python读取csv文件报错UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc9 in position 0: invalid co...

今天要处理大量的csv文件，出现UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc9 in position 0: invalid continuation byte 报错，于是统一将文件转为utf-8编码，代码如下：

# 将编码转化为utf-8编码

def change_code(original_file, newfile):

files = os.listdir(original_file)

for namein files:

original_path = original_file +'\\' + name

f =open(original_path, 'rb+')

content = f.read()

source_encoding ='utf-8'

        try:

content.decode('utf-8').encode('utf-8')

source_encoding ='utf-8'

        except:

try:

content.decode('gbk').encode('utf-8')

source_encoding ='gbk'

            except:

try:

content.decode('gb2312').encode('utf-8')

source_encoding ='gb2312'

                except:

try:

content.decode('gb18030').encode('utf-8')

source_encoding ='gb18030'

                    except:

try:

content.decode('big5').encode('utf-8')

source_encoding ='gb18030'

                        except:

content.decode('cp936').encode('utf-8')

source_encoding ='cp936'

        f.close()

# 按照确定的encoding读取文件内容，并另存为utf-8编码：

        block_size =4096

        with codecs.open(original_path, 'r', source_encoding)as f:

newfile_path = newfile +'\\' + name

with codecs.open(newfile_path, 'w', 'utf-8')as f2:

while True:

content = f.read(block_size)

if not content:

break

                    f2.write(content)