Python：正则表达式

# 正则表达式书写

‘hing‘
‘\wing‘
‘123456‘
‘\d\d\d\d\d\d‘
‘regex.py‘
‘.*\.py‘

>>> # re模块的compile()函数将返回（创建）一个Regex模式对象
>>> import re
>>> phoneNumRegex = re.compile(r‘\d\d\d-\d\d\d-\d\d\d\d‘)

>>> Regex = re.compile(r‘(\d\d\d)-(\d\d\d-\d\d\d\d)‘)
>>> mo = Regex.search(‘My number is 415-555-4242.‘)
>>> Regex = re.compile(r‘(\d\d\d)-(\d\d\d-\d\d\d\d)‘) # 创建Regex对象
>>> mo = Regex.search(‘My number is 415-555-4242.‘)   # 返回Match对象
>>> mo.group()         # 调用Regex对象的group()方法将返回整个匹配文本
‘415-555-4242‘
>>> mo.group(1)
‘415‘
>>> mo.group(2)
‘555-4242‘
>>> mo.group(0)
‘415-555-4242‘
>>> mo.groups()
(‘415‘, ‘555-4242‘)
>>> a,b = mo.groups()   # groups()方法返回多个值得元组
>>> a
‘415‘
>>> b
‘555-4242‘
>>> 

>>> heroRegex = re.compile (r‘Batman|Tina Fey‘)
>>> mo1 = heroRegex.search(‘Batman and Tina Fey.‘)
>>> mo1.group()
‘Batman‘
>>> mo2 = heroRegex.search(‘Tina Fey and Batman.‘)
>>> mo2.group()
‘Tina Fey

>>> batRegex = re.compile(r‘Bat(wo)?man‘)   # 如果‘wo‘没有用括号括起来，则可选的字符将是Batwo
>>> mo1 = batRegex.search(‘The Adventures of Batman‘)
>>> mo1.group()
‘Batman‘
>>> mo2 = batRegex.search(‘The Adventures of Batwoman‘)
>>> mo2.group()
‘Batwoman‘

>>> batRegex = re.compile(r‘Bat(wo)*man‘) # 如果要匹配‘*‘号则用\*
>>> mo1 = batRegex.search(‘The Adventures of Batman‘)
>>> mo1.group()
‘Batman‘
>>> mo2 = batRegex.search(‘The Adventures of Batwoman‘)
>>> mo2.group()
‘Batwoman‘
>>> mo3 = batRegex.search(‘The Adventures of Batwowowowoman‘)
>>> mo3.group()
‘Batwowowowoman

>>> batRegex = re.compile(r‘Bat(wo)+man‘)  # 如果要匹配+号用\+
>>> mo1 = batRegex.search(‘The Adventures of Batwoman‘)
>>> mo1.group()
‘Batwoman‘
>>> mo2 = batRegex.search(‘The Adventures of Batwowowowoman‘)
>>> mo2.group()
‘Batwowowowoman‘
>>> mo3 = batRegex.search(‘The Adventures of Batman‘)
>>> mo3 == None
True

>>> greedyHaRegex = re.compile(r‘(Ha){3,5}‘) # 若果要匹配{,则用\{
>>> mo1 = greedyHaRegex.search(‘HaHaHaHaHa‘)
>>> mo1.group()
‘HaHaHaHaHa‘
>>> nongreedyHaRegex = re.compile(r‘(Ha){3,5}?‘)
>>> mo2 = nongreedyHaRegex.search(‘HaHaHaHaHa‘)
>>> mo2.group()
‘HaHaHa‘

>>> nongreedyRegex = re.compile(r‘<.*?>‘)
>>> mo = nongreedyRegex.search(‘<To serve man> for dinner.>‘)
>>> mo.group()
‘<To serve man>‘
>>> greedyRegex = re.compile(r‘<.*>‘)
>>> mo = greedyRegex.search(‘<To serve man> for dinner.>‘)
>>> mo.group()
‘<To serve man> for dinner.>‘

