用于解析xml文件和对UUID排序的Python脚本

Question

下面是python脚本，我必须对多个.xml文件的UUID进行排序：

import os
import lxml.etree as ET

inputpath = 
xsltfile = 
outpath = 

dir = []

for dirpath, dirnames, filenames in os.walk(inputpath):
    structure = os.path.join(outpath, dirpath[len(inputpath):])
    if not os.path.isdir(structure):
        os.mkdir(structure)
    for filename in filenames:
        if filename.endswith(('.xml')):
            dir = os.path.join(dirpath, filename)
            print(dir)
            dom = ET.parse(dir)
            xslt = ET.parse(xsltfile)
            transform = ET.XSLT(xslt)
            newdom = transform(dom)
            outfile = open(structure + "\\" + filename, 'a', encoding="utf-8")
            outfile.write(ET.tostring(newdom,pretty_print=True,xml_declaration=True,standalone='yes').decode())

我在尝试解析多个.xml文件时看到这个错误

Traceback (most recent call last):
  File "python.py", line 23, in <module>
outfile.write(ET.tostring(newdom,pretty_print=True,xml_declaration=True,encoding='UTF-8',standalone='yes').decode())
  File "C:\Program Files\Python38\lib\encodings\cp1252.py", line 19, in encode
    return codecs.charmap_encode(input,self.errors,encoding_table)[0]
UnicodeEncodeError: 'charmap' codec can't encode characters in position 19935-19939: character maps to <undefined>

仅当我在py文件中传递encoding='UTF-8'时，才会出现上述错误

Answer 1

下面是运行良好的python代码

import os
import lxml.etree as ET
import sys


inputpath = "C:\\projects\\xmlformat\\uuid\\"
xsltfile = "C:\\projects\\xmlformat\\uuid\\uuid.xslt"
outpath = "C:\\projects\\xmlformat\\output"

dir = []

if sys.version_info[0] >= 3:
    unicode = str

for dirpath, dirnames, filenames in os.walk(inputpath):
    structure = os.path.join(outpath, dirpath[len(inputpath):])
    if not os.path.isdir(structure):
        os.mkdir(structure)
    for filename in filenames:
        if filename.endswith(('.xml')):
            dir = os.path.join(dirpath, filename)
            print(dir)
            dom = ET.parse(dir)
            xslt = ET.parse(xsltfile)
            transform = ET.XSLT(xslt)
            newdom = transform(dom)
            infile = unicode(ET.tostring(newdom, pretty_print=True,xml_declaration=True,standalone='yes',encoding="UTF-8").decode())
            outfile = open(structure + "\\" + filename, 'a',encoding="UTF-8")
            outfile.write(infile)