Python Re Library-----Learning (regular expression)

#!/usr/bin/env python#-*- coding:utf-8 -*-##################################################### # author: sunfx   [email protected]# last modified:  2014/11 /12  - 2014/11/13# filename:  re.py# q  q   Group:   236147801#################################################### #import  re#1. Find the characters in the text pattern =   ' This ' text =  ' Does this text match the pattern? ' Match = re.search (Pattern,text) S = match.start () e = match.end () print  ' Found   '%s ' \nin  '%s ' \nfrom %d to %d  ('%s ') '  %       (Match.re.pattern,match.string,s,e,text[s:e]) "match.re.pattern  to match the content match.string  match the characters s    Match to content start index d   match to content end index text[s:e]  match character ' #2. Compile expression regexes = [ re.compile (p)        &nbSp;    for p in [' This ' and ' that ']               ]  #把字符转换Regexobject格式print   ' text: %r\n '  %  text  #输出text内容for  regex in regexes:print  ' seeking  '%s '  %  regex.pattern,   #regex .pattern  to match the character If regex.search (text):  #在text中搜索this  or  thatprint  ' match! ' else:print  ' No match ' #3. Multiple match text =  ' abbaaabbbbaaaaa ' pattern =  ' ab ' For match  in re.findall (pattern,text):p rint  ' found:  '%s '  % match#findall  return string directly for  match in re.finditer (Pattern,text): S = match.start () e = match.end () print   ' found  '%s '  at %d:%d '  %  (text[s:e],s,e) #finditer   Return the original input text at the position of the string # #. Pattern Syntax def  test_patterns (text,patterns=[]):for pattern,desc in patterns: print  ' Pattern %r  (%s)  \n '  % (pattern,desc)  print  '    %r '  % textfor  match in re.finditer (Pattern,text): S = match.start () e = match.end () substr  = text[s:e]  #匹配到的字符n_backslashes  = text[:s].count (' \ \ ')   #查找文本: How many \prefix are included before the s-coordinate  =  '. '  *  ( s + n_backslashes )  print  '     %s%r '  %   (PREFIX,SUBSTR)  printreturntest_patterns (' Abbaaabbbbaaaaa ',             [(' ab ', ' ' A '  followed by  ' B ')]) #贪婪模式   This mode reduces the single match reduction '      *                  ' match once to multiple '      +                  ' match at least once to multiple '      ?                  ' matches only once '      ab*,               ' a followerd by  Zero or more b '),   #匹配0次或者更多次      ab+,               ' a followerd by one or  Mrore b '),   #最少匹配一次或者更多次      ab?,               ' a followerd by zero or one b '),     #匹配0最多一次      ab{3},             ' a followerd by three b '),           #最少匹配三次      ab{2,3},             ' A&NBSP;FOLLOWERD&NBsp;by two to three b ')     #匹配两至三次      ab*?,               ' A followerd by zero  or more b '),   #匹配0次或者更多次      ab+?,               ' A followerd by one or mrore  b '),   #最少匹配一次或者更多次      ab??,                ' a followerd by zero or one b '),     #匹配0最多一次      ab{3}?,             ' a followerd by three b '),           #最少匹配三次      ab{2,3}?,             ' a followerd&Nbsp;by two to three b ')     #匹配两至三次 ' #用法如下:str =  ' ABSDSDSDSDSD ' Print re.findall (' ab* ', str) #[' AB ']print re.findall (' ab*? ', str) #[' a '] #5. Character Set ' [ab]       ' either a or b  match A or B ' a[ab]+    ' a followerd by 1  more a or b  match A, B or multiple   ' a[ab]+?   ' a followerd by 1  or more a or b,not greedy  Match 11 times can match multiple ' [^]        ' does not contain content ' [a-z]     ' all lowercase ascii letters '  [A-Z]     ' all uppercase write ASCII letters '   [a-za-z]  ' a lowercase and uppercase sequence ' [a-za-z]  ' an uppercase lowercase sequence ' ' str = ' Aaaaaaaaaaaaaaaaaabbbbbbbbbbbbbbbbbbbbabbbbbbbbbbbasbsbab,a_baba ' Print re.findall (' [AB] ', str) print  Re.findall (' a[ab]+ ', str) print re.findall (' a[ab]+? ', str) print re.findall (' [^_] ', str) str =  ' China,love ' Print re.findall (' [a-z][a-z] ', str)   #['VE '] print re.findall (' [a-z][a-z] ', str)   #[' Ch ']print re.findall (' [a-z][a-z]+ ', str)  #[' China ']print re.findall (' [a-z][a-z]+ ', str)  #[' VE ']print re.findall (' [a-z][a-z]* ', str)  #[' China ',  ' E ']print re.findall (' [a-z][a-z]* ', str)  #[' h ',  ' i ',  ' n ',  ' a ',   ' l ',  ' o ',  ' VE ']print re.findall (' [a-z][a-z]? ', str)  #[' Ch ',  ' E ']print  Re.findall (' [a-z][a-z]? ', str)  #[' h ',  ' i ',  ' n ',  ' a ',  ' l ',  ' o ',  ' VE ' ".        