拆分txt文件

---

前言

拆分txt文件

1. 根据行数拆分txt文件
2. 根据文件大小拆分txt文件
3. 提取txt文件的奇数行，偶数行

---

一、根据行数拆分

def spilt_1(file_path, output_file, limit):
    """
    根据行数拆分文件
    :param file: 待拆分的文件
    :param output_file: 拆分之后的文件名（前部）
    :param limit: 每个文件中的行数
    :return:
    """
    out_i = 1  # 拆分之后的文件名下标
    txt_line = []
    with open(file_path, 'r', encoding='UTF-8') as fp:
        for line in fp:
            txt_line.append(line)
            if len(txt_line) <= limit:
                continue
            with open(output_file + str(out_i) + '.txt', 'w', encoding='UTF-8') as fo:
                for i in txt_line[:-1]:
                    fo.write(i)
                txt_line = []
                out_i += 1
    if txt_line:
        with open(output_file + str(out_i) + '.txt', 'w', encoding='UTF-8') as fo:
            for i in txt_line[:-1]:
                fo.write(i)
    print("done!")

二、根据文件大小拆分

def spilt_2(file_path, output_file, limit):
    """
    根据文件大小拆分文件
    :param file: 待拆分的文件
    :param output_file: 拆分之后的文件名（前部）
    :param limit: 每个文件的大小*1000  
    （limit=100000, 即100KB：每次读取100KB大小内容,拆分后每个文件大小100MB）
    :return:
    """
    out_i = 1  # 拆分之后的文件名下标
    with open(file_path, 'r', encoding='UTF-8') as fp:
        read_data = fp.read(limit)  # 100KB  每次读取100KB大小内容
        while(read_data != ''):
            with open(output_file + str(out_i) + '.txt', 'w', encoding='UTF-8') as fo:
                for j in range(0, 1024):  # 100KB * 1024 =100mb      拆分后每个文件大小100MB
                    fo.write(read_data)
                    read_data = fp.read(limit)  # 100KB
                    if(read_data == ""):
                        break
            out_i = out_i + 1
    print("done!")

三、提取奇偶行

def spilt_3(path, odd_path, even_path):
    """
    提取奇数行，偶数行并分别保存为txt文件
    :param path: 待拆分的文件
    :param odd_path: 奇数行文件
    :param even_path: 偶数行文件
    :return:
    """
    with open(path, "r", encoding="utf-8") as f:
        lines = f.readlines()
        file_1 = open(odd_path, 'w', encoding='utf-8')
        file_2 = open(even_path, 'w', encoding='utf-8')

        for num, line in enumerate(lines):
            # print(num, line)
            if (num % 2) == 0:  # num为偶数说明是奇数行
                print(line.strip(), file=file_1)  # .strip用来删除空行
            else:  # # num为奇数说明是偶数行
                print(line.strip(), file=file_2)

        file_1.close()
        file_2.close()