Python正则表达式re库

1. 字符匹配

• 字符相关

  import re
  
  text = "Hello World! 123alialiya啊123alialiya啊 Hello"
  
  """简单字符串匹配"""
  data_list = re.findall("23a", text)
  print(data_list)
  
  """单个字符匹配"""
  data_list = re.findall("[abcde]", text)
  print(data_list)
  data_list = re.findall("23[abced]", text)
  print(data_list)
  
  """ [^a-z]除小写字母以外的其他字符"""
  data_list = re.findall("[^a-z]", text)
  print(data_list)
  
  """数字"""
  data_list = re.findall("1[0-9]", text)
  print(data_list)
  
  """ .代指除换行符以外的任意字符"""
  data_list = re.findall("a.i", text)
  print(data_list)
  
  """贪婪匹配"""
  data_list = re.findall("a.+i", text)  # 贪婪匹配
  print(data_list)
  
  """非贪婪匹配"""
  data_list = re.findall("a.+?i", text)  # 非贪婪匹配
  print(data_list)
  
  """ \w指字母或数字或下划线(包含汉字) +贪婪匹配"""
  data_list = re.findall("a\w+ya", text)
  print(data_list)
  
  """ \d代指数字"""
  data_list = re.findall("\dali", text)
  print(data_list)
  
  """贪婪匹配"""
  data_list = re.findall("\d+ali", text)
  print(data_list)
  
  """ \s代指意的空白符，包括空格、制表符等 """
  """ ?问号代表前面的字符最多只可以出现一次（0次或1次）"""
  """ +?结合代指非贪婪匹配 """
  data_list = re.findall("\s\w+?", text)
  print(data_list)
  

• 次数相关

  """
  * 重复0次或多次
  + 重复1次或多次
  ? 重复0次或1次
  {n} 重复n次
  {n,} 重复n次或更多次
  {n,m} 重复n到m次
  """
  

• 括号（分组）

  """提取指定区域"""
  import re
  
  text = "Hello World! 123alialiya啊123alialiya啊 Hello"
  
  data_list = re.findall("1(\d{2}\w{3})", text)
  print(data_list)
  
  data_list = re.findall("!\s(1(\d{2}\w{3}))", text)
  print(data_list)
  

  """提取指定区域 + 或条件"""
  data_list = re.findall("([\s|\w]123)", text)
  print(data_list)  # [' 123', '啊123']
  

2.起始和结束

• 场景：要求用户输入的内容必须是指定的内容开头和结尾
• ^ 起始
• $ 结束
• 示例:

  import re
  
  text1 = "aliali@qq.comali"
  text2 = "1234567@qq.com"
  
  email_list = re.findall("^\d+@\w+.com$", text1)
  print(email_list)  # []
  email_list = re.findall("^\d+@\w+.com$", text2, re.ASCII)
  print(email_list)  # ['1234567@qq.com']
  

3. 特殊字符

• 正则表达式中：* . \ { } ( ) 等都具有特殊的含义，匹配时需要转义
• 转义符号：\

4. re模块常用方法

• findall，获取匹配到的所有数据，返回list

  import re
  
  text = "dsf130429191912015219k13042919591219521Xkk"
  data_list = re.findall("(\d{6})(\d{4})(\d{2})(\d{2})(\d{3})([0-9]|X)", text)
  print(data_list) # [('130429', '1919', '12', '01', '521', '9'), ('130429', '1959', '12', '19', '521', 'X')]
  

• match，从起始位置开始匹配，匹配成功返回一个对象，未匹配成功返回None

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.match("逗\dB", text)
  if data:
      content = data.group() # "逗2B"
      print(content)
  

• search，浏览整个字符串去匹配第一个，匹配成功返回对象，未匹配成功返回None

  import re
  
  text = "大小逗2B最逗3B欢乐"
  data = re.search("逗\dB", text)
  if data:
      print(data.group())  # "逗2B"
  

• sub，替换匹配成功的位置

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.sub("\dB", "沙雕", text, 1)  # 替换一次，不指定次数默认替换全部
  print(data) # 逗沙雕最逗3B欢乐
  

• split，根据匹配成功的位置分割，返回list

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.split("\dB", text, 1)  # 分割第一个，不指定次数时默认分割全部
  print(data) # ['逗', '最逗3B欢乐']
  

• finditer，返回迭代器对象

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.finditer("\dB", text)
  for item in data:
      print(item.group())
  
  data = re.finditer("(?P<xx>\dB)", text)  # 命名分组
  for item in data:
      print(item.groupdict())
  

5. 例：判断字符串是否是合法的整数或小数（首位可能含有空格），例如：‘.12’, ‘12’, ‘1.2’, ‘1e+2’都是合法数，’.', ‘2 3’, '3e’不合法

   import re
   s = '    -234.3e+3  '
   res = re.match('^\ *[\+-]?(\d+\.?\d*|\.\d+)([eE][\+-]?\d+)?\ *$', s)
   # re.match方法，符合返回第一个成功的匹配，否则返回None
   if res:
       return True
   else:
       return False