python re模块使用技巧总结

python re模块使用技巧总结

import re

#使用(?P<name>...) 或者 (?P=name)来标记变量，使用\g<name>的方式来检索

test = '110-120'
result = re.sub(r'1(?P<rest>[0-9]+)','A\g<rest>',test)
print(result)

#使用\+数字来索引已经标记的分组
test = 'aabb-aabb'
results = re.findall(r'([a-z]+)-(\1)',test)
print(results)

# (?i)忽略大小写 
th = re.compile(r'(?i)th')
results = re.finditer(th,'The quickest way is through this tunnel')
for result in results:
    print(result.group())
    print(result.start())
    print(result.end())
    print(result.span())

#(?im) 忽略大小写且匹配多行
th = re.compile(r'(?im)th')
results = re.findall(th,'''The quickest
way is through
this tunnel
''')
print(results)

#(?s)使得.号可以匹配\n


results = re.findall(r'th.*','''The first line
the second line
the third line
''')
print(results)

results = re.findall(r'(?s)th.*','''The first line
the second line
the third line
''')
print(results)

#使用(?m)跨行来查找，第一个例子将找不到第三行的th，因为这里不认为第三行是一个行开头，而是
#这三行的一部分，换句话说，默认情况下查找将这三行作为一个整体，而不是每一行作为一个部分
#依次去查找

results = re.findall(r'^th','''The first line
another line
the third line
''')
print(results)

results = re.findall(r'(?m)^th','''The first line
another line
the third line
''')
print(results)
#(?x)可以让正则表达式更加易懂，忽略所有的空白字符
#想要使用空白字符可以用字符组实现，例如空格[ ]
email = re.compile(r'''(?x)
                [\w\.]+
                @
                [\w\.]+
                \.com
                ''')

result = re.match(email,'cm.bioinformatcis@gmail.com')
if result:
    print(result.group())

#re.sub 可以通过指定第四个参数来指定替换的次数，默认所有匹配的位置都会匹配
print(re.sub(r'aabb','ccdd','aabb-aabb-aabb'))
print(re.sub(r'aabb','ccdd','aabb-aabb-aabb',1))

#re.split可以指定多个分隔符，并通过第三个参数来指定分割的次数
print(re.split(';|-|\+','a;b-c+d'))
print(re.split(';|-|\+','a;b-c+d',1))