Excle文件编码方式类型转换

标题注释为文件格式

import csv

import chardet
import pandas as pd
# 定义输入和输出文件名
input_filename = 'input.csv'
output_filename = 'output.csv'
import codecs

# UTF-8格式
def convert_to_utf8(input_file, output_file, encoding='utf-8'):
    with codecs.open(input_file, 'r', encoding='original_encoding') as f:
        content = f.read()
    with codecs.open(output_file, 'w', encoding='utf-8') as f:
        f.write(content)
# 使用方法
# convert_to_utf8('input_file_path', 'output_file_path', encoding='original_encoding')
# with-BOM-UTF-8
def with_bom():
# 打开原始CSV文件和目标文件进行写入，指定编码为utf-8-sig
    with open(input_filename, 'r', encoding='utf-8-sig', newline='') as csvfile, codecs.open(output_filename, 'w','utf-8-sig') as out_csvfile:
        reader = csv.reader(csvfile)
        writer = csv.writer(out_csvfile)
        # 写入BOM头
        out_csvfile.write(codecs.BOM_UTF8.decode('utf-8'))

        # 复制内容到新文件，添加BOM头
        for row in reader:
            writer.writerow(row)
with_bom()
# GBK格式
def with_gbk():
    # 读取CSV文件，这里假设文件是UTF-8编码
    df = pd.read_csv(input_filename, encoding='utf-8')
    # 将编码转换为GBK
    df.to_csv(input_filename, index=False, encoding='gbk')
# with_gb2312
def with_gb2312():
    with open(input_filename, 'r', encoding='utf-8') as input_file,codecs.open(output_filename, 'w', 'gb2312') as output_file:
        # 创建CSV读取器
        reader = csv.reader(input_file)
        writer = csv.writer(output_file)
        # 读取并写入
        for row in reader:
            writer.writerow(row)
# with_gb2312()

#查看文件格式

def detect_csv_encoding(file_path):
    with open(file_path, 'rb') as f:
        data = f.read()
    return chardet.detect(data)['encoding']
# 使用函数
file_path = 'example.csv'  # 替换为你的CSV文件路径
encoding = detect_csv_encoding(file_path)
print(f"The encoding of the CSV file is: {encoding}")