字符串操作、文件操作，英文词频统计预处理

作业来源：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/2684

1.字符串操作：

解析身份证号：生日、性别、出生地等

import requests
import chardet
from bs4 import BeautifulSoup
from fake_useragent import UserAgent

def get_ID_Info(Id):
    url = "http://blog.sina.com.cn/s/blog_55a319c701015pjt.html"
    ua = UserAgent()
    headers = {'User_Agent':ua.random}
    html = requests.get(url,headers=headers)
    charset = chardet.detect(html.content)
    html.encoding = charset['encoding']
    soup = BeautifulSoup(html.text,'lxml')
    areaInfo = soup.select('#sina_keyword_ad_area2')[0].get_text(' ','<br/>').replace("u3000",' ')
    areaInfo = ' '.join(areaInfo.split()).split(' ')
    for areaVerify in areaInfo:
        if Id[0:6] == areaVerify:
            i = areaInfo.index(areaVerify)+1
            print(u"地区:{}".format(areaInfo[i]))
    print(u"出生:%s" % (Id[6:10] + '年' + Id[10:12] + '月' + Id[12:14]))
    if (int(Id[-2])%2) == 0:
        sex = "女"
    else:
        sex = "男"
    print(u"性别:%s" % sex)

def check_ID_Number(Id):
    str_to_int = {'0': 0, '1': 1, '2': 2, '3': 3, '4': 4, '5': 5,
                  '6': 6, '7': 7, '8': 8, '9': 9, 'X': 10}
    check_dict = {0: '1', 1: '0', 2: 'X', 3: '9', 4: '8', 5: '7',
                  6: '6', 7: '5', 8: '4', 9: '3', 10: '2'}
    if len(Id) != 18:
        raise TypeError(u'请输入标准的第二代身份证号码')
    check_num = 0
    for index, num in enumerate(Id):
        if index == 17:
            right_code = check_dict.get(check_num % 11)
            if num == right_code:
                print(u"身份证号: %s 校验通过" % Id)
                return True
            else:
                print(u"身份证号: %s 校验不通过, 正确尾号应该为：%s" % (Id, right_code))
                return False
        check_num += str_to_int.get(num) * (2 ** (17 - index) % 11)
if __name__ == '__main__':
    Id = input(u'请输入标准的第二代身份证号码:')
    Id = str(Id)
    if check_ID_Number(Id):
        get_ID_Info(Id)

凯撒密码编码与解码

MAX_KEY_SIZE = 26
def getMode():
    while True:
        print('请选择加密或解密模式,或者选择暴力破解：')
        print('加密:encrypt(e)')
        print('解密:decrypt(d)')
        print('暴力破解:brute(b)')
        mode = input().lower()
        if mode in 'encrypt e decrypt d brute b'.split():
            return mode
        else:
            print('请输入"encrypt"或"e"或"decrypt"或"d"或"brute"或"b"!')

def getMessage():
    print('请输入你的信息：')
    return input()

def getKey():
    key = 0
    while True:
        print('请输入密钥数字(1-%s)' % (MAX_KEY_SIZE))
        key = int(input())
        if (key >=1 and key <= MAX_KEY_SIZE):
            return key

def getTranslatedMessage(mode, message, key):
    if mode[0] == 'd':
        key = -key
    translated = ''
    for symbol in message:
        if symbol.isalpha():
            num = ord(symbol)
            num += key
            if symbol.isupper():
                if num > ord('Z'):
                    num -= 26
                elif num < ord('A'):
                    num += 26
            elif symbol.islower():
                if num > ord('z'):
                    num -= 26
                elif num < ord('a'):
                    num += 26
            translated += chr(num)
        else:
            translated += symbol
    return translated

if __name__ == '__main__':
    mode = getMode()
    message = getMessage()
    if mode[0] != 'b':
        key = getKey()
    print('你要翻译的信息是:')
    if mode[0] != 'b':
        print(getTranslatedMessage(mode, message, key))
    else:
        for key in range(1, MAX_KEY_SIZE + 1):
            print(key, getTranslatedMessage('decrypt', message, key))

