上传文件至 /

26.03.31 43movies.py

@@ -0,0 +1,43 @@
+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'<span class="title">([^<&]+)</span>'
+rating_pattern = r'<span class="rating_num"[^>]*>(\d+\.?\d*)</span>'
+
+titles = re.findall(title_pattern, html)
+ratings = re.findall(rating_pattern, html)
+
+movies = []
+for i in range(min(10, len(titles))):
+    # 每两个title为一组（中文 + 可能有的英文）
+    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())

26.03.31 43test.py

@@ -0,0 +1,33 @@
+import requests
+import re
+
+# 1. 发送请求获取页面
+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
+
+# 2. 用正则表达式提取电影名称
+# 电影名称在 <span class="title"> 中
+pattern = r'<span class="title">([^<&]+)</span>'
+titles = re.findall(pattern, html)
+
+# 3. 过滤掉英文名（只保留中文名）
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+# 取前10个
+top10 = chinese_titles[:10]
+
+# 4. 保存到文本文件
+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')
+
+# 显示内容验证
+with open('movies.txt', 'r', encoding='utf-8') as f:
+    print(f.read())

26.03.31 43test1.py

@@ -0,0 +1,52 @@
+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'<span class="title">([^<&]+)</span>'
+rating_pattern = r'<span class="rating_num"[^>]*>(\d+\.?\d*)</span>'
+quote_pattern = r'<span class="inq">([^<]+)</span>'
+
+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']}")

26.03.31 43test2.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')

26.03.31 43test3.py

@@ -0,0 +1,22 @@
+import json
+
+# 读取JSON
+with open('movies.json', 'r', encoding='utf-8') as f:
+    movies = json.load(f)
+
+# 计算平均分
+total = sum(float(m['rating']) for m in movies)
+average = total / len(movies)
+print(f'Top10 电影平均分: {average:.2f}')
+
+# 找出最高分
+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']}")
+
+# 统计有经典台词的电影
+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']}")