python 正则表达式

　　内容来自text process in python
　　re_show.py import re
　　def re_show(pat, s):
　　print re.compile(pat, re.M).sub("{\g}", s.rstrip()),'\n'
　　s = '''Mary had a little lamb
　　And everywhere that Mary
　　went, the lamb was sure
　　to go'''
　　re_show('a', s)
　　M{a}ry h{a}d {a} little l{a}mb.
　　And everywhere th{a}t M{a}ry
　　went, the l{a}mb w{a}s sure
　　to go. >>> from re_show import re_show
　　>>> s = '''Special characters must be escaped.*'''
　　>>> re_show(r'.*', s)
　　>>> re_show(r'\.\*', s)
　　>>> re_show('\\\\', r'Python \ escaped \ pattern')
　　>>> re_show(r'\\', r'Regex \ escaped \ pattern')
　　>>> re_show(r'^Mary', s)
　　>>> re_show(r'Mary$', s)
　　>>> re_show(r'$','Mary had a little lamb')
　　>>> re_show(r'.a', s)
　　>>> re_show(r'(Mary)( )(had)', s)
　　>>> re_show(r'\(.*\)', 'spam (and eggs)')
　　>>> re_show(r'[a-z]a', s)
　　>>> re_show(r'[^a-z]a', s)
　　>>> s2 = 'The pet store sold cats, dogs, and birds.'
　　>>> re_show(r'cat|dog|bird', s2)
　　>>> s3 = '=first first= # =second second= # =first= # =second='
　　>>> re_show(r'=first|second=', s3)
　　>>> re_show(r'(=)(first)|(second)(=)', s3)
　　>>> re_show(r'=(first|second)=', s3)
　　>>> s = '''Match with zero in the middle: @@
　　... Subexpression occurs, but...: @=!=ABC@
　　... Lots of occurrences: @=!==!==!==!==!=@
　　... Must repeat entire pattern: @=!==!=!==!=@'''
　　>>> re_show(r'@(=!=)*@', s)
　　>>> s = '''AAAD ... ABBBBCD ... BBBCD ... ABCCD ... AAABBBC'''
　　>>> re_show(r'A+B*C?D', s)
　　>>> s2 = '''aaaaa bbbbb ccccc ... aaa bbb ccc ... aaaaa bbbbbbbbbbbbbb ccccc'''
　　>>> re_show(r'a{5} b{,6} c{4,8}', s2)
　　>>> re_show(r'a+ b{3,} c?', s2)
　　>>> re_show(r'a{5} b{6,} c{4,8}', s2)
　　>>> s2 = '''jkl abc xyz
　　... jkl xyz abc
　　... jkl abc abc
　　... jkl xyz xyz
　　... '''
　　>>> re_show(r'(abc|xyz) \1', s2)
　　>>> re_show(r'(abc|xyz) (abc|xyz)', s2)
　　>>> re_show(r'(?Pabc|xyz) (?P=let3)', s2)
　　>>> s2 = '''-- I want to match the words that start ... -- with 'th' and end with 's'. ... this ... thus ... thistle ... this line matches too much ... ''' >>> re_show(r'th.*s', s2)
　　>>> s2 = '''-- I want to match the words that start ... -- with 'th' and end with 's'. ... this ... thus ... thistle ... this line matches too much ... ''' >>> re_show(r'th[^s]*.', s2)
　　>>> re.search(r'(?Li)cat','The Cat in the Hat').start()
　　>>> re.search(r'cat','The Cat in the Hat',re.L|re.I).start() s = '''-- I want to match the words that start ... -- with 'th' and end with 's'. ... this line matches just right ... this # thus # thistle''' >>> re_show(r'th.*s',s) >>> re_show(r'th.*?s',s) >>> s = 'A-xyz-37 # B:abcd:142 # C-wxy-66 # D-qrs-93' >>> re_new(r'([A-Z])(?:-[a-z]{3}-)([0-9]*)', r'\1\2', s) >>> re_new(r'([A-Z])(-[a-z]{3}-)([0-9]*)', r'\1\2', s) >>> s = "A-xyz-37 # B:abcd:142 # C-wxy-66 # D-qrs-93" >>> re_new(r'(?P[A-Z])(-[a-z]{3}-)(?P[0-9]*)', r'\g\g',s) >>> s = 'A-xyz37 # B-ab6142 # C-Wxy66 # D-qrs93' >>> # Assert that three lowercase letters occur after CAP-DASH >>> re_new(r'([A-Z]-)(?=[a-z]{3})([\w\d]*)', r'\2\1', s) >>> # Assert three lowercase letts do NOT occur after CAP-DASH ... >>> re_new(r'([A-Z]-)(?![a-z]{3})([\w\d]*)', r'\2\1', s) >>> re_show('Man', 'Manhandled by The Man') >>> re_show('(?<!The )Man', 'Manhandled by The Man')