Python程序设计基础第七章笔记：字符串

    '字符串'.encode()  ==>b'\xe5\xad\x97\xe7\xac\xa6\xe4\xb8\xb2'   #默认以 utf-8 形式编码
    
    _.decode()  ==>'字符串'
    
    '字符串'.encode('gbk')  ==>b'\xd7\xd6\xb7\xfb\xb4\xae'

    import sys
    sys.getdefaultcoding()  ==>'utf-8'   #查看默认编码格式

     f = 'The number {0:,} in hex is: {0:#_x} , in oct is {0:#_o} , \ {1:,} in hex is:'
     +' {1:#_x}'.format    #在 {0:,} 中，0 表示参数列表的第一位， ： 表示后面是要格式化的形式 ，, 表示用 , 分割长数字， {0：#_x} 中的 # 表示输出进制前缀
     
    f(123456789,2000000000)  ==>'The number 123,456,789 in hex is: 0x75b_cd15 , in oct is 0o7_2674_6425 , 2,000,000,000 in hex is: 0x7735_9400'
    
    lst = [123456789,2000000000]
    
    f = 'The number {0[0]:,} in hex is: {0[0]:#_x} , in oct is {0[0]:#_o} , {0[1]:,} in hex is: {1:#_x}'.format     
    #format 是字符串这个类的内置方法，在 f 中，字符串的实例是 'The number {0[0]:,} in hex is: {0[0]:#_x} , in oct is {0[0]:#_o} , {0[1]:,} in hex is: {1:#_x}'
    f(lst)  ==>'The number 123,456,789 in hex is: 0x75b_cd15 , in oct is 0o7_2674_6425 , 2,000,000,000 in hex is: 0x7735_9400'
    #f 的参数是 lst
    'my name is {name}, my age is {age}'.format(age = 23, name = lihua) 
    ==>'my name is lihua, my age is 23'     #支持关键参数

    width, precision, value = 10, 4, 11/3
    f'result:{value : {width}.{precision}}'  ==>'result:     3.667'  #width 是最小宽度，3.667是五个字节，所以要留出 5 个空格，precision 指精度 ，必须要在花括号内再套一个花括号来格式后面的两个值

    from string import Template
    t = Template('My name is ${name} and my age is ${age}')
    d = {name:'zhangsan' , age:18}
    t.substitute(d)
    ==>'My name is zhangsan and my age is 18'

    s = 'i am tired of notes'
    
    s.find('tired',5,15)
    Out[74]: 5
    
    s.find('am',5,10)
    Out[75]: -1
    
    s.index('e')
    Out[76]: 8
    
    s.rindex('e')
    Out[77]: 17
    
    s.rindex('happy')
    ValueError: substring not found
    
    
    s.count('e')
    Out[79]: 2

    'i am so so\n\n\ntired of notes'.split()
    Out[80]: ['i', 'am', 'so', 'so', 'tired', 'of', 'notes']
    
    'i am so so\n\n\ntired of notes'.split('\n')
    Out[81]: ['i am so so', '', '', 'tired of notes']
    
    'i am so so tired of notes'.rpartition('so')
    Out[82]: ('i am so ', 'so', ' tired of notes')
    
    'i am so so\n\n\ntired of notes'.split(maxsplit = 5)
    Out[83]: ['i', 'am', 'so', 'so', 'tired', 'of notes']

    x = 'aaa   bb   c d e fff   '
    
    ' '.join(x.split())
    Out[2]: 'aaa bb c d e fff'

    x.lower()
    Out[5]: 'katty is a cat'
    
    x.upper()
    Out[6]: 'KATTY IS A CAT'
    
    x.capitalize()
    Out[7]: 'Katty is a cat'
    
    x.title()
    Out[8]: 'Katty Is A Cat'
    
    x.swapcase()
    Out[9]: 'KATTY IS A cat'

    'One of the classmates of John is the cousin of John'.replace('of','in')
    Out[16]: 'One in the classmates in John is the cousin in John'
    
    table = ''.maketrans('abcdefg','ABCDEFG')
    
