f = open(‘test.txt‘,‘r‘) news = f.read() f.close() sep = ‘‘‘.,‘?!:"‘‘‘ exclude = {‘the‘,‘and‘,‘to‘,‘a‘,‘of‘,‘was‘,‘on‘,‘with‘,‘i‘,‘s‘,‘is‘,‘were‘,‘that‘,‘back‘,‘at‘,‘little‘,‘have‘} for w in sep: news = news.replace(w,‘ ‘) wordList = news.lower().split() wordDict = {} ‘‘‘ for v in wordList: wordDict[v] = wordDict.get(v, 0)+1 for v in exclude del( wordDict[v]) ‘‘‘ wordset = set(wordList) - exclude for v in wordset: wordDict[v] = wordList.count(v) dictList = list(wordDict.items()) dictList.sort(key=lambda x:x[1],reverse=True) for i in range(20): print(dictList[i]) f = open(‘newscount.txt‘,‘a‘) for i in range(25): f.write(dictList[i][0]+‘ ‘+str(dictList[i][1])+‘\n‘)
运行结果: