1.首先你要有一个原始文本，
2.写一段python
#!/usr/粗心的小蜜蜂/python3# -*- coding:utf-8 -*-# @Time:2018/8/24 9:37# @Author: wardseptember# @File: CountHighFrequencyWords.pyimport reexcludes = ['1','c','1.','2.','b','d','a','10', '2','12.','13.','29.','3.','4.','5.','6.','7.','8.','9.','10.','11.','14.', '15.']#自行过滤简单词，太多了不写了#替换字符def ReplaceTxt( ifile ): ifile = ifile.lower() for ch in '1234567890!"@#$%^&*()+,-./:;<=>?@[]_`~{|}"': #替换特殊字符 ifile = ifile.replace(ch, ' ') return ifile#1. 打开总的文件EngTxt = ReplaceTxt(open('3.txt').read())#with open('o3.txt','w') as f: # f.write(EngTxt)# f.close()#2.打开多个单独文件listTxt = [] ##创建空列表listTxt.append(ReplaceTxt(open('09-05.txt').read()))listTxt.append(ReplaceTxt(open('10-11.txt').read()))listTxt.append(ReplaceTxt(open('11-05.txt').read()))listTxt.append(ReplaceTxt(open('11-11.txt').read()))listTxt.append(ReplaceTxt(open('12-05.txt').read()))listTxt.append(ReplaceTxt(open('12-11.txt').read()))listTxt.append(ReplaceTxt(open('13-05.txt').read()))listTxt.append(ReplaceTxt(open('13-11.txt').read()))listTxt.append(ReplaceTxt(open('14-05.txt').read()))listTxt.append(ReplaceTxt(open('14-11.txt').read()))listTxt.append(ReplaceTxt(open('15-05.txt').read()))listTxt.append(ReplaceTxt(open('15-11.txt').read()))listTxt.append(ReplaceTxt(open('16-05.txt').read()))listTxt.append(ReplaceTxt(open('16-11.txt').read()))listTxt.append(ReplaceTxt(open('17-05.txt').read()))listTxt.append(ReplaceTxt(open('17-11.txt').read()))#1.获取单词#EngTxt = getTxt()#3.切割为列表格式txtarrlist = [] txtArr = EngTxt.split()for i in range(0,16): txtarrlist.append(listTxt[i].split())#4.遍历统计counts = {}for word in txtArr: flag=True for word1 in excludes: if word==word1: flag=False else: continue if flag is True: counts[word] = counts.get(word, 0) + 1 else: continue#4.转换格式，方便打印，将字典转换为列表countsList = list(counts.items())countsList.sort(key=lambda x:x[1], reverse=True)#按次数从大到小排序#5.在子文件查找outlist = [] ## 输出列表with open('to6.txt','a+') as f6: for word,count in countsList: cnt = 0 str1 = word for i in range(0,16): if word in txtarrlist[i]: cnt = cnt + 1 else: str1 += " " + str(i) f6.writelines(str1+'n') if cnt > 0: outlist.append((word,cnt)) #按次数从大到小排序 outlist.sort(key=lambda x:x[1], reverse=True) f6.close()#6.打印输出n = 1for word,count in outlist: with open('o5.txt','a+') as f: if ( len(word) + len(str(n)) ) < 6 : str1=str(n) + ', ' + word+'tt'+str(count)+ ' ' else: str1=str(n) + ', ' + word+'t'+str(count)+ ' ' f.writelines(str1+'n') f.close() n = n + 13.找到字典放入excel表
这里引用的是初中1600和三级词汇大纲
4，通过vlookup函数导出词汇意思
5，排序完成
下载链接