【无标题】

1. 字符相关

• weijianmin 匹配文本中的weijianmin

  import re
  
  text = "你好weijianmin,阿斯顿发wupeiqasd 阿士大夫能接受的weijianminff"
  data_list = re.findall("weijianmin", text)
  print(data_list) # ['weijianmin', 'weijianmin'] 可用于计算字符串中某个字符出现的次数
  

• [abc] 匹配a或b或c 字符。

  import re
  
  text = "你2b好weijianmin,阿斯顿发aweijianeiqasd 阿士大夫a能接受的wffbbupqaceiqiff"
  data_list = re.findall("[abc]", text)
  print(data_list) # ['b', 'a', 'a', 'a', 'b', 'b', 'c']
  

  import re
  
  text = "你2b好weijianmin,阿斯顿发awupeiqasd 阿士大夫a能接受的wffbbupqcceiqiff"
  data_list = re.findall("q[abc]", text)
  print(data_list) # ['qa', 'qc']
  

• [^abc] 匹配除了abc以外的其他字符。

  import re
  
  text = "你wffbbupceiqiff"
  data_list = re.findall("[^abc]", text)
  print(data_list)  # ['你', 'w', 'f', 'f', 'u', 'p', 'e', 'i', 'q', 'i', 'f', 'f']
  

• [a-z] 匹配a~z的任意字符（ [0-9]也可以 ）。 [A-Z]

  import re
  
  text = "alexrootrootadmin"
  data_list = re.findall("t[a-z]", text)
  print(data_list)  # ['tr', 'ta']
  

• . 代指除换行符以外的任意字符。

  import re
  
  text = "alexraotrootadmin"
  data_list = re.findall("r.o", text)
  print(data_list) # ['rao', 'roo']
  

  import re
  
  text = "alexraotrootadmin"
  data_list = re.findall("r.+o", text) # 贪婪匹配
  print(data_list) # ['raotroo']
  

  import re
  
  text = "alexraotrootadmin"
  data_list = re.findall("r.+?o", text) # 非贪婪匹配
  print(data_list) # ['rao']
  

• \w 代指字母或数字或下划线（汉字）。

  import re
  
  text = "北京武沛alex齐 北京武沛alex齐"
  data_list = re.findall("武\w+x", text)
  print(data_list) # 
  

• \d 代指数字

  import re
  
  text = "root-ad32min-add3-admd1in"
  data_list = re.findall("d\d", text)
  print(data_list) # ['d3', 'd3', 'd1']
  

  import re
  
  d\d
  d\d{2}       固定数量-2个。
  d\d{2,10}    固定数量-2,10个。   text = "root-ad32min-add3111-admd1in"
  d\d{2,}
  d\d?         0次或1次  d    d一个数字
  d\d+         1次或n次
  d\d*         0次或n次
  
  # 示例1
  import re
  
  text = "陈松的手机号13999999993，欧阳的手机号99999999993999999手机号15999999993，"
  data = re.findall('1[358]\d{9}', text)
  print(data)
  
  # 示例2（默认贪婪匹配）
  import re
  text = "陈松的d9手机号d123,asdfddd999as;df123"
  data = re.findall('d\d+', text)
  print(data)
  
  # 示例3：（数量后面加？，变成非贪婪模式）
  import re
  text = "陈松的d9手机号d123,asdfddd999as;df123"
  data = re.findall('d\d+?', text)
  print(data)
  
  
  text = "root-ad32min-add3-admd1in"
  data_list = re.findall("d\d+", text)
  print(data_list) # ['d32', 'd3', 'd1']
  

• \s 代指任意的空白符，包括空格、制表符等。

  import re
  
  text = "root admin add admin"
  data_list = re.findall("a\w+\s\w+", text)
  print(data_list) # ['admin add']
  

2. 数量相关

• * 重复0次或更多次

  import re
  
  text = "他是大B个，确实是个大2B。"
  data_list = re.findall("大2*B", text)
  print(data_list) # ['大B', '大2B']
  

• + 重复1次或更多次

  import re
  
  text = "他是大B个，确实是个大2B，大3B，大66666B。"
  data_list = re.findall("大\d+B", text)
  print(data_list) # ['大2B', '大3B', '大66666B']
  

• ? 重复0次或1次

  import re
  
  text = "他是大B个，确实是个大2B，大3B，大66666B。"
  data_list = re.findall("大\d?B", text)
  print(data_list) # ['大B', '大2B', '大3B']
  

• {n} 重复n次

  import re
  
  text = "楼主太牛逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
  data_list = re.findall("151312\d{5}", text)
  print(data_list) # ['15131255789']
  

• {n,} 重复n次或更多次

  import re
  
  text = "楼主太牛逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
  data_list = re.findall("\d{9,}", text)
  print(data_list) # ['442662578', '15131255789']
  
  

• {n,m} 重复n到m次

  import re
  
  text = "楼主太牛逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
  data_list = re.findall("\d{10,15}", text)
  print(data_list) # ['15131255789']
  

3.括号

分组功能1：提取数据区域

import re

text = "楼主太牛51789逼了，在手机号也可15131251789线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
data_list = re.findall("151(312\d{5})", text)
print(data_list)

import re

text = "楼主太牛逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来15131266666呀"
data_list = re.findall("15(13)1(2\d{5})", text)
print(data_list)  # [ ('13', '255789')   ]

import re

text = "楼主太牛逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
data_list = re.findall("(15131(2\d{5}))", text)
print(data_list)  # [('15131255789', '255789')]

示例：身份证

import re

text = "dsf130429191912015219k13042919591219521Xkk"
data_list = re.findall("\d{17}[\dX]", text) # [abc]
print(data_list) # ['130429191912015219', '13042919591219521X']

import re

text = "dsf130429191912015219k13042919591219521Xkk"
data_list = re.findall("\d{17}(\d|X)", text)
print(data_list) # ['9', 'X']

import re

text = "dsf130429191912015219k13042919591219521Xkk"
data_list = re.findall("(\d{17}(\d|X))", text)
print(data_list) # [('130429191912015219', '9'), ('13042919591219521X', 'X')]

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')]

分组功能2：获取指定区域 + 或条件

import re

text = "楼主15131root太牛15131alex逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
data_list = re.findall("15131(2\d{5}|r\w+太)", text)
print(data_list)  # ['root太', '255789']

import re

text = "楼主15131root太牛15131alex逼了，在线想要 442662578@qq.com和xxxxx@live.com谢谢楼主，手机号也可15131255789，搞起来呀"
data_list = re.findall("(15131(2\d{5}|r\w+太))", text)
print(data_list)  # [('15131root太', 'root太'), ('15131255789', '255789')]