metacharacters match one character A.b.a.*ba.*?b ' c =  ' WOAIZHONGGUOAWSB, Wasssssssssssssdsdsdsdbsdddddddbaaabbbbbbbsd ' Print re.findall (' A. ', c)   #[' ai ',  ' aw ',  ' as ',  ' AA ',  ' ab ']print re.findall (' B. ', c)   #[' B, ',  ' bs ',  ' ba ',  ' BB ',   ' BB ',  ' BB ',  ' BS ']print re.findall (' a.*b ', c)   #[' AIZHONGGUOAWSB, WASSSSSSSSSSSSSDSDSDSDBSDDDDDDDBAAABBBBBBB ']  #贪婪模式匹配a到Any character length between B characters print re.findall (' A.*?b ', c)   #[' AIZHONGGUOAWSB ',  ' asssssssssssssdsdsdsdb ',   ' Aaab '] #  end the greedy pattern of * ,                              # It's not going to go to the last B match and just get it, match the shortest possible character. Escape code ' escape code                                       meaning  \d                                       a digital  \D                                       a non-character  \s                                       whitespace characters (tabs, spaces, line breaks)  \S                                       non-whitespace characters (symbols, letters, numbers)  \w                                       Alpha-Numeric  \W                                       non-alphanumeric (symbol , tabs, spaces, line breaks) ' #7. Anchoring "anchor code &NBsp;                                meaning   ^                                 start of string or line   $                                 string or line end   \A                                string Start   \Z                                End of String   \b                               an empty string at the beginning or end of a word   \B                                not at the beginning of a word the empty string "#8. Limit search  match, searchtext =  ' this  is some text --with punctuation. ' pattern =  ' is ' print  ' text    : ',textprint  ' pattern: ', patternm =  re.match (pattern,text)     #因为match是从字符开头开始匹配  is not at the beginning so no match to .print  ' match : ' , M   s = re.search (pattern,text)   #is在文本中出现了两次所以匹配到内容print   ' search : ', Spattern = re.compile (R ' \b\w*is\w*\b ')   #编译规则print   ' Text: ',textpos = 0while   true:match = pattern.search (text,pos)   #搜索规则if &NBSP;NOT&NBSp;match:breaks = match.start () e = match.end ()  print  '   %d :  %d =  "%s" '  %  (S,e-1,text[s:e])  pos = e#9  User Group Resolution match ( Any one of the regular can be a group and nested in a larger expression) Regex = re.compile (R ' (\bt\w+) \w+ (\w+) ') print  ' Input  text       : ',textprint  ' pattern           : ', Regex.patternmatch = regex.search (text) print  ' entire match      : ', Match.group (0)   #表示整个表达式的字符串, sub-group sort print  ' world start with  "T" starting from 1: ', Match.group (1)   #匹配到的第一组print   ' world after  "T" &NBSP;WORD&NBSP;: ', Match.group (2)  # The second group matched to the #python extended the basic grouping   (? P<name>pattern) Print textprintfor pattern in [ r ' ^ (? p<first_word>\w+) ',                  r ' (? p<last_word>\w+) \s*$ ',                  r ' (? p<t_word>\bt\w+) \w+ (? p<other_word>\w+) ',                  r ' (? p<ends_with_t>\w+t) \b ',                  ]:    regex = re.compile (pattern)      match = regex.search (text)     print  ' matching  '%s '  %  pattern    print  '   ', match.groups ()     print  '   ', Match.groupdict ()     print

Continue to study in .....

This article is from the "brotherxing" blog, make sure to keep this source http://brotherxing.blog.51cto.com/3994225/1576216

Python Re Library-----Learning (regular expression)