#Python系列#--自然语言处理之langid对文本语言检测识别

pip install langid

#!/usr/bin/python
# _*_ coding:utf-8 _*_
# author: robinn

import langid

def inputoutput(infile,outfile):
    infilestr = ""
    f_out = open(outfile, "w")
    with open(infile, "r") as f:
        for line in f:
            linestr = line.strip()
            langidstr = langid.classify(linestr)
            if langidstr[0] == "en":
                continue
            f_out.write(linestr+"\n")
        f_out.close()

if __name__ == "__main__":
    inputoutput("inputfile.txt","outputfile.txt")