>> Regex = re.compile(r‘(\d\d\d)-(\d\d\d-\d\d\d\d)‘)
>>> mo = Regex.search(‘My number is 415-555-4242.‘)
>>> Regex = re.compile(r‘(\d\d\d)-(\d\d\d-\d\d\d\d)‘) # 创建Regex对象
>>> mo = Regex.search(‘My number is 415-555-4242.‘)   # 返回Match对象
>>> mo.group()         # 调用Regex对象的group()方法将返回整个匹配文本
‘415-555-4242‘
>>> mo.group(1)
‘415‘
>>> mo.group(2)
‘555-4242‘
>>> mo.group(0)
‘415-555-4242‘
>>> mo.groups()
(‘415‘, ‘555-4242‘)
>>> a,b = mo.groups()   # groups()方法返回多个值得元组
>>> a
‘415‘
>>> b
‘555-4242‘
>>> 

>>> Regex = re.compile(r‘\d\d\d-\d\d\d-\d\d\d\d‘) # has no groups
>>> Regex.findall(‘Cell: 415-555-9999 Work: 212-555-0000‘)
[‘415-555-9999‘, ‘212-555-0000‘]
>>> Regex = re.compile(r‘(\d\d\d)-(\d\d\d)-(\d\d\d\d)‘) # has groups
>>> Regex.findall(‘Cell: 415-555-9999 Work: 212-555-0000‘)
[(‘415‘, ‘555‘, ‘1122‘), (‘212‘, ‘555‘, ‘0000‘)]

>>> namesRegex = re.compile(r‘Agent \w+‘)
>>> namesRegex.sub(‘CENSORED‘, ‘Agent Alice gave the secret documents to Agent Bob.‘)
‘CENSORED gave the secret documents to CENSORED.‘
>>> namesRegex = re.compile(r‘Agent \w+‘)
>>> namesRegex.sub(‘CENSORED‘, ‘Agent Alice gave the secret documents to Agent Bob.‘ , 1)  # 匹配1次
‘CENSORED gave the secret documents to Agent Bob.‘

>>> someRegexValue = re.compile(‘foo‘, re.IGNORECASE | re.DOTALL | re.VERBOSE)

>>> re.findall(r‘http://(?:\w+\.)*(\w+\.com)‘, ‘http://google.com http://www.google.com http://code.google.com‘)
[‘google.com‘, ‘google.com‘, ‘google.com‘]
>>> 

# （文件读写）疯狂填词2.py

‘‘‘
创建一个疯狂填词（ Mad Libs）程序，它将读入文本文件， 并让用户在该文本文件中出现 
ADJECTIVE、 NOUN、 ADVERB 或 VERB 等单词的地方， 加上他们自己的文本。例如，一个文本文件可能看起来像这样：
The ADJECTIVE panda walked to the NOUN and then VERB. A nearby NOUN was
unaffected by these events.
程序将找到这些出现的单词， 并提示用户取代它们。
Enter an adjective:
silly
Enter a noun:
chandelier
Enter a verb:
screamed
Enter a noun:
pickup truck
以下的文本文件将被创建：
The silly panda walked to the chandelier and then screamed. A nearby pickup truck was unaffected by these events.
结果应该打印到屏幕上， 并保存为一个新的文本文件。
‘‘‘


import re

def mad_libs(filename_path, save_path):
    with open(filename_path,‘r‘) as strings: # 相对路径下的文档
        words = strings.read()
    Regex = re.compile(r‘\w[A-Z]+‘)   # \w ：匹配1个任何字母、数字或下划线
    finds = Regex.findall(words)
    for i in finds:
        replace = input(‘输入你想替换 {} 的单词:\n‘.format(i)) 
        Regex2 = re.compile(i)
        words = Regex2.sub(replace,words,1) # 这个变量必须要是words与上面一致否则只打印最后替换的一个,可以画栈堆图跟踪这个变量的值
    print(words)
    
    # strings.close()  不用这一行，with 上下文管理器会自动关闭

    with open(save_path,‘a‘) as txt: 
        txt.write(words + ‘\n‘) #分行写
        txt.close()
        
    # save_txt = open(‘保存疯狂填词文档.txt‘,‘a‘)
    # save_txt.write(words)
    # save_txt.close()

if __name__ == ‘__main__‘: 
    filename_path = input(‘输入要替换的txt文本路径：‘)    # ‘疯狂填词原始文档.txt‘
    save_path = input(‘输入要保存的文件路径(包含文件名称）:‘) # ‘保存疯狂填词文档.txt‘
    mad_libs(filename_path, save_path)