字元串、檔案操作，英文詞頻統計預處理

作業要求來源：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2646

1、解析身份證号碼

源代碼

citizenID = input("請輸入身份證号碼：")

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:{},區:{}，年:{}，月:{}，日:{}，派出所:{}，性别:{}, 校驗碼:{}".format(province, city, county, year, month, day, area, sex,checkNumber))
print("(注：地區編碼請參考全國地區編碼表)")

           

結果

2、凱撒密碼編碼與解碼

choose = input("請選擇模式:  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("請輸入文本：")
offset = input("請輸入偏移量:")
ofs = int(offset)

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

           

3、網址觀察與批量生成

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)
           

4、英文詞頻統計預處理

fo = open(r'G:\test\song.txt', encoding='utf-8')
text = fo.read()
fo.close()
text = text.lower()  # 轉換成小寫
sep = ",.?!:''\n'"

for s in sep:  # 去除各種符号,用空格代替
    text = text.replace(s, ' ')
allWord = text.split(' ')  # 分隔出單詞
result = []  # 存儲不重複的單詞
print("單詞    個數")

for b in allWord:
    isRepeat = False
    for c in result:
        if b == c:
            isRepeat=True
    if isRepeat == False:  # 若未出現在result字典裡，則加入
        result.append(b)

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