网址观察与批量生成

for i in range(2,15):
    print('http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i))

2.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

import requests
import chardet
from bs4 import BeautifulSoup
from fake_useragent import UserAgent

def Info():
    url = "http://www.duwenzhang.com/wenzhang/yingyuwenzhang/20130519/255870.html"
    ua = UserAgent()
    headers = {'User_Agent':ua.random}
    html = requests.get(url,headers=headers)
    charset = chardet.detect(html.content)
    html.encoding = charset['encoding']
    soup = BeautifulSoup(html.text,'lxml')
    engInfo = soup.find('div',{'class':'article 255870'}).find_all('p')[0].get_text(' ','<br/>').replace("u3000",' ')#获取文本
    print(engInfo)
    engInfo = engInfo.lower()#将所有大写转换为小写
    print(engInfo)
    s = ',.？！'
    for i in s:
        engInfo = engInfo.replace(i,' ')#将所有其他做分隔符（,.？！）替换为空格
    print(engInfo)
    engInfo = engInfo.split()#分隔出一个一个的单词
    print(engInfo)
    InfoSet = set(engInfo)
    Count = {}
    for word in InfoSet:
        Count.setdefault(word,engInfo.count(word))#统计单词出现的次数
    print(Count)
if __name__ == '__main__':
    Info()

3.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。

def getMima():
    Massage = str(input("输入明文并保存文本:"))
    with open('massage.txt','w') as f:
        f.write(Massage)
        f.close()
    Mima = ''
    for i in Massage:
        Mima = Mima + chr(ord(i)+3)
    print('加密结果:'+Mima+'
')
    with open('secret.txt','w') as f:
        f.write(Mima)
        f.close()

def getMassageFromTXT():
    print("对文本内容解码..")
    with open('secret.txt','r') as f:
        s = f.read()
    Massage = ''
    if s == None:
        print('没有可解码的文本
')
    else:
        for i in s:
            Massage = Massage + chr(ord(i)-3)
        print('解码结果:'+Massage+'
')

if __name__ == '__main__':
    while 1:
        a = int(input('加密(1)解码(2)退出(0):'))
        if a == 0:
            break
        elif a == 1:
            getMima()
        elif a == 2:
            getMassageFromTXT()

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。

engInfo = '''My father was a self-taught mandolin player.
 He was one of the best string instrument players in our town.
  He could not read music, but if he heard a tune a few times, 
  he could play it. When he was younger, he was a member of a small country music band. 
  They would play at local dances and on a few occasions would play for the local radio station. 
  He often told us how he had auditioned and earned a position in a band that featured Patsy Cline as their lead singer.
   He told the family that after he was hired he never went back. Dad was a very religious man. 
   He stated that there was a lot of drinking and cursing the day of his audition and he did not want to be around that type of environment.
'''
f = open('EngTxt.txt','a',encoding='utf-8')
f.write(engInfo)
f.close()

4.函数定义

加密函数、解密函数

def getTranslatedMessage(mode, message, key):
    if mode[0] == 'd':
        key = -key
    translated = ''
    for symbol in message:
        if symbol.isalpha():
            num = ord(symbol)
            num += key
            if symbol.isupper():
                if num > ord('Z'):
                    num -= 26
                elif num < ord('A'):
                    num += 26
            elif symbol.islower():
                if num > ord('z'):
                    num -= 26
                elif num < ord('a'):
                    num += 26
            translated += chr(num)
        else:
            translated += symbol
    return translated

读文本函数

def getMima():
    Massage = str(input("输入明文并保存文本:"))
    with open('massage.txt','w') as f:
        f.write(Massage)
        f.close()
    Mima = ''
    for i in Massage:
        Mima = Mima + chr(ord(i)+3)
    print('加密结果:'+Mima+'
')
    with open('secret.txt','w') as f:
        f.write(Mima)
        f.close()