02-数据操作【读、写、拼接、清洗、函数封装】

def read24list(file):
    """ 读取24条已有的数据列表 """
    data = []
    list24 = []
    getIndex24 = []

    # 方法2： with优化文件操作
    with  open (file, "r", encoding="UTF-8") as fileName:
        line = fileName.readline ()
        line = line[:-1]  # 第一行数据内容,（容易误删）
        list24.append (line.split ())
        while line:
            # 按行读取数据
            line = fileName.readline ()
            line = line[:-1]
            list24.append (line.split ())  # 默认按照空格和Tab作为分割
    # 删除尾元素
    list24.remove (list24[-1])

    # 取2维列表的元素，并对每个子列表进行遍历
    # for index2 in list24:
    #     getIndex24.append (index2[1])
    # print (getIndex24)
    # outlist = list (set (getIndex24))
    # print (outlist)  # 列表——》集合，元素去重复——》列表

    return list24

# 2000条数据列表
def read2000list(file):
    """ 读取1200数据，进行筛选和比较 """

    data = []
    list2000 = []
    getIndex2000 = []
    getIndex24 = []

    # 方法2： with 优化文件操作
    with  open (file, "r", encoding="UTF-8") as fileName:
        line = fileName.readline ()
        line = line[ :-1 ]  # 第一行数据内容,（容易误删）
        list2000.append ( line.split () )
        while line:
            # 按行读取数据
            line = fileName.readline ()
            line = line[:-1]
            list2000.append (line.split ())  # 默认按照空格和Tab作为分割
    # 删除尾元素
    list2000.remove (list2000[-1])

    # 取2维列表的元素，并对每个子列表进行遍历
    list24 = read24list("24ricedetail.txt")

    for element24 in list24:
        getIndex24.append (element24[1])

    for element2000 in list2000:
        getIndex2000.append (element2000[1])
        # 取2维列表的元素，并对每个子列表进行遍历
        if element2000[1]  in getIndex24:
            # 米种已存在
            print("yes,it is in the list",element2000[1])
        else:
            # 米种不存在
            print("this element is out of the list",element2000[1])
            str = txtLength("24ricedetail.txt") + '\t' + '\t'.join(element2000) + "\n"
            writeDataIntoTxt(str, "24ricedetail.txt")

    return list2000

# 在文件的末尾追加数据
def writeDataIntoTxt(object,filename):
    with open(filename,"a+",encoding="UTF-8") as fwIn:
        fwIn.writelines(object)

# 统计txt文件的总行数
def txtLength(filename):
    with open(filename, 'r',encoding="UTF-8")  as f:
        return str(len(f.readlines()))


if __name__ == "__main__":
    print ("----start------")

    file2000 = "2000ricedetail.txt"
    read2000list (file2000)

    print ("----End------")