文件读写操作¶

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    print(poem.read())  # 读文件为字符串输出
    for line in poem:       # 指针在文件末尾，后面无数据，读到空字符串
        print(line.strip())  # 无输出

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    print(poem.read())  # 读文件为字符串输出
    poem.seek(0) # 将文件指针移动到文件开始位置
    for line in poem:       # 指针在文件开头
        print(line.strip())  # 重新输出一次文件内容

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    print([poem.read(20)])  # 读取前20个字符,放入列表中输出是为了能看到换行符
    
    print(poem.read())      # 输出剩余字符

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    print([poem.read(11)])    # ['出塞\n秦时明月汉时关，']，字符串末尾保留换行符
    print(poem.readline(10))  # 万里长征人未还。

file =  'images/ch8/9.1 出塞.txt'
with open(file, 'r', encoding='utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    for i in range(1, 12):  
        print(i, [poem.readline(i)], poem.tell())  # 从当前行可读数据中读取前i个字符，指针后移

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    while txt := poem.readline():  # 逐行读文件，直至文件结束
        print(txt.strip())          # 去除行末的换行符后输出当前读到的字符串

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    print(poem.readlines())      # 输出全部内容放入列表
    

with open( 'images/ch8/9.1 出塞.txt','r',encoding = 'utf-8') as poem:  # 打开文件创建文件对象，命名为poem
    print(poem.readlines(4))      # 输出到第4个字符"秦"所在的行的数据， ['出塞\n', '秦时明月汉时关，万里长征人未还。\n']

def read_file(file):
    """接收文件名为参数，将文件中的内容读为字符串，
    过滤掉中文(中文字符及全角符号Unicode编码都大于256),返回字符串 """
    with open(file, 'r', encoding='utf-8') as novel:
        txt = novel.read()  # 读取文件全部内容为字符串
    english_txt = ''
    for x in txt:
        if ord(x) < 256:
            english_txt = english_txt + x   # 过滤掉中文，拼接为字符串
    return english_txt  # 返回英文文本


if __name__ == '__main__':
    filename = 'images/ch8/Who Moved My Cheese.txt'
    print(read_file(filename))

def read_file(file):
    """接收文件名为参数，将文件中的内容读为字符串，
    过滤掉中文(中文字符及全角符号Unicode编码都大于256),返回字符串 """
    with open(file, 'r', encoding='utf-8') as novel:
        txt = novel.read()  # 读取文件全部内容为字符串
    english_txt = ''.join([x for x in txt if ord(x) < 256])  # 过滤掉中文，拼接为字符串
    return english_txt  # 返回英文文本


if __name__ == '__main__':
    filename =  'images/ch8/Who Moved My Cheese.txt'
    print(read_file(filename))

def read_file(file):
    """接收文件名为参数，将文件中的内容读为字符串，
    过滤掉中文(中文字符及全角符号Unicode编码都大于256),返回字符串 """
    with open(file, 'r', encoding='utf-8') as novel:
        txt = novel.read()  # 读取文件全部内容为字符串
    english_txt = ''.join([x for x in txt if ord(x) < 256])  # 过滤掉中文，拼接为字符串
    return english_txt  # 返回英文文本


def words_lst(text):
    """接收字符串为参数，用空格替换字符串中所有标点符号，根据空格将字符串切分为列表
    返回值为元素为单词的列表。
    """
    # 补充你的代码
    
    


if __name__ == '__main__':
    filename = 'images/ch8/Who Moved My Cheese.txt'
    txt = read_file(filename)
    print(len(words_lst(txt)))  # 输出列表的长度

def read_file(file):
    """接收文件名为参数，将文件中的内容读为字符串，
    过滤掉中文(中文字符及全角符号Unicode编码都大于256),返回字符串 """
    with open(file, 'r', encoding='utf-8') as novel:
        txt = novel.read()  # 读取文件全部内容为字符串
    english_txt = ''.join([x for x in txt if ord(x) < 256])  # 过滤掉中文，拼接为字符串
    return english_txt  # 返回英文文本


def words_lst(text):
    """接收字符串为参数，用空格替换字符串中所有标点符号，根据空格将字符串切分为列表
    返回值为元素为单词的列表。
    """
    # 补充你的代码

    
    

def word_frequency(words_ls):
    """接收元素为单词的列表，统计每个单词出现的次数，根据出现次数排序，输出出现频率最高的50个单词及其出现次数"""
    # 补充你的代码
    
    
    
    


if __name__ == '__main__':
    filename = 'images/ch8/Who Moved My Cheese.txt'
    txt = read_file(filename)
    words_list = words_lst(txt)  # 单词列表
    word_frequency(words_list)

def read_txt():  # 根据性别生成一个姓名
    """无参数，读百家姓文件，将单字姓和复姓拆分，返回以姓为元素的列表"""
    with open('images/ch8/百家姓.txt', 'r', encoding='utf-8') as data:
        # 替换掉换行符、逗号和句号，每行转为一个字符串，得到列表
        last_ls = [line.strip().replace('，', '').replace('。', '') for line in data]
        # print(last_ls)  # ['赵钱孙李周吴郑王', '冯陈褚卫蒋沈韩杨', ...]

    single = list(''.join(last_ls[:51]))    # 前51行为单字姓，拼接为一个字符串转列表
    # print(single)  # ['赵', '钱', '孙', '李', '周', '吴', '郑', '王',...]
    
    double_txt = ''.join(last_ls[51:])       # 51行后为复姓，拼接为一个字符串
    double = []                              # 创建空列表
    for i in range(0, len(double_txt), 2):   # 遍历字符串序号，步长为2
        double.append(double_txt[i: i + 2])  # 当前序号向后切2个字符，加入到列表
    # double = [double_txt[i: i + 2] for i in range(0, len(double_txt), 2)]  # 列表推导式方法
    # print(double)  # ['万俟', '司马', '上官', '欧阳', '夏侯', '诸葛', '闻人', '东方', ...]
    lastname = single + double               # 单字姓列表与复姓列表拼接为一个列表
    return lastname                          # 返回百家姓中所有姓的列表


if __name__ == '__main__':
    family_names = read_txt()                # 调用函数将文件读为列表
    print(family_names)                      # 输出

def write_str(s, filename):
    """接收要写入的字符串和文件名为参数，将字符串追加写入到文件现在数据末尾"""
    with open(filename, 'w', encoding='utf-8') as f:
        f.write(s)        # 将字符串s写入文件


def write_list(ls, filename):
    """接收要写入的列表和文件名为参数，将列表中的字符串追加写入到文件现在数据末尾"""
    with open(filename, 'a', encoding='utf-8') as f:
        f.writelines(ls)  # 将列表ls写入文件，附加到后面


def read_file(filename):
    """接收表示文件名的字符串为参数，读文件，以字符串形式返回"""
    with open(filename, 'r', encoding='utf-8') as f:
        return f.read()   # 返回字符串形式的文件内容


if __name__ == '__main__':
    file = 'score.txt'     # 定义文件名变量，方便程序扩展和修改
    score_str = '姓名,C语言,Java,Python,C#\n罗明,95,96,85,63\n朱佳,75,93,66,85\n'
    score_lst = ['李思,86,76,96,93\n郑君,88,98,76,90\n']
    write_str(score_str, file)   # 传递要写入的字符串和文件名为参数
    write_list(score_lst, file)  # 传递要写入的列表和文件名为参数
    print(read_file(file))       # 读文件，查看写入是否成功