Python统计文本词汇出现次数的实例代码

open_file=open("text.txt")
file_txt=open_file.read()

def wordcount(readtxt):
readlist = readtxt.split()
dict1={}
for every_world in readlist:
if every_world in dict1:
dict1[every_world] += 1
else:
dict1[every_world] = 1
return dict1
print(wordcount(file_txt))

#coding=utf-8
__author__ = 'zcg'
import collections
import os
with open('abc.txt') as file1:#打开文本文件
 str1=file1.read().split(' ')#将文章按照空格划分开
print "原文本:\n %s"% str1
print "\n各单词出现的次数：\n %s" % collections.Counter(str1)
print collections.Counter(str1)['a']#以字典的形式存储，每个字符对应的键值就是在文本中出现的次数

__author__ = 'zcg'
#endcoding utf-8
import string,random
field=string.letters+string.digits
def getRandom():
 return "".join(random.sample(field,4))
def concatenate(group):
 return "-".join([getRandom() for i in range(group)])
def generate(n):
 return [concatenate(4) for i in range(n)]
if __name__ =='__main__':
 print generate(10)

__author__ = 'Administrator'
import xlrd
workbook = xlrd.open_workbook('config.xlsx')
print "There are {} sheets in the workbook".format(workbook.nsheets)
for booksheet in workbook.sheets():
 for col in xrange(booksheet.ncols):
 for row in xrange(booksheet.nrows):
 value=booksheet.cell(row,col).value
 print value

#coding=utf-8
__author__ = 'zcg'
#2017 9/26
import xlrd
fileOutput = open('Configs.lua','w')
writeData="--@author:zcg\n\n\n"
workbook = xlrd.open_workbook('config.xlsx')
print "There are {} sheets in the workbook".format(workbook.nsheets)
for booksheet in workbook.sheets():
 writeData = writeData+'AT' +booksheet.name+' ={\n'
 for col in xrange(booksheet.ncols):
 for row in xrange(booksheet.nrows):
 value = booksheet.cell(row,col).value
 if row ==0:
 writeData = writeData+'\t'+'["'+value+'"]'+'='+'{'
 else:
 writeData=writeData+'"'+str(booksheet.cell(row,col).value)+'", '
 else:
 writeData=writeData+'},\n'
 else:
 writeData=writeData+'}\n\n'
else :
 fileOutput.write(writeData)
fileOutput.close()