import re, collections from cppy.cp_util import stopwordfilepath,testfilepath stopwords = set(open( stopwordfilepath,encoding = 'utf8' ).read().split(',')) words = re.findall('[a-z]{2,}', open( testfilepath,encoding = 'utf8').read().lower()) counts = collections.Counter( w for w in words if w not in stopwords ) for (w, c) in counts.most_common(10) : print(w, '-', c) ''' 熟练的软件工程师,会如此简单完成任务 后面的例子,我们必须变的啰嗦一些,不能用这种太 hacker 的写法 '''