Script/xiaoya_compare_files.py

# 处理115文件
# python compare_files.py - -pan115 "115share_list.txt" "115share_list [tg].txt"

# 处理夸克文件
# python compare_files.py - -quark "quarkshare_list.txt" "quarkshare_list [tg].txt"

# 同时处理两种文件
# python compare_files.py - -pan115 "115share_list.txt" "115share_list [tg].txt" - -quark "quarkshare_list.txt" "quarkshare_list [tg].txt"
import sys
import argparse

def read_file(filename):
    with open(filename, 'rb') as f:
        return f.read().decode('utf-8').splitlines()

def get_share_type(filename):
    """判断分享文件类型"""
    filename_lower = filename.lower()
    # 115网盘相关的文件名模式
    if any(pattern in filename_lower for pattern in ['115share', '115code', '115pan']):
        return "115"
    # 夸克网盘相关的文件名模式
    elif any(pattern in filename_lower for pattern in ['quarkshare', 'quarkcode', 'quarkpan']):
        return "quark"
    else:
        raise ValueError(f"无法判断文件类型: {filename}\n文件名需包含 '115share/115code/115pan' 或 'quarkshare/quarkcode/quarkpan'")

def verify_file_types(file1, file2):
    """验证两个文件是否属于同一类型"""
    type1 = get_share_type(file1)
    type2 = get_share_type(file2)
    if type1 != type2:
        raise ValueError(f"文件类型不匹配:\n{file1} 是 {type1} 类型\n{file2} 是 {type2} 类型")
    return type1

def extract_share_id(line, share_type):
    """根据不同类型提取分享ID"""
    parts = line.strip().split()
    if len(parts) >= 3:
        if share_type == "115":
            return parts[1]  # 115格式：第二部分是分享ID
        elif share_type == "quark":
            return f"{parts[1]}_{parts[2]}"  # 夸克格式：第二和第三部分组合
    return None

def get_category(line):
    """获取分类路径（第一个部分）"""
    parts = line.strip().split()
    return parts[0] if parts else ""

def merge_files(file1, file2):
    """根据文件名判断类型并合并文件"""
    # 判断并验证文件类型
    share_type = verify_file_types(file1, file2)
    output_prefix = f"merged_{share_type}"
    
    output_file = f"{output_prefix}share_list.txt"
    removed_file = f"removed_{share_type}share_items.txt"
    
    # 读取并合并所有有效行
    lines1 = [line for line in read_file(file1) if line.strip()]
    lines2 = [line for line in read_file(file2) if line.strip()]
    
    # 使用字典来存储，键为"分类+分享ID"，值为完整行
    share_dict = {}
    removed_lines = []
    
    # 处理第一个文件
    for line in lines1:
        share_id = extract_share_id(line, share_type)
        if share_id:
            category = get_category(line)
            key = f"{category}_{share_id}"
            share_dict[key] = line

    # 处理第二个文件，记录重复项
    for line in lines2:
        share_id = extract_share_id(line, share_type)
        if share_id:
            category = get_category(line)
            key = f"{category}_{share_id}"
            if key in share_dict:
                removed_lines.append(line)
            else:
                share_dict[key] = line

    # 写入去重后的文件
    with open(output_file, 'w', encoding='utf-8') as f:
        for line in share_dict.values():
            f.write(line + '\n')
    
    # 写入删除项清单
    with open(removed_file, 'w', encoding='utf-8') as f:
        f.writelines(line + '\n' for line in removed_lines)
    
    print(f"处理完成！")
    print(f"合并后的文件：{output_file}")
    print(f"重复项清单：{removed_file}")

def main():
    """主函数，处理不同类型的文件"""
    parser = argparse.ArgumentParser(description='合并并去重分享链接文件')
    parser.add_argument('--pan115', nargs=2, metavar=('FILE1', 'FILE2'),
                      help='115网盘的两个文件')
    parser.add_argument('--quark', nargs=2, metavar=('FILE1', 'FILE2'),
                      help='夸克网盘的两个文件')
    
    args = parser.parse_args()
    
    # 处理115网盘文件
    if args.pan115:
        try:
            merge_files(args.pan115[0], args.pan115[1])
        except FileNotFoundError:
            print(f"未找到115网盘分享文件: {args.pan115}")
        except ValueError as e:
            print(f"处理115网盘文件时出错: {e}")
    
    # 处理夸克网盘文件
    if args.quark:
        try:
            merge_files(args.quark[0], args.quark[1])
        except FileNotFoundError:
            print(f"未找到夸克网盘分享文件: {args.quark}")
        except ValueError as e:
            print(f"处理夸克网盘文件时出错: {e}")

if __name__ == "__main__":
    main()