python二维数据读取对齐_文本对齐：使用python提取匹配序列

difflib.SequenceMatcher.get_matching_blocks完全符合您的要求.

import difflib

def sequ(s1, s2):

words1 = s1.split()

words2 = s2.split()

matcher = difflib.SequenceMatcher(a=words1, b=words2)

for block in matcher.get_matching_blocks():

if block.size == 0:

continue

yield ' '.join(words1[block.a:block.a+block.size])

txt1 = 'the heavy lorry crashed into the building at midnight'

txt2 = 'what a heavy lorry it is that crashed into the building'

print list(sequ(txt1, txt2))

输出：

['heavy lorry', 'crashed into the building']