字符串、文件操作，英文词频统计预处理

作业要求来源：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2646

1、解析身份证号码

源代码

citizenID = input("请输入身份证号码：")

province = citizenID[0:2]
city = citizenID[2:4]
county = citizenID[4:6]
year = citizenID[6:10]
month = citizenID[10:12]
day = citizenID[12:14]
area = citizenID[14:16]
sexCode = citizenID[16]
checkNumber = citizenID[17]

sex = "男"
if ((int(sexCode)) % 2 == 0):
    sex = "女"

print("省:{}，市:{},区:{}，年:{}，月:{}，日:{}，派出所:{}，性别:{}, 校验码:{}".format(province, city, county, year, month, day, area, sex,checkNumber))
print("(注：地区编码请参考全国地区编码表)")

结果

2、凯撒密码编码与解码

源代码

choose = input("请选择模式:  1.加密  2.解密   :")
ch = int(choose)


def encode(txt, ofs):  # 加密
    t = ""
    for ch in txt:
        if 'a' <= ch <= 'z':
            t += chr(ord('a') + ((ord(ch) - ord('a')) + ofs) % 26)
        elif 'A' <= ch <= 'Z':
            t += chr(ord('A') + ((ord(ch) - ord('A')) + ofs) % 26)
        else:
            t += ch
    return t


def decode(txt, ofs):  # 解密
    t = ""
    for ch in txt:
        if 'a' <= ch <= 'z':
            t += chr(ord('a') + ((ord(ch) - ord('a')) - ofs) % 26)
        elif 'A' <= ch <= 'Z':
            t += chr(ord('A') + ((ord(ch) - ord('A')) - ofs) % 26)
        else:
            t += ch
    return t


inputTxt = input("请输入文本：")
offset = input("请输入偏移量:")
ofs = int(offset)

if ch == 1:
    result = encode(txt=inputTxt, ofs=ofs)
    print("加密为：" + result)
else:
    result = decode(txt=inputTxt, ofs=ofs)
    print("解密为：" + result)

结果

3、网址观察与批量生成

源代码

import webbrowser as web

url = "http://news.gzcc.cn/html/xiaoyuanxinwen/2.html"
web.open_new_tab(url)
for i in range(3, 10):
    url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' + str(i) + '.html'
    web.open_new_tab(url)
    print(url)

结果

4、英文词频统计预处理

源代码

fo = open(r'G:	estsong.txt', encoding='utf-8')
text = fo.read()
fo.close()
text = text.lower()  # 转换成小写
sep = ",.?!:''
'"

for s in sep:  # 去除各种符号,用空格代替
    text = text.replace(s, ' ')
allWord = text.split(' ')  # 分隔出单词
result = []  # 存储不重复的单词
print("单词    个数")

for b in allWord:
    isRepeat = False
    for c in result:
        if b == c:
            isRepeat=True
    if isRepeat == False:  # 若未出现在result字典里，则加入
        result.append(b)

for ch in result:
    if ch != '':
        print("{:<10} {:<5}".format(ch, allWord.count(ch)))  # 格式化输出

结果