今天写一个脚本文件,需要将多个文件中的内容汇总到一个txt文件中,由于多个文件有三种不同的编码方式,读写出现错误,先将解决方法记录如下:
今天写一个脚本文件,需要将多个文件中的内容汇总到一个txt文件中,由于多个文件有三种不同的编码方式,读写出现错误,先将解决方法记录如下:
# -*- coding: utf-8 -*-
import wave
import pylab as pl
import numpy as np
import pandas as pd
import os
import time
import datetime
import arrow
import chardet
import sys
reload(sys)
sys.setdefaultencoding('utf8')
os.chdir("F:/new_srt")
#get words of srt file
###########################################
def get_word():
path = "F:/new_srt"
filelist = os.listdir(path)
for files in filelist:
print files
encoding = chardet.detect(open(files,'r').read())['encoding']
if encoding == 'utf-8':
data=pd.read_csv(files,encoding="utf-8",sep='\r',header=None)
elif encoding == 'GB2312':
try:
data=pd.read_csv(files,encoding="gbk",sep='\r',header=None)
except UnicodeDecodeError:
data=pd.read_csv(files,encoding="utf-8",sep='\r',header=None)
elif encoding == 'UTF-8-SIG':
data=pd.read_csv(files,encoding="UTF-8-SIG",sep='\r',header=None)
else:
print 'this is an error about %s' % files
data_new=pd.DataFrame(np.reshape(data.values, (-1,3)))
data_new.columns=['index','timecut','content']
filename = os.path.splitext(files)[0] #filetype = os.path.splitext(files)[1]
with open('F:/result.txt', 'a') as file:
file.write(str(filename)+' ' )
for item in data_new['content']:
file.write(item.decode("utf-8") +' ') #s=s.decode("utf-8")
file.write('\n')
if __name__ == '__main__':
get_word()