Python YAML文件特定键值重复项查找教程

pip install pyyaml

import yaml

# 假设您的YAML文件名为 'myyaml.yaml'
with open('myyaml.yaml', 'r') as file:
    data = yaml.safe_load(file)

import yaml
import os

def find_duplicated_ips_with_same_type(yaml_file_path):
    """
    查找YAML文件中IP地址相同且类型也相同的重复条目。

    Args:
        yaml_file_path (str): YAML文件的路径。

    Returns:
        list: 包含重复IP和类型信息的字符串列表。
    """
    if not os.path.exists(yaml_file_path):
        print(f"错误: 文件 '{yaml_file_path}' 不存在。")
        return []

    try:
        with open(yaml_file_path, 'r', encoding='utf-8') as file:
            data = yaml.safe_load(file)
    except yaml.YAMLError as e:
        print(f"错误: 解析YAML文件时发生错误: {e}")
        return []
    except Exception as e:
        print(f"错误: 读取文件时发生未知错误: {e}")
        return []

    if not isinstance(data, list):
        print("警告: YAML文件根结构不是列表，可能无法按预期处理。")
        return []

    # 用于记录已遇到的IP及其最新类型
    # 键为IP地址，值为对应的类型
    ip_type_map = {}
    # 用于存储已报告的重复项，避免重复打印相同的(IP, Type)组合
    reported_duplicates = set()

    duplicate_results = []

    for entry in data:
        # 确保条目是字典且包含'ip'和'type'键
        if isinstance(entry, dict) and 'ip' in entry and 'type' in entry:
            ip = entry['ip']
            entry_type = entry['type']

            # 检查IP是否已在map中，并且其类型是否与当前条目类型一致
            if ip in ip_type_map and entry_type == ip_type_map[ip]:
                duplicate_key = (ip, entry_type)
                if duplicate_key not in reported_duplicates:
                    result_message = f"IP {ip}, {entry_type} duplicate"
                    duplicate_results.append(result_message)
                    reported_duplicates.add(duplicate_key) # 标记为已报告
            else:
                # 如果是新IP，或者IP已存在但类型不同，则更新map
                ip_type_map[ip] = entry_type
        else:
            print(f"警告: YAML数据中发现无效条目或缺少'ip'/'type'键: {entry}")

    return duplicate_results

# 示例YAML数据，保存为 'myyaml.yaml'
# -
#     ip: 1.1.1.1
#     status: Active
#     type: 'typeA'
# -
#     ip: 1.1.1.1
#     status: Disabled
#     type: 'typeA'
# -
#     ip: 2.2.2.2
#     status: Active
#     type: 'typeC'
# -
#     ip: 3.3.3.3
#     status: Active
#     type: 'typeB'
# -
#     ip: 3.3.3.3
#     status: Active
#     type: 'typeC'
# -
#     ip: 2.2.2.2
#     status: Active
#     type: 'typeC'
# -

if __name__ == "__main__":
    yaml_file = 'myyaml.yaml' # 替换为您的YAML文件路径

    # 创建一个示例YAML文件用于测试
    example_yaml_content = """
-
    ip: 1.1.1.1
    status: Active
    type: 'typeA'
-
    ip: 1.1.1.1
    status: Disabled
    type: 'typeA'
-
    ip: 2.2.2.2
    status: Active
    type: 'typeC'
-
    ip: 3.3.3.3
    status: Active
    type: 'typeB'
-
    ip: 3.3.3.3
    status: Active
    type: 'typeC'
-
    ip: 2.2.2.2
    status: Active
    type: 'typeC'
-
"""
    with open(yaml_file, 'w', encoding='utf-8') as f:
        f.write(example_yaml_content)
    print(f"已创建示例文件: {yaml_file}")

    duplicates = find_duplicated_ips_with_same_type(yaml_file)
    if duplicates:
        print("\n发现以下重复项:")
        for dup in duplicates:
            print(dup)
    else:
        print("\n未发现符合条件的重复项。")

    # 清理示例文件
    # os.remove(yaml_file)
    # print(f"已删除示例文件: {yaml_file}")