Merge pull request 'dev' (#2) from dev into main

Reviewed-on: #2

urls/main.py

@@ -3,60 +3,75 @@ import urllib.parse
 import argparse
 import re
 import time
+import yaml
 
 def natural_sort_key(s):
     """为了自然排序的辅助函数，将字符串中的数字部分转换成整数"""
     return [int(text) if text.isdigit() else text.lower() for text in re.split('([0-9]+)', s)]
 
-def generate_urls(file_names, base_url, sub_directory):
-    """根据文件名、基础URL和子目录生成URL链接"""
-    urls = []
-    # 确保base_url和sub_directory以斜线结尾（如果sub_directory不为空）
+def generate_urls(file_paths, base_url, sub_directory, min_size):
+    """根据文件路径、基础URL、子目录和最小文件大小生成URL链接"""
+    urls = {}
     if not base_url.endswith('/'):
         base_url += '/'
     if sub_directory and not sub_directory.endswith('/'):
         sub_directory += '/'
-    current_timestamp = int(time.time())  # 获取当前时间的时间戳，转换为整数
-    for name in sorted(file_names, key=natural_sort_key):  # 使用自定义排序
-        file_path = os.path.join('.', name)
-        file_size_bytes = os.path.getsize(file_path)  # 获取文件大小（字节），为整数
-        # 对文件名进行URL编码
-        encoded_name = urllib.parse.quote(name)
-        url = f"{base_url}{sub_directory}{encoded_name}"
-        urls.append(f"{file_size_bytes}:{current_timestamp}:{url}")
+    current_timestamp = int(time.time())  # 移到循环外
+    for path in sorted(file_paths, key=natural_sort_key):
+        file_size_bytes = os.path.getsize(path)
+        if file_size_bytes < min_size:
+            continue
+        relative_path = os.path.relpath(path, start='.')
+        encoded_path = urllib.parse.quote(relative_path)
+        url = f"{base_url}{sub_directory}{encoded_path}"
+        dir_name = os.path.dirname(relative_path)
+        if dir_name not in urls:
+            urls[dir_name] = []
+        urls[dir_name].append(f"{file_size_bytes}:{current_timestamp}:{url}")
     return urls
 
-def save_urls(urls, output_file):
-    """将URL链接保存到文本文件中"""
+def save_urls(urls, output_file, root_folder):
+    """将URL链接保存到YAML文件中"""
     with open(output_file, 'w', encoding='utf-8') as f:
-        for url in urls:
-            f.write(url + '\n')
+        f.write(f"{root_folder}:\n")
+        for dir_name, files in urls.items():
+            if dir_name == '.':
+                for file in files:
+                    f.write(f"  {file}\n")
+            else:
+                f.write(f"  {dir_name}:\n")
+                for file in files:
+                    f.write(f"    {file}\n")
 
 def parse_arguments():
     """解析命令行参数"""
     parser = argparse.ArgumentParser(description='Generate URLs from file names.')
     parser.add_argument('--dir', type=str, default='', help='Sub-directory for generating file URLs (optional)')
+    parser.add_argument('--output', type=str, default='urls.yaml', help='Output file name (default: urls.yaml)')
+    parser.add_argument('--base-url', type=str, default='https://link.kite.kim/feng', help='Base URL for generating file URLs (default: https://link.kite.kim/feng)')
+    parser.add_argument('--min-size', type=int, default=128*1024, help='Minimum file size in bytes (default: 128KB)')
+    parser.add_argument('--rf', type=str, required=True, help='Root folder name for YAML output')
     return parser.parse_args()
 
-def main():
-    # 解析命令行参数
-    args = parse_arguments()
-    
-    # 固定的base_url值
-    base_url = 'https://link.kite.kim/feng'
-    
-    # 获取当前目录下的所有文件名，排除此脚本文件和隐藏文件
-    current_script = os.path.basename(__file__)
-    file_names = [f for f in os.listdir('.') if os.path.isfile(f) and f != current_script and not f.startswith('.')]
-    
-    # 生成URL链接
-    urls = generate_urls(file_names, base_url, args.dir)
-    
-    # 保存URL链接到文本文件
-    output_file = 'urls.txt'
-    save_urls(urls, output_file)
+def list_files_recursive(start_path='.', exclude_files=None):
+    """递归列出目录及其子目录中的所有文件，排除指定的文件"""
+    if exclude_files is None:
+        exclude_files = set()
+    file_paths = []
+    for root, dirs, files in os.walk(start_path):
+        for file in files:
+            if file not in exclude_files:
+                file_paths.append(os.path.join(root, file))
+    return file_paths
 
-    print(f"URL链接已保存到{output_file}")
+def main():
+    args = parse_arguments()
+    current_script = os.path.basename(__file__)
+    exclude_files = {current_script}  # 排除当前脚本文件
+    file_paths = list_files_recursive('.', exclude_files)
+    urls = generate_urls(file_paths, args.base_url, args.dir, args.min_size)
+    save_urls(urls, args.output, args.rf)
+    print(f"URL链接已保存到{args.output}")
 
 if __name__ == '__main__':
-    main()
+    main()