#encoding:utf-8
import os
import re
def getPairStriList(filename):
  pairStrList = []
  textFile = open(filename, 'r')
  pattern = re.compile(u'.{3}\u56e0\u4e3a.*\u6240\u4ee5.{3}') #u'\u56e0\u4e3a和u'\u6240\u4ee5'分别为“因为”和“所以”的utf8码
  for line in textFile:
    utfLine = line.decode('utf8')
    result = pattern.search(utfLine)
    while result:
      resultStr = result.group()
      pairStrList.append(resultStr)
      result = pattern.search(resultStr,2,len(resultStr)-2)
  #对每个字符串进行格式转换和拼接  
  for i in range(len(pairStrList)):
    pairStrList[i] = pairStrList[i][:3] + pairStrList[i][3:5].replace(u'\u56e0\u4e3a',u' *\u56e0\u4e3a* ',1) + pairStrList[i][5:]
    pairStrList[i] = pairStrList[i][:len(pairStrList[i])-5] + pairStrList[i][len(pairStrList[i])-5:].replace(u'\u6240\u4ee5',u' &\u6240\u4ee5& ',1)
    pairStrList[i] = str(i+1) + ' ' + pairStrList[i]
  return pairStrList
  if __name__ == '__main__':
  pairStrList = getPairStriList('test.txt')
  for str in pairStrList:
    print str

#python 3.6 
#蔡军生  
#http://blog.csdn.net/caimouse/article/details/51749579 
# 
import re 
def test_patterns(text, patterns): 
  """Given source text and a list of patterns, look for 
  matches for each pattern within the text and print 
  them to stdout. 
  """ 
  # Look for each pattern in the text and print the results 
  for pattern, desc in patterns: 
    print('{!r} ({})\n'.format(pattern, desc)) 
    print(' {!r}'.format(text)) 
    for match in re.finditer(pattern, text): 
      s = match.start() 
      e = match.end() 
      prefix = ' ' * (s) 
      print( 
        ' {}{!r}{} '.format(prefix, 
                   text[s:e], 
                   ' ' * (len(text) - e)), 
        end=' ', 
      ) 
      print(match.groups()) 
      if match.groupdict(): 
        print('{}{}'.format( 
          ' ' * (len(text) - s), 
          match.groupdict()), 
        ) 
    print() 
  return 

#python 3.6 
#蔡军生  
#http://blog.csdn.net/caimouse/article/details/51749579 
# 
from re_test_patterns_groups import test_patterns 
test_patterns( 
  'abbaabbba', 
  [(r'a((a*)(b*))', 'a followed by 0-n a and 0-n b')], 
) 

'a((a*)(b*))' (a followed by 0-n a and 0-n b)
 'abbaabbba'
 'abb'    ('bb', '', 'bb')
   'aabbb'  ('abbb', 'a', 'bbb')
     'a' ('', '', '')