python遍歷文件進行數據處理

背景

之前寫過一個遍歷文件夾進行處理的Python程序，但因為時間太久找不着了。。 導致只能自己再寫一遍，於是決定將代碼放置於博客之中，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']#編碼集
    #編碼集循環
    for k in decode_set:
        try:
            file = open(directions,"r",encoding=k)
            readfile = file.read()#這步如果解碼失敗就會引起錯誤，跳到except。
            
            #print("open file %s with encoding %s" %(directions,k))#打印讀取成功
            #readfile = readfile.encode(encoding="utf-8",errors="replace")#若是混合編碼則將不可編碼的字符替換為"?"。
            file.close()
            break#打開路徑成功跳出編碼匹配
        except:
            if k=="Error":#如果碰到這個程序終止運行
                raise Exception("%s had no way to decode"%directions)
            continue
    return readfile

filenames = []
filenames=glob.glob(r"C:/Users/Administrator/Documents/Tencent Files/9/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/9/FileRecv/TXT/" +filename[names:namee]+'keyword' + '.txt','w')
    
    file_data = content[start:end]
    #基於TF-IDF算法進行關鍵詞抽取
    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")