python re 正则表达式

1 正则表达式相关

当给你一大堆文本信息，让你提取其中的指定数据时，可以使用正则来实现。例如：提取文本中的邮箱和手机号

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"

phone_list = re.findall("1[3|5|8|9]\d{9}", text)
print(phone_list)

1.1 正则表达式

1. 字符相关

• wupeiqi匹配文本中的wupeiqi

  import re
  
  text = "你好wupeiqi,阿斯顿发wupeiqasd 阿士大夫能接受的wupeiqiff"
  data_list = re.findall("wupeiqi", text)
  print(data_list) # ['wupeiqi', 'wupeiqi'] 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wupeiqi,阿斯顿发awupeiqasd 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wupeiqi,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意外的其他字符。

  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 ）。

  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) # ['武沛alex', '武沛alex']
  

• \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
  
  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）

• 提取数据区域

  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)  # ['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')]
  

• 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')]
  

  练习题

1. 利用正则匹配QQ号码

   [1-9]\d{4,}
   

2. 身份证号码

   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')]
   

3. 手机号

   import re
   
   text = "我的手机哈是15133377892，你的手机号是1171123啊？"
   data_list = re.findall("1[3-9]\d{9}", text)
   print(data_list)  # ['15133377892']
   

4. 邮箱地址

   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"
   email_list = re.findall("\w+@\w+\.\w+",text)
   print(email_list) # ['442662578@qq.com和xxxxx']
   

   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"
   email_list = re.findall("[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+\.[a-zA-Z0-9_-]+", text, re.ASCII)
   print(email_list) # ['442662578@qq.com', 'xxxxx@live.com']
   
   

   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"
   email_list = re.findall("\w+@\w+\.\w+", text, re.ASCII)
   print(email_list) # ['442662578@qq.com', 'xxxxx@live.com']
   

   import re
   
   text = "楼主太牛44266-2578@qq.com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"
   email_list = re.findall("(\w+([-+.]\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*)", text, re.ASCII)
   print(email_list) # [('44266-2578@qq.com', '-2578', '', ''), ('xxxxx@live.com', '', '', '')]
   

5. 补充代码，实现获取页面上的所有评论（已实现），并提取里面的邮箱。

   # 先安装两个模块
   pip3 install requests
   pip3 install beautifulsoup4
   

   import re
   import requests
   from bs4 import BeautifulSoup
   
   res = requests.get(
       url="https://www.douban.com/group/topic/79870081/",
       headers={
           'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36',
       }
   )
   bs_object = BeautifulSoup(res.text, "html.parser")
   comment_object_list = bs_object.find_all("p", attrs={"class": "reply-content"})
   for comment_object in comment_object_list:
       text = comment_object.text
       print(text)
       # 请继续补充代码，提取text中的邮箱地址
   
   

4. 起始和结束

上述示例中都是去一段文本中提取数据，只要文本中存在即可。

但，如果要求用户输入的内容必须是指定的内容开头和结尾，比就需要用到如下两个字符。

• ^开始
• $结束

import re

text = "啊442662578@qq.com我靠"
email_list = re.findall("^\w+@\w+.\w+$", text, re.ASCII)
print(email_list) # []

import re

text = "442662578@qq.com"
email_list = re.findall("^\w+@\w+.\w+$", text, re.ASCII)
print(email_list) # ['442662578@qq.com']

这种一般用于对用户输入数据格式的校验比较多，例如：

import re

text = input("请输入邮箱：")
email = re.findall("^\w+@\w+.\w+$", text, re.ASCII)
if not email:
    print("邮箱格式错误")
else:
    print(email)

5. 特殊字符

由于正则表达式中* . \ { } ( )等都具有特殊的含义，所以如果想要在正则中匹配这种指定的字符，需要转义，例如：

import re

text = "我是你{5}爸爸"
data = re.findall("你{5}爸", text)
print(data) # []

import re

text = "我是你{5}爸爸"
data = re.findall("你\{5\}爸", text)
print(data)

1.2 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
  

#手机号码校验
import re
while True:
    iphone = input('请输入手机号码：').strip()
    res = re.match("1[35678]\d{9}", iphone)
    #res = re.match("1[3-9]\d{9}", iphone)
    if res:
        print(iphone)
        break


#邮箱校验
import re
while True:
    email = input('请输入邮箱：').strip()
    res = re.match("\w+@\w+\.\w+", email, re.ASCII)
    if res:
        print(email)
        break

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

  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)