字符串操作、文件操作，英文词频统计预处理

一、字符串操作

• 解析身份证号：生日、性别、出生地等。

provinces = {'11': '北京市', '12': '天津市', '13': '河北省', '14': '山西省', '15': '内蒙古自治区', '21': '辽宁省',\
           '22': '吉林省', '23': '黑龙江省', '31': '上海市', '32': '江苏省', '33': '浙江省', '34': '安徽省', \
           '35': '福建省', '36': '江西省', '37': '山东省', '41': '河南省', '42': '湖北省', '43': '湖南省', \
           '44': '广东省', '45': '广西壮族自治区', '46': '海南省', '50': '重庆市', '51': '四川省', '52': '贵州省', \
           '53': '云南省', '54': '西藏自治区', '61': '陕西省', '62': '甘肃省', '63': '青海省', '64': '宁夏回族自治区', \
           '65': '新疆维吾尔自治区', '71': '台湾省','81': '香港特别行政区', '82': '澳门特别行政区'}
city = {"01": "广州市", "02": "韶关市", "03": "深圳市", "04": "珠海市", "05": "汕头市", "06": "佛山市", "07": "江门市", \
        "08": "湛江市", "09": "茂名市", "12": "肇庆市", "13": "惠州市", "14": "梅州市", "15": "汕尾市", "16": "河源市", \
        "17": "阳江市", "18": "清远市", "19": "东莞市", "20": "中山市", "51": "潮州市", "52": "揭阳市", "53": "云浮市"}
id = input('请输入十八位身份证号码: ')
id_check = id[17]
id_add = id[0:6]
id_birth = id[6:14]
id_sex = id[14:17]
birth_year = id_birth[0:4]
birth_moon = id_birth[4:6]
birth_day = id_birth[6:8]
W = [7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2]
ID_num = [18, 17, 16, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2]
id_check_num = ['1', '0', 'X', '9', '8', '7', '6', '5', '4', '3', '2']
ID_aXw = 0
for i in range(len(W)):
    ID_aXw = ID_aXw + int(id[i]) * W[i]

id_check_index = ID_aXw % 11
if id_check == id_check_num[id_check_index]:
    if len(id) == 18:
        if int(id_sex) % 2 == 0:
            print('性别：女')
        else:
            print('性别：男')
        print("出生地为：" + provinces.get(id[0:2]) + city.get(
            id[2:4]) + "\n" + "出生日期为: " + birth_year + '年' + birth_moon + '月' + birth_day + '日')
        print("你的身份证号码是：" + id)
        print("\n身份证号检验：这是一个正确的身份证号码")
    else:
        print("\n身份证号检验：" + id + "是一个错误的身份证号码")
else:
    print("\n身份证号检验：" + id + "是一个错误的身份证号码")

　　执行效果如下：

• 凯撒密码编码与解码

code = input("请输入要编码的信息：")
print("编码后为：")
for i in code:
    print(chr(ord(i)+3),end="")
decode = input("\n请输入要解码的信息：")
print("解码后为：")
for i in decode:
    print(chr(ord(i)-3),end="")

　　执行效果如下：

 

• 网址观察与批量生成

import webbrowser as web        # 命名为web
for i in range(2, 22):
    URL = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    print(URL)
URL = 'http://news.gzcc.cn/html/xiaoyuanxinwen/2.html'
web.open(URL)

　　　执行效果如下：

 

二、英文词频统计预处理

• 下载一首英文的歌词或文章或小说。
• 将所有大写转换为小写
• 将所有其他做分隔符（,.？！）替换为空格
• 分隔出一个一个的单词
• 并统计单词出现的次数。

 

def read_text():
    fo=open("C:The_Spectre.txt", "r", encoding="UTF-8-sig")
    line = fo.read()
    print(line)
    print("\n")
    fo.close()
    return line


def modify_text():
    changes = {',', '.', 'don\'t', '\n', 'I\'ve'}
    text = read_text()
    for change in changes:
        if change == 'don\'t':
            text = text.replace(change, 'do not')
        elif change == 'I\'ve':
            text = text.replace(change, 'I have')
        else:
            text = text.replace(change, ' ')
    return text


def lowercase_and_count():
    string = modify_text().lower()
    result = []
    print(string.split(' '))
    print("\n")
    for word in string.split(' '):
        if word not in result:
            result.append(word)
    for word in result:
        if word != "":
            print(word + " 这个词在歌曲中出现了" + str(string.count(word)) + "次")
        else:
            pass
    return


lowercase_and_count()

　　执行效果如下：

 

三、文件操作

• 同一目录、绝对路径、相对路径
• 凯撒密码：从文件读入密函，进行加密或解密，保存到文件。
• 词频统计：下载一首英文的歌词或文章或小说，保存为utf8文件。从文件读入文本进行处理。

 

#同一目录
fo=open('text.txt','r',encoding='UTF-8-sig')
content=fo.read()
fo.close()
print(content,end='')
#绝对路径
fo=open(r'C:\Users\Administrator\PycharmProjects\MadLibs\text.txt','r',encoding="UTF-8-sig")
content=fo.read()
fo.close()
print(content,end='')
#相对路径
fo=open(r'./text.txt','r',encoding="UTF-8-sig")
content=fo.read()
fo.close()
print(content,end='')

 

def encode():
    fo = open(r'C:\Users\Administrator\PycharmProjects\MadLibs\The_Spectre.txt', 'r', encoding="UTF-8-sig")
    s = fo.read()
    str = ''
    for i in s:
        str = str +chr(ord(i)+3)
        print(chr(ord(i) + 3), end='')
    fo.close()
    fo = open(r'C:\Users\Administrator\PycharmProjects\MadLibs\The_Spectre.txt', 'w', encoding="UTF-8-sig")
    fo.write(str)
    fo.close()
    return


def decode():
    fo = open(r'C:\Users\Administrator\PycharmProjects\MadLibs\The_Spectre.txt', 'r', encoding="UTF-8-sig")
    s = fo.read()
    str = ''
    for i in s:
        str = str + chr(ord(i) - 3)
        print(chr(ord(i) - 3), end='')
    fo.close()
    fo = open(r'C:\Users\Administrator\PycharmProjects\MadLibs\The_Spectre.txt', 'w', encoding="UTF-8-sig")
    fo.write(str)
    fo.close()
    return


def main():
    while True:
        print(u"1. 加密,2. 解密")
        choice = input("请选择：")
        if choice == "1":
            encode()
            print("")
        elif choice == "2":
            decode()
        else:
            print(u"您的输入有误！")
    return


if __name__ == '__main__':
    main()

　　执行效果如下：

 

四、函数定义

• 加密函数

def bian_ma():
    code = input("请输入要编码的信息：")
    print("编码后为：")
    for i in code:
        print(chr(ord(i)+3),end="")
    return

 

• 解密函数

def jie_ma():
    decode = input("\n请输入要解码的信息：")
    print("解码后为：")
    for i in decode:
        print(chr(ord(i) - 3), end="")
    return

 

• 读文本函数

def read_text():
    fo=open("C:The_Spectre.txt", "r", encoding="UTF-8-sig")
    line = fo.read()
    print(line)
    print("\n")
    fo.close()
    return line