使用python写xml

工作中需要把PPOCRLabel标注格式转化成需要的xml格式。

遇到的问题：1、之前只使用过使用minidom读xml，还没有使用过minidom写xml。2、minidom写xml顺序与写入的顺序不一致问题。

minidom源码在我本地路径：D:\Anaconda3\Lib\xml\dom\minidom.py

参考：Python3.7写入xml文件 保持节点属性顺序不变

首先导入模块 from xml.dom.minidom import Document,然后按下ctrl 使用鼠标点击minidom进入源码

ctrl+F 搜索 a_names = sorted(attrs.keys())。然后注释掉

添加 a_names = attrs.keys()  不使用排序

 

下面是我的PPOCRLabel标注格式转化成需要的xml格式的代码。

# -*- coding : UTF-8 -*-
# @file   : conver_json_icdar.py
# @Time   : 2021/4/9 11:24
# @Author : wmz

import os
import json
import xml.dom.minidom as minidom


def json_2_icdar(js_path, ic_path):
    with open(js_path, 'r', encoding='utf-8') as f:
        for line in f.readlines():
            print(line)
            content = line.split('\t')
            print(content[0])
            txt_file = str(content[0]).replace('jpg', 'txt')
            dst_file = os.path.join(ic_path, txt_file)
            # write file
            file_lineinfo = open(dst_file, 'w', encoding='utf-8')
            list_dict = json.loads(content[1])
            nsize = len(list_dict)
            print(nsize)
            for i in range(nsize):
                print(list_dict[i])
                lin = list_dict[i]
                info = lin['transcription']
                points = lin['points']
                points = [int(y) for x in points for y in x]
                pts = ','.join(map(str, points))
                lineinfo = pts + ',' + info + '\n'
                file_lineinfo.write(lineinfo)
            file_lineinfo.close()


def json_2_xml(js_path, xml_path):
    with open(js_path, 'r', encoding='utf-8') as f:
        for line in f.readlines():
            print(line)
            content = line.split('\t')
            print(content[0])
            xml_file = str(content[0]).replace('jpg', 'xml')
            dst_xml_file = os.path.join(xml_path, xