原文連結

#!/usr/bin/env python
#-*- coding:utf-8 -*-
#author: Enoch time:2018/10/30 0030

import re
import time
from collections import Counter
import os
import sys
import cProfile

###################################################################################
#Name:count_words
#Inputs:file name,the first n words, stopfile name
#outputs:None
#Author: Thomas
#Date:2018.10.22
###################################################################################
def CountPhrases(file_name,k):

    totalNum = 0

    t0 = time.clock()
    with open(file_name) as f:
        txt = f.read()
    txt = txt.lower()
    txt = re.sub(r'\s+',' ',txt)
    pword = r'(([a-z]+ )+[a-z]+)'  # extract sentence
    pattern = re.compile(pword)
    sentence = pattern.findall(txt)
    txt = ','.join([sentence[m][0] for m in range(len(sentence))])

    pattern = "[a-z]+[0-9]*"
    for i in range(k-1):
        pattern += "[\s|,][a-z]+[0-9]*"
    wordList = []
    for i in range(k):
        if( i == 0 ):
            tempList = re.findall(pattern, txt)
        else:
            wordpattern = "[a-z]+[0-9]*"
            txt = re.sub(wordpattern, '', txt, 1).strip()
            tempList = re.findall(pattern, txt)
        wordList += tempList
    tempc = Counter(wordList)

    dicNum = {}
    phrases = tempc.keys()
    for phrase in phrases:
        if (',' not in phrase):
            dicNum[phrase] = tempc[phrase]
            totalNum += tempc[phrase]
    dicNum = sorted(dicNum.items(), key=lambda k: k[0])
    dicNum = sorted(dicNum, key=lambda k: k[1], reverse=True)
    t1 = time.clock()

    for letter, fre in dicNum[:2]:
        print("|\t{:15}|{:<11.2%}|".format(letter, fre / totalNum))
    print(t1 - t0)


CountPhrases('../gone_with_the_wind.txt', 2)