noname.py

# encoding=utf-8

import re


s = """It was a very cold evening, an old man was waiting for a ride across the river. He saw several horsemen pass by but he didn’t ask for any help. The wait seemed __1__(end)．Then came another rider,the old man __2__(catch) his eye and said, “Sir, would you mind doing me a favor？”
	Stopping his horse,he replied, “Of course.” Almost __3__(freeze), the old man could not get __4__ the ground. The horseman helped him onto his horse. He took the old man not just across the river,__5__ to his home.
	“Sir, you didn’t even ask the other riders for help, why? What __6__ I had said ‘no’ and left you there？” the horseman asked.
	The old man looked at him straight in the eyes and said, “I looked into their eyes, I found they didn’t care,__7__ told me it would be useless, but when I looked into __8__，I saw kindness.”
	These words touched the rider deeply. “Thank you for __9__ you’ve said, I hope I will never be too busy to help others.” with that, Thomas Jefferson, the __10__(three) president of the US, turned his horse around and went away."""


def parse(str):
	ret = []
	words = str.replace('，', ',').replace('．', '.').replace('？', '?').replace(';',' ').replace(',',' ').replace('.', ' ').replace('“', ' ').replace('”', ' ').replace('"', ' ').replace('’', '\'').replace('‘', '\'').replace('?', ' ').replace('\'', ' ').replace('\n', ' ').replace('\t', ' ').split(' ')
	key = 0
	for w in words:
		if len(w):
			if (w.startswith('_')):
				key += 1
				if (w.endswith(')')):
					ret.append([re.match(r".+(.+)", w).group(0)])
				else:
					ret.append([w, key])
			else:
				ret.append([w, 0])
	print ret
		


parse(s)