Python 合并多个TXT文件并统计词频的实现

 # coding=utf-8 import re import os # 获取源文件夹的路径下的所有文件 sourceFileDir = 'D:\\Python\\txt\\' filenames = os.listdir(sourceFileDir) # 打开当前目录下的 result.txt 文件，如果没有则创建 # 文件也可以是其他类型的格式，如 result.js file = open('D:\\Python\\result.txt', 'w') # 遍历文件 for filename in filenames: filepath = sourceFileDir+'\\'+filename # 遍历单个文件，读取行数，写入内容 for line in open(filepath): file.writelines(line) file.write('\n') # 关闭文件 file.close() # 获取单词函数定义 def getTxt(): txt = open('result.txt').read() txt = txt.lower() txt = txt.replace(''', '\'') # !"@#$%^&*()+,-./:;<=>?@[\\]_`~{|} for ch in '!"'@#$%^&*()+,-/:;<=>?@[\\]_`~{|}': txt.replace(ch, ' ') return txt # 1.获取单词 hamletTxt = getTxt() # 2.切割为列表格式，'' 兼容符号错误情况，只保留英文单词 txtArr = re.findall('[a-z\''A-Z]+', hamletTxt) # 3.去除所有遍历统计 counts = {} for word in txtArr: # 去掉一些常见无价值词 forbinArr = ['a.', 'the', 'a', 'i'] if word not in forbinArr: counts[word] = counts.get(word, 0) + 1 # 4.转换格式，方便打印，将字典转换为列表，次数按从大到小排序 countsList = list(counts.items()) countsList.sort(key=lambda x: x[1], reverse=True) # 5. 输出结果 for i in range(10): word, count = countsList[i] print('{0:<10}{1:>5}'.format(word, count)) 

 # coding=utf-8 from collections import Counter # words 为读取到的结果 list words = ['a', 'b' ,'a', 'c', 'v', '4', ',', 'w', 'y', 'y', 'u', 'y', 'r', 't', 'w'] wordCounter = Counter(words) print(wordCounter.most_common(10)) # output: [('y', 3), ('a', 2), ('w', 2), ('b', 1), ('c', 1), ('v', 1), ('4', 1), (',', 1), ('u', 1), ('r', 1)]