Python批次將csv檔案編碼方式轉換為UTF-8的實戰記錄

import pandas as pd
filename='222.csv'
try:
    df = pd.read_csv(filename, encoding='utf-8')
except BaseException:
    df = pd.read_csv(filename, encoding='cp950')
    df.to_csv(filename, encoding='utf-8', index=False)

import os
from chardet.universaldetector import UniversalDetector

def get_filelist(path):
    """
    獲取路徑下所有csv檔案的路徑列表
    """
    Filelist = []
    for home, dirs, files in os.walk(path):
        for filename in files:
            if ".csv" in filename:
                Filelist.append(os.path.join(home, filename))
    return Filelist

def read_file(file):
    """
    逐個讀取檔案的內容
    """
    with open(file, 'rb') as f:
        return f.read()

def get_encode_info(file):
    """
    逐個讀取檔案的編碼方式
    """
    with open(file, 'rb') as f:
        detector = UniversalDetector()
        for line in f.readlines():
            detector.feed(line)
            if detector.done:
                break
        detector.close()
        return detector.result['encoding']

def convert_encode2utf8(file, original_encode, des_encode):
    """
    將檔案的編碼方式轉換為utf-8，並寫入原先的檔案中。
    """    
    file_content = read_file(file)
    file_decode = file_content.decode(original_encode, 'ignore')
    file_encode = file_decode.encode(des_encode)
    with open(file, 'wb') as f:
        f.write(file_encode)

def read_and_convert(path):
    """
    讀取檔案並轉換
    """
    Filelist = get_filelist(path=path)
    fileNum= 0
    for filename in Filelist:
        try:
            file_content = read_file(filename)
            encode_info = get_encode_info(filename)
            if encode_info != 'utf-8':
                fileNum +=1
                convert_encode2utf8(filename, encode_info, 'utf-8')
                print('成功轉換 %s 個檔案 %s '%(fileNum,filename))
        except BaseException:
            print(filename,'存在問題，請檢查！')

def recheck_again(path):
    """
    再次判斷檔案是否為utf-8
    """    
    print('---------------------以下檔案仍存在問題---------------------')
    Filelist = get_filelist(path)
    for filename in Filelist:
        encode_info_ch = get_encode_info(filename)
        if encode_info_ch != 'utf-8':
            print(filename,'的編碼方式是：',encode_info_ch)

    print('--------------------------檢查結束--------------------------')
if __name__ == "__main__":
    """
    輸入檔案路徑
    """    
    path = './'
    read_and_convert(path)
    recheck_again(path)
    print('轉換結束！')

def get_encode_info(file):
    """
    逐個讀取檔案的編碼方式
    """
    with open(file, 'rb') as f:
        detector = UniversalDetector()
        for line in f.readlines():
            detector.feed(line)
            if detector.done:
                break
        detector.close()
        return detector.result['encoding']

Filelist = get_filelist(path=path)
fileNum= 0
for filename in Filelist:
    try:
        file_content = read_file(filename)
        encode_info = get_encode_info(filename)
        if encode_info != 'utf-8':
            fileNum +=1
            convert_encode2utf8(filename, encode_info, 'utf-8')
            print('成功轉換 %s 個檔案 %s '%(fileNum,filename))
            except BaseException:
                print(filename,'存在問題，請檢查！')