import pandas as pd


def merge():
    # 读取三份csv文件
    df1 = pd.read_csv("../_dataset/TrafficLabelling_/Friday-WorkingHours-Morning.pcap_ISCX.csv")
    df2 = pd.read_csv("../_dataset/TrafficLabelling_/Friday-WorkingHours-Afternoon-PortScan.pcap_ISCX.csv")
    df3 = pd.read_csv("../_dataset/TrafficLabelling_/Friday-WorkingHours-Afternoon-DDos.pcap_ISCX.csv")
    # 将它们拼合成一个DataFrame
    df = pd.concat([df1, df2, df3])
    # 保存为新的csv文件
    df.to_csv("../_dataset/TrafficLabelling_/Friday-WorkingHours-merged.csv", index=False)


def select():
    df = pd.read_csv('../_dataset/TrafficLabelling_/Friday-WorkingHours-merged.csv')
    df_ddos = df[df.iloc[:, -1] == 'DDoS']
    df_ddos.to_csv('../_dataset/TrafficLabelling_/Friday-WorkingHours-DDoS.csv', index=False)


def search(query: str, row_name: str):
    df = pd.read_csv('../_dataset/TrafficLabelling_/Friday-WorkingHours-merged.csv')
    result = df[df[row_name].str.contains(query)]
    print(result.head())


if __name__ == "__main__":
    # merge()
    # select()
    search("172.16.0.1-192.168.10.50-49533-80-6", "Flow ID")