CHARDET Archives - icodebroker

[PYTHON/CHARDET] detect 함수 : 텍스트 파일 인코딩 구하기

■ detect 함수를 사용해 텍스트 파일 인코딩을 구하는 방법을 보여준다. ▶ main.py


import chardet
import io
import os

def getEncoding(sourceFilePath):
    headerCount = min(32, os.path.getsize(sourceFilePath))

    sourceBufferedReader = open(sourceFilePath, "rb")

    headerBytes = sourceBufferedReader.read(headerCount)

    resultDictionary = chardet.detect(headerBytes)

    encoding = resultDictionary["encoding"]

    return encoding.lower()

print(getEncoding("source.txt"))
print(getEncoding("target.txt"))

"""
utf-8-sig
utf-8
"""

import chardet

import io

import os

def getEncoding(sourceFilePath):

headerCount = min(32, os.path.getsize(sourceFilePath))

sourceBufferedReader = open(sourceFilePath, "rb")

headerBytes = sourceBufferedReader.read(headerCount)

resultDictionary = chardet.detect(headerBytes)

encoding = resultDictionary["encoding"]

return encoding.lower()

print(getEncoding("source.txt"))

print(getEncoding("target.txt"))

"""

utf-8-sig

utf-8

"""

▶ requirements.txt


chardet==5.2.0

chardet==5.2.0

※ pip install chardet 명령을 실행했다.