【大数据作业二】字符串操作，英文词频统计预处理

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

1.字符串操作：

• 解析身份证号：生日、性别、出生地等。
• 凯撒密码编码与解码
• 网址观察与批量生成

解析身份证号：

ID = input('请输入十八位身份证号码(只限广州市内): ')
if len(ID) == 18:
    print("你的身份证号码是 " + ID)
else:
    print("错误的身份证号码")

ID_add = ID[0:4]
ID_area=ID[4:6]
ID_birth = ID[6:14]
ID_sex = ID[14:17]
ID_check = ID[17]

# ID_add是身份证中的区域代码，如果有一个行政区划代码字典，就可以用获取大致地址#

year = ID_birth[0:4]
moon = ID_birth[4:6]
day = ID_birth[6:8]
print("生日: " + year + '年' + moon + '月' + day + '日')

if ID_area == 16:
    print('地区：萝岗区')
if ID_area == '06':
    print('地区：天河区')
if ID_area == '03':
    print('地区：荔湾区')
if ID_area == '04':
    print('地区：越秀区')
if ID_area == '05':
    print('地区：海珠区')
if ID_area == '07':
    print('地区：芳村区')
if ID_area == 11:
    print('地区：白云区')
if ID_area == 12:
    print('地区：黄埔区')
if ID_area == 13:
    print('地区：番禺区')
if ID_area == 14:
    print('地区：花都区')
if ID_area == 15:
    print('地区：南沙区')
if ID_area == '02':
    print("地区：东山区")


if int(ID_sex) % 2 == 0:
    print('性别：女')
else:
    print('性别：男')

# 此部分应为错误判断，如果错误就不应有上面的输出，如何实现？#
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 = ['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 = ID_aXw % 11
if ID_check == ID_CHECK[ID_Check]:
    print('正确的身份证号码:{}'.format(ID))
else:
    print('错误的身份证号码')

显示结果：

凯撒密码编码与解码：

plaincode=input('')
for i in plaincode:
    print(chr(ord(i)+3),end='')
plaincode=input('')
s=ord('a')
t=ord('z')
for i in plaincode:
    if s<= ord(i)<=t:
        print(chr(s+(ord(i)-s+3)%26), end='')
    else:
        print(i,end='')

显示结果：

网址观察：

#引入第三方库，并用as取别名
import  webbrowser as web
url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
web.open_new_tab(url)
for i in range(2,4):
    web.open_new_tab('http://news.gzcc.cn/html/xiaoyuanxinwen/'+str(i)+'.html')

显示结果：

网址批量生成：

for i in range(2,10):
    url='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    print(url)

显示结果：

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。

英文词频统计：

text='''When the bundle was
nestled in her
arms and she moved 
the fold of cloth to look 
upon his tiny face, she gasped. 
The doctor turned quickly 
and looked out the tall 
hospital window. The baby 
had been born without ears.'''
print(text.split())
print(text.count('the'),text.count('The'))

显示结果：

大小写转换及统计：

text='''When the bundle was
nestled in her
arms and she moved 
the fold of cloth to look 
upon his tiny face, she gasped. 
The doctor turned quickly 
and looked out the tall 
hospital window. The baby 
had been born without ears.'''
text=text.lower()
sep='.,'
for s in sep:
    text=text.replace(s,' ')
print(text.split())
print(text.count('the'),text.count('The'))

显示结果：

将文章改成txt模式打开：

f = open(r'F:python	hee.txt','r')
text=f.read()
print(text)
f.close()

显示结果：