    'there are many uppercases'.translate(table)
    Out[18]: 'thErE ArE mAny uppErCAsEs'

    'aabbccddeeeffg'.strip('gbaef')
    ==> 'ccdd'
    #第一轮循环：aabbccddeeeff~~g~~ ,~~aa~~ bbccddeeeff,bbccddeee~~ff~~ ==>bbccddeee
    #第二轮循环：~~bb~~ ccddeee，ccdd~~eee~~ ==>ccdd
    #第三轮循环：ccdd ==>ccdd
    #二三轮结果相同，不再循环

    'It is boring'.startswith('I',0,0)
    Out[27]: False
    
    'It is boring'.startswith('I',0,1)
    Out[28]: True
    
    'It is boring'.endswith('is',0,4)
    Out[32]: False
    
    'It is boring'.endswith('is',0,5)      #注意起始和结束位置
    Out[33]: True

    '\n\t'.isspace()
    Out[12]: True
    
    '123.4'.isalnum()
    Out[1]: False
    
    '123.4'.isdigit()
    Out[2]: False```

    'center'.center(20,'=')
    Out[15]: '=======center======='
    
    'left'.ljust(15,'r')
    Out[17]: 'leftrrrrrrrrrrr'
    
    'right'.rjust(15,'l')
    Out[19]: 'llllllllllright'
    
    'center'.zfill(20)
    Out[20]: '00000000000000center'

    import math 
    
    eval(math.sqrt(3))
    TypeError: eval() arg 1 must be a string, bytes or code object
    
    eval('math.sqrt(3)')
    Out[32]: 1.7320508075688772
    
    a ,b = 3 ,4
    
    eval('a + 1')
    Out[35]: 4
    
    x = input()
    ab
    
    eval(x)
    NameError: name 'ab' is not defined
    
    ab = 1
    
    eval(x)
    Out[39]: 1
    
    lst = input()
    
    ['a','b',15]
    
    lst1 = list(lst)
    
    lst1
    Out[47]: ['[', "'", 'a', "'", ',', "'", 'b', "'", ',', '1', '5', ']']
    
    eval(lst)
    Out[48]: ['a', 'b', 15]    #使用 eval() 将值为列表的字符串转化为列表

    import string
    
    string.digits+ string.ascii_letters+ string.punctuation
    Out[88]: '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\ ]^_`{|}~'

    import jieba
    import snownlp
    
    x = '分词的准确度直接影响了后续文本处理和挖掘算法的最终效果'
    jieba.cut(x)
    
    print(list(_))
    ['分词', '的', '准确度', '直接', '影响', '了', '后续', '文本处理', '和', '挖掘', '算法', '的', '最终', '效果']
    
    print(snownlp.snowNLP(x).words)
    ['分词', '的', '准确度', '直接', '影响', '了', '后续', '文本处理', '和', '挖掘', '算法', '的', '最终', '效果']
    
    jieba.add_word('本来是要被分开的一句话')   #为词库增加单词
    
    list(jieba.cut('本来是要被分开的一句话'))
    Out[65]: ['本来是要被分开的一句话']

    import pypinyin
    from pypinyin import lazy_pinyin,pinyin
    
    lazy_pinyin('逃离')
    Out[69]: ['tao', 'li']     #返回拼音
    
    lazy_pinyin('逃离',1)      #带声调
    Out[70]: ['táo', 'lí']
    
    lazy_pinyin('逃离',2)
    Out[71]: ['ta2o', 'li2']
    
    lazy_pinyin('逃离',3)
    Out[72]: ['t', 'l']
    
    pinyin('重要')
    Out[76]: [['zhòng'], ['yào']]   
    
    pinyin('重阳')
    Out[77]: [['chóng'], ['yáng']]   #识别多音字
    
    pinyin('重阳节',heteronym = True)
    Out[79]: [['chóng'], ['yáng'], ['jié', 'jiē']]   #识别多音字并返回全部音，可能未更新扩展库导致出错
    
    lazy_pinyin('中Englishi混合123',1)   #区别中英文
    Out[81]: ['zhōng', 'Englishi', 'hùn', 'hé', '123']