python读取txt， jieba分词并统计词频后输出结果到Excel和txt文档

1 2 3 4 5

open('1.txt''r') as fp: =fp.readlines() =[line.split()[1][9forinlines] open('out.txt''w+') as out: out.write('\n'.join(res))

#encoding=utf-8
import jieba
import jieba.posseg as pseg
import re
filename='result.txt'
fileneedCut='test.txt'
fn=open(fileneedCut,"r")
f=open(filename,"w+")
for line in fn.readlines():



f.close()

fn.close()

1. import
4. sys.setdefaultencoding('utf-8'
6. import
7. import
8. import#写入Excel表的库
10. if"__main__"
12. 'ascii'
13. "wordCount")#Excel单元格名字
16. forin'1.txt'):#1.txt是需要分词统计的文档
18. '\n\r').split('\t'#制表格切分
20. 0#jieba分词
21. forin
25. "wordCount.txt",'w'#打开文件
27. forin
28. ifnotin#统计数量
29. 1
30. else
31. 1
34. True
36. forin
37. forin
38. if
39. +str(word_dict[key])+'\n'#写入txt文档
41. 0
44. forin
45. 1
46. 0
47. 'wordCount.xls'

1.txt是你需要分词统计的文本内容，最后会生成wordCount.txt和wordCount.xls两个文件。下图是最后结果

文章来源: python读取txt， jieba分词并统计词频后输出结果到Excel和txt文档