#导入 re 模块import re s = ‘nick jenny nice‘ # 匹配方式（一）b = re.match(r‘nick‘,s)q = b.group()print(q) # 匹配方式（二）# 生成Pattern对象实例,r表示匹配源字符串a = re.compile(r‘nick‘)print(type(a))               #<class ‘_sre.SRE_Pattern‘> b = a.match(s)print(b)                     #<_sre.SRE_Match object; span=(0, 4), match=‘nick‘> q = b.group()print(q)  #被匹配的字符串放在string中print(b.string)              #nick jenny nice#要匹配的字符串放在re中print(b.re)                  #re.compile(‘nick‘)

# "." 匹配任意字符（除了\n）a = re.match(r".","95nick")b = a.group()print(b)输出结果：9 # [...] 匹配字符集a = re.match(r"[a-zA-Z0-9]","123Nick")b = a.group()print(b)输出结果：1

# \d \D 匹配数字/非数字a = re.match(r"\D","nick")b = a.group()print(b)输出结果：n # \s \S 匹配空白/非空白字符a = re.match(r"\s"," ")b = a.group()print(b)输出结果： # \w \W 匹配单词字符[a-zA-Z0-9]/非单词字符a = re.match(r"\w","123Nick")b = a.group()print(b)输出结果：1a = re.match(r"\W","+-*/")b = a.group()print(b)输出结果：+

# "*" 匹配前一个字符0次或者无限次a = re.match(r"[A-Z][a-z]*","Aaaaaa123")    #可以只匹配A，123不会匹配上b = a.group()print(b)输出结果：Aaaaaaa # “+” 匹配前一个字符1次或者无限次a = re.match(r"[_a-zA-Z]+","nick")b = a.group()print(b)输出结果：nick # “？” 匹配一个字符0次或者1次a = re.match(r"[0-8]?[0-9]","95")   #(0-8)没有匹配上9b = a.group()print(b)输出结果：9 # {m} {m,n} 匹配前一个字符m次或者m到n次a = re.match(r"[\w]{6,10}@qq.com","630571017@qq.com")b = a.group()print(b)输出结果：630571017@qq.com # *? +? ?? 匹配模式变为非贪婪（尽可能少匹配字符串）a = re.match(r"[0-9][a-z]*?","9nick")b = a.group()print(b)输出结果：9a = re.match(r"[0-9][a-z]+?","9nick")b = a.group()print(b)输出结果：9n

# "^" 匹配字符串开头,多行模式中匹配每一行的开头。li = "nick\nnjenny\nsuo"a = re.search("^s.*",li,re.M)b = a.group()print(b)输出结果：suo # "$" 匹配字符串结尾,多行模式中匹配每一行的末尾。li = "nick\njenny\nnick"a = re.search(".*y$",li,re.M)b = a.group()print(b)输出结果：jenny # \A 仅匹配字符串开头li = "nickjennyk"a = re.findall(r"\Anick",li)print(a)输出结果：[‘nick‘] # \Z 仅匹配字符串结尾li = "nickjennyk"a = re.findall(r"nick\Z",li)print(a)输出结果：[] # \b 匹配一个单词边界，也就是指单词和空格间的位置a = re.search(r"\bnick\b","jenny nick car")b = a.group()print(b)输出结果：nick

# "|" 匹配左右任意一个表达式a = re.match(r"nick|jenny","jenny")b = a.group()print(b)输出结果: jenny # (ab) 括号中表达式作为一个分组a = re.match(r"[\w]{6,10}@(qq|163).com","630571017@qq.com")b = a.group()print(b)输出结果: 630571017@qq.com # \<number> 引用编号为num的分组匹配到的字符串a = re.match(r"<([\w]+>)[\w]+</\1","<book>nick</book>")b = a.group()print(b)输出结果: <book>nick</book> # (?P<key>vlace) 匹配输出字典li = ‘nick jenny nnnk‘a = re.match("(?P<k1>n)(?P<k2>\w+).*(?P<k3>n\w+)",li)print(a.groupdict())输出结果：{‘k2‘: ‘ick‘, ‘k1‘: ‘n‘, ‘k3‘: ‘nk‘} # (?P<name>) 分组起一个别名# (?P=name) 引用别名为name的分组匹配字符串a = re.match(r"<(?P<jenny>[\w]+>)[\w]+</(?P=jenny)","<book>nick</book>")b = a.group()print(b)输出结果: <book>nick</book>

######## 模块方法介绍 ########## match 从头匹配 # search 匹配整个字符串，直到找到一个匹配 # findall 找到匹配，返回所有匹配部分的列表# findall 加括号li = ‘nick jenny nick car girl‘ r = re.findall(‘n\w+‘,li)print(r)#输出结果：[‘nick‘, ‘nny‘, ‘nick‘]r = re.findall(‘(n\w+)‘,li)print(r)#输出结果：[‘nick‘, ‘nny‘, ‘nick‘]r = re.findall(‘n(\w+)‘,li)print(r)#输出结果：[‘ick‘, ‘ny‘, ‘ick‘]r = re.findall(‘(n)(\w+)(k)‘,li)print(r)#输出结果：[(‘n‘, ‘ic‘, ‘k‘), (‘n‘, ‘ic‘, ‘k‘)]r = re.findall(‘(n)((\w+)(c))(k)‘,li)print(r)#输出结果：[(‘n‘, ‘ic‘, ‘i‘, ‘c‘, ‘k‘), (‘n‘, ‘ic‘, ‘i‘, ‘c‘, ‘k‘)]  # finditer 返回一个迭代器，和findall一样li = ‘nick jenny nnnk‘a = re.finditer(r‘n\w+‘,li)for i in a:    print(i.group()) # sub 将字符串中匹配正则表达式的部分替换为其他值li = ‘This is 95‘a = re.sub(r"\d+","100",li)print(a) li = "nick njenny ncar ngirl"a = re.compile(r"\bn")b = a.sub(‘cool‘,li,3)      #后边参数替换几次print(b) #输出结果：#coolick cooljenny coolcar ngirl # split 根据匹配分割字符串，返回分割字符串组成的列表li = ‘nick,suo jenny:nice car‘a = re.split(r":| |,",li)   #或|print(a) li = ‘nick1jenny2car3girl5‘a = re.compile(r"\d")b = a.split(li)print(b) #输出结果:#[‘nick‘, ‘jenny‘, ‘car‘, ‘girl‘, ‘‘]   #注意后边空元素

li = ‘nick jenny nnnk‘ a = re.match("n\w+",li)print(a.group()) a = re.match("(n)(\w+)",li)print(a.groups()) a = re.match("(?P<k1>n)(?P<k2>\w+).*(?P<k3>n\w+)",li)print(a.groupdict())输出结果：nick(‘n‘, ‘ick‘){‘k1‘: ‘n‘, ‘k3‘: ‘nk‘, ‘k2‘: ‘ick‘} -----------------------------------------------import rea = "123abc456" re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(0)   #123abc456,返回整体 re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(1)   #123 re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(2)   #abc re.search("([0-9]*)([a-z]*)([0-9]*)",a).group(3)   #456  group(1) 列出第一个括号匹配部分，group(2) 列出第二个括号匹配部分，group(3)列出第三个括号匹配部分。

#re.I   使匹配对大小写不敏感a = re.search(r"nick","NIck",re.I)print(a.group()) #re.L   做本地化识别（locale-aware）匹配#re.U   根据Unicode字符集解析字符。这个标志影响 \w, \W, \b, \B. #re.S：.将会匹配换行符，默认.逗号不会匹配换行符a = re.findall(r".","nick\njenny",re.S)print(a)输出结果:[‘n‘, ‘i‘, ‘c‘, ‘k‘, ‘\n‘, ‘j‘, ‘e‘, ‘n‘, ‘n‘, ‘y‘] #re.M：^$标志将会匹配每一行，默认^只会匹配符合正则的第一行；默认$只会匹配符合正则的末行n = """12 drummers drumming,11 pipers piping, 10 lords a-leaping""" p = re.compile("^\d+")p_multi = re.compile("^\d+",re.M)print(re.findall(p,n))print(re.findall(p_multi,n))

# 匹配手机号phone_num = ‘13001000000‘a = re.compile(r"^1[\d+]{10}")b = a.match(phone_num)print(b.group())

# 匹配IP地址ip = ‘192.168.1.1‘a = re.compile(r"(((1?[0-9]?[0-9])|(2[0-4][0-9])|(25[0-5]))\.){3}((1?[0-9]?[0-9])|(2[0-4][0-9])|(25[0-5]))$")b = a.search(ip)print(b)

# 匹配 emailemail = ‘630571017@qq.com‘a = re.compile(r"(.*){0,26}@(\w+){0,20}.(\w+){0,8}")b = a.search(email)print(b.group())