re.findall(title_pattern, html)
+ratings = re.findall(rating_pattern, html)
+quotes = re.findall(quote_pattern, html)
+
+movies = []
+title_index = 0
+for i in range(10):
+ while title_index < len(titles) and titles[title_index].startswith('/'):
+ title_index += 1
+
+ movie = {
+ 'rank': i + 1,
+ 'title': titles[title_index] if title_index < len(titles) else '',
+ 'en_title': '',
+ 'rating': ratings[i] if i < len(ratings) else '',
+ 'quote': quotes[i] if i < len(quotes) else ''
+ }
+ if title_index + 1 < len(titles) and titles[title_index + 1].startswith('/'):
+ movie['en_title'] = titles[title_index + 1].replace('/ ', '')
+
+ movies.append(movie)
+ title_index += 1
+
+with open('movies.json', 'w', encoding='utf-8') as f:
+ json.dump(movies, f, ensure_ascii=False, indent=2)
+
+print('已保存到 movies.json')
+
+with open('movies.json', 'r', encoding='utf-8') as f:
+ data = json.load(f)
+ print(f'共保存 {len(data)} 部电影')
+ for m in data[:3]:
+ print(f" {m['rank']}. {m['title']} ({m['en_title']}) - {m['rating']}")
\ No newline at end of file
diff --git a/26331,09test3.py b/26331,09test3.py
new file mode 100644
index 0000000..d646f81
--- /dev/null
+++ b/26331,09test3.py
@@ -0,0 +1,18 @@
+import csv
+
+with open('movies.csv', 'r', encoding='utf-8') as f:
+ reader = csv.DictReader(f)
+
+ print('评分高于9.5的电影：')
+ print('-' * 40)
+
+ count = 0
+ for row in reader:
+ if float(row['rating']) > 9.5:
+ count += 1
+ print(f"{row['rank']}. {row['title']}")
+ print(f" 英文名: {row['en_title']}")
+ print(f" 评分: {row['rating']}")
+ print()
+
+ print(f'共 {count} 部评分超过9.5')
\ No newline at end of file
diff --git a/26331,09test4.py b/26331,09test4.py
new file mode 100644
index 0000000..70b639f
--- /dev/null
+++ b/26331,09test4.py
@@ -0,0 +1,18 @@
+import json
+
+with open('movies.json', 'r', encoding='utf-8') as f:
+ movies = json.load(f)
+
+total = sum(float(m['rating']) for m in movies)
+average = total / len(movies)
+print(f'Top10 电影平均分: {average:.2f}')
+
+highest = max(movies, key=lambda m: float(m['rating']))
+print(f'\n评分最高的电影:')
+print(f" {highest['rank']}. {highest['title']} ({highest['en_title']})")
+print(f" 评分: {highest['rating']}")
+
+with_quote = [m for m in movies if m['quote']]
+print(f'\n有经典台词的电影: {len(with_quote)} 部')
+for m in with_quote:
+ print(f" \"{m['quote']}\" —— {m['title']}")
\ No newline at end of file