背景
之前写过一个遍历文件夹进行处理的Python程序,但因为时间太久找不着了。。 导致只能自己再写一遍,于是决定将代码放置于博客之中,以便以后使用。
#!usr/bin/env python
#-*- coding:utf-8 -*-
import math
import os
import glob
import numpy as np
import jieba
import string
import jieba.analyse
def read_from_file(directions):
decode_set=[‘utf-8‘,‘gb18030‘,‘ISO-8859-2‘,‘gb2312‘,‘gbk‘,‘Error‘]#编码集
#编码集循环
for k in decode_set:
try:
file = open(directions,"r",encoding=k)
readfile = file.read()#这步如果解码失败就会引起错误,跳到except。
#print("open file %s with encoding %s" %(directions,k))#打印读取成功
#readfile = readfile.encode(encoding="utf-8",errors="replace")#若是混合编码则将不可编码的字符替换为"?"。
file.close()
break#打开路径成功跳出编码匹配
except:
if k=="Error":#如果碰到这个程序终止运行
raise Exception("%s had no way to decode"%directions)
continue
return readfile
filenames = []
filenames=glob.glob(r"C:/Users/Administrator/Documents/Tencent Files/937610520/FileRecv/TXT/*.txt")
filenameslen=len(filenames)
count=0
for filename in filenames:
print("%d : %d" %(count,filenameslen))
names=filename.find(‘TXT‘)+4
namee=filename.find(‘.txt‘)
f=open(filename,"rb")
content=f.readlines()
content=" ".join(‘%s‘ %id for id in content)
start=content.find(‘description‘)+16
overflow=content.find(‘comments‘)
end=content[start:].find(‘#‘)+start
if end>=overflow:
end=overflow
file = open(r"C:/Users/Administrator/Documents/Tencent Files/937610520/FileRecv/TXT/" +filename[names:namee]+‘keyword‘ + ‘.txt‘,‘w‘)
file_data = content[start:end]
#基于TF-IDF算法进行关键词抽取
tfidf=jieba.analyse.extract_tags
keywords=tfidf(file_data)
for i in range(len(keywords)):
if len(keywords)<=0:
print("error,please check your input")
break
file.write(keywords[i]+‘\n‘)
file.close()
count=count+1
print("%d : %d" %(count,filenameslen))
print("finished")
原文地址:https://www.cnblogs.com/harrysong666/p/10347124.html
时间: 2024-10-08 07:57:52