正则re模块

正则re模块

1. re模块

python中提供了re模块，可以处理正则表达式并对文本进行处理。

• findall，获取匹配到的所有数据

  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 = "大小逗2B最逗3B欢乐"
  data = re.match("逗\dB", text)
  print(data) # 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，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)
  print(data) # 逗沙雕最逗沙雕欢乐
  

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.sub("\dB", "沙雕", text, 1)
  print(data) # 逗沙雕最逗3B欢乐
  

• split，根据匹配成功的位置分割

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.split("\dB", text)
  print(data) # ['逗', '最逗', '欢乐']
  

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.split("\dB", text, 1)
  print(data) # ['逗', '最逗3B欢乐']
  

• finditer，匹配结果为迭代器

  import re
  
  text = "逗2B最逗3B欢乐"
  data = re.finditer("\dB", text)
  for item in data:
      print(item.group())
  

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

  text = "dsf130429191912015219k13042919591219521Xkk"
  data_list = re.finditer("\d{6}(?P<year>\d{4})(?P<month>\d{2})(?P<day>\d{2})\d{3}[\d|X]", text)
  for item in data_list:
      info_dict = item.groupdict()
      print(info_dict)