关于python正则表达式

import re
#普通字符串分割
line = '王 宝; 强, 是,一个, 好人'
s=line.split(';')
print(s)
#['王 宝', ' 强, 是,一个, 好人']
#函数 re.split() 分割，它允许为分隔符指定多个正则模式。
#在上面的例子中，分隔符可以是逗号，分号或者是空格，并且后面紧跟着任意个的空格
s=re.split(r'[;,\s]\s*', line)
print(s)
#['王', '宝', '强', '是', '一个', '好人']
#加竖线的split分割，阅读会容易一些
s=re.split(r'[;|,|\s]\s*', line)
print(s)
#['王', '宝', '强', '是', '一个', '好人']
#re.split捕获分组，使用（）方式
#如果使用捕获分组，那么被匹配的文本也将出现在结果列表中
s=re.split(r'(;|,|\s)\s*', line)
print(s)
#['王', ' ', '宝', ';', '强', ',', '是', ',', '一个', ',', '好人']
#不加竖线的捕获分组，无法解析字符串，所以建议统一使用|分割
s=re.split(r'(;,\s)\s*', line)
print(s)
#['王 宝; 强, 是,一个, 好人']

filenames=[ 'Makefile', 'foo.c', 'bar.py', 'spam.c', 'spam.h' ,'foo.h']
#用 str.startswith()检查字符串开头
filename= [name for name in filenames if name.startswith('foo') ]
print(filename)
#['foo.c', 'foo.h']
#用 str.endswith()检查字符串结尾
filename= [name for name in filenames if name.endswith(('.c')) ]
print(filename)
#['foo.c', 'spam.c']
#用 str.endswith()检查多个字符串结尾，必须用元祖参数
filename= [name for name in filenames if name.endswith(('.c', '.h')) ]
print(filename)
#['foo.c', 'spam.c', 'spam.h', 'foo.h']

url = 'http://www.python.org'
s=re.match('http:|https:|ftp:',url)
print(s)
#<re.Match object; span=(0, 5), match='http:'>

from fnmatch import fnmatch, fnmatchcase
#通过fnmatch, fnmatchcase匹配字符串
filenames = ['dat1.csv', 'Dat2.csv', 'DAT33.csv', 'config.ini', 'foo.py']
##fnmatch对大小写不敏感
filename=[name for name in filenames if fnmatch(name, 'Dat*.csv')]
print(filename)
#['dat1.csv', 'Dat2.csv', 'DAT33.csv']
filename=[name for name in filenames if fnmatch(name, 'Dat[0-9]*.csv')]
print(filename)
#['dat1.csv', 'Dat2.csv', 'DAT33.csv']
#fnmatchcase对大小写敏感
filename=[name for name in filenames if fnmatchcase(name, 'Dat*.csv')]
print(filename)
#['Dat2.csv']

dt1 = '11/27/2012'
dt2 = 'Nov 27,2012'
if re.match(r'\d+/\d+/\d+',dt1):
    print('yes')
else:
    print('no')
#模式编译
#如果用同一个模式去做多次匹配，应先将模式字符串预编译为模式对象
dtrep=re.compile(r'\d+/\d+/\d+')
if dtrep.match(dt1):
    print('yes')
else:
    print('no')
text = 'Today is 11/27/2012. PyCon starts 3/13/2013.'
s=dtrep.findall(text)
print(s)
#['11/27/2012', '3/13/2013']

dtrep = re.compile(r'(\d+)/(\d+)/(\d+)')
m = dtrep.match('11/27/2012')
print(m.groups())      #('11', '27', '2012')
print(m.group(0))      #11/27/2012
print(m.group(1))      #11
print(m.group(2))      #27
print(m.group(3))      #2012
month, day, year = m.groups()
for month, day, year in dtrep.findall(text):
    print('{}-{}-{}'.format(year,month,day))    #2012-11-27 2013-3-13
#以迭代方式返回匹配
for m in dtrep.finditer(text):
    print(m)    #<re.Match object; span=(9, 19), match='11/27/2012'>    <re.Match object; span=(34, 43), match='3/13/2013'>
    print(m.groups())   #('11', '27', '2012')   ('3', '13', '2013')
dtrep = re.compile(r'(\d+/\d+/\d+)')
for date in dtrep.findall(text):
    print(date)    #2012-11-27 2013-3-13

text = 'yeah, but no, but yeah, but no, but yeah'
text.replace('yeah','yep')
print(text)
#yeah, but no, but yeah, but no, but yeah
text = 'Today is 11/27/2012. PyCon starts 3/13/2013.'
newtext=re.sub(r'(\d+)/(\d+)/(\d+)',r'\3-\1-\2',text)
print(newtext)
#Today is 2012-11-27. PyCon starts 2013-3-13.

strre = re.compile(r'\"(.*)\"')
text1 = 'Computer says "no."'
print(strre.findall(text1))
#['no.']
text2 = 'Computer says "no." Phone says "yes."'
print(strre.findall(text2))
#['no." Phone says "yes.']
#加?变成非贪婪模式，从而得到最短的匹配
strre = re.compile(r'\"(.*?)\"')
print(strre.findall(text2))
#['no.', 'yes.']

comment = re.compile(r'/\*(.*?)\*/')
text1 = '/* this is a comment */'
text2 = '''/* this is a
 multiline comment */
... '''
print(comment.findall(text1))   #[' this is a comment ']
print(comment.findall(text2))   #[]
#(?:.|\n) 指定了一个非捕获组
comment = re.compile(r'/\*((?:.|\n)*?)\*/')
print(comment.findall(text2))
#[' this is a\n multiline comment ']
#正则表达式中的点 (.) 匹配包括换行符在内的任意字符串
comment = re.compile(r'/\*(.*?)\*/', re.DOTALL)
print(comment.findall(text2))
#[' this is a\n multiline comment ']