[Python知识库]python 统计小说词数（完整，无bug，优化版）

import os

with open('DouJuan', encoding='utf-8') as file_obj:
    contents = file_obj.read()
    print(contents)

string = contents.lower()
string = string.replace("\n"," ")

# 删除字符串内除了字母与空格的字符 例如@#$%^&*()_+:<>.|}""?这些特殊符号
newstring = ""

for i in string:
    if((i >= 'a' and i <='z') or i == ' '):
        newstring += i

# print(newstring)
        
words = newstring.split(sep=' ')

#虚词数组，用于存放虚词这种没有统计意义的词，再用于过滤掉这些词
FunctionWord = [""," ","the","a","an","and","of","to","in","at","but","as","with","or"]
# print(words)

statisticsWords = ["start"]
for i in words:
    if(not(i in FunctionWord)):
        statisticsWords.append(i)
print(statisticsWords)

print(type(words))

# 统计单词个数并存到字典中
wordsDict = {}
for i in statisticsWords:
    if(not(i in wordsDict.keys())):
        wordsDict[i] = 1
    else:
        wordsDict[i] += 1
print(wordsDict)

# z=zip(wordsDict.values(),wordsDict.keys())
# sorted(z)
wordsDict = sorted(wordsDict.items(),key=lambda x:x[1],reverse=True)

statisticsDescirbe = ""
for i in wordsDict:
    statisticsDescirbe += str(i[0]) + " : " + str(i[1]) + '\n'
print(statisticsDescirbe)

with open("/root/test1/XXXXXXXXXXXX","w") as file_object:
    file_object.write(statisticsDescirbe)
print("done")