python3读取windows下的utf-8等编码格式的文本文件

在windows下，创建一个文本,默认的编码是: ANSI, 用python3的open()方法读取这样的文本很方便

直接用:

f = open("sample.txt","r")

text = f.read()

 

就能直接读到。但是如果存为 utf-8等其他的编码就会出现读取错误。

windows下的utf-8编码格式的文本有3个字节的BOM头, 在python3中对应codecs.BOM_UTF8。

整理了用python3读取windows下4中编码格式的文本的module作为学习。

读取模块:WinTxtReader.py 

#!/usr/bin/env python3

#encoding=utf-8

import codecs

"这个模块用于读取widons下的文本文件,windows下的文本文件会存为\

(ANSI, utf-8, unicode, unicode big endian)4种编码格式\

这个模块就用于读取这4种格式的文本"

name = "WinTxtReader"

version = "1.0"

author = "vily"

email = "vily313@126.com"



def readUTF8(f_url):

    try:

        f = codecs.open(f_url)

    except IOError as err:

        print("In function readUTF8, ",err)

        return ""

    txt = f.read()

    f.close()

    if txt[:3]==codecs.BOM_UTF8:

        txt = txt[3:].decode("utf-8")

        return txt

    return ""



def readANSI(f_url):

    try:

        f = open(f_url,"r")

    except IOError as err:

        print("In function readANSI, ",err)

        return ""

    txt = f.read()

    return txt

def readUNICODE(f_url):

    try:

        f = codecs.open(f_url)

    except IOError as err:

        print("In function readUNICODE, ",err)

        return ""

    txt = f.read()

    f.close()

    try:

        txt = txt.decode("utf-16")

        return txt

    except UnicodeDecodeError as err:

        print("In function readUNICODE, ",err)

        return ""

def readUBE(f_url):    

    return readUNICODE(f_url)



# 自动选择读取这四种编码格式的

def readTxt(f_url):

    try:

        f = open(f_url,"rb")

    except IOError as err:

        print("In function readTxt, ",err)

        return ""

    bytes = f.read()

    f.close()

    if bytes[:3] == codecs.BOM_UTF8:

        return bytes[3:].decode("utf-8")

    else:

        # 先当作 ansi 编码解码

        try:

            txt = bytes.decode("gb2312")

            #print("当作 ansi 编码解码")

            return txt

        except UnicodeDecodeError as err:

            # 再当作unicode 编码解码

            try:

                txt = bytes.decode("utf-16")

                #print("当作 unicode 编码解码")

                return txt

            except UnicodeDecodeError as err:

                print("In function readTxt, ",err)

                return ""

测试代码:

 #这是测试代码...

#!/usr/bin/env python3
import WinTxtReader
txtUrl_a = "hello_utf8.txt"
text = WinTxtReader.readUTF8(txtUrl_a)
print("utf-8 txt:",text)

txtUrl_b = "hello_ansi.txt"
text = WinTxtReader.readANSI(txtUrl_b)
print("ansi txt:",text)

txtUrl_c = "hello_unicode.txt"
text = WinTxtReader.readUNICODE(txtUrl_c)
print("unicode txt:",text)

txtUrl_d = "hello_ube.txt"
text = WinTxtReader.readUBE(txtUrl_d)
print("unicode big endian txt:",text)

print("----------------------")
text = WinTxtReader.readTxt(txtUrl_d)
print("read ",txtUrl_d,":",text)