[Python知识库]tsv文件删除带中文的行，awk命令

awk -F "[\t$]" '{if (substr($2, i, 1) > "\177"){}else{print $0}}' train.tsv >result.tsv

awk -F "[\t$]" '{if (substr($2, i, 1) > "\177"){}else{print $0}}' train.tsv >result.tsv

import re

lineList = []
matchPattern = re.compile(r'[\u4e00-\u9fa5]+')
file = open('E:\\Chrome_download\\math-formula-recognition-master\\train.tsv','r',encoding='UTF-8')
while 1:
    line = file.readline()
    if not line:
        print("Read file End or Error")
        break
    elif matchPattern.search(line):
        pass
    else:
        lineList.append(line)
file.close()
file = open(r'E:\\Chrome_download\\math-formula-recognition-master\\result.tsv', 'w',encoding='UTF-8')
for i in lineList:
    file.write(i)
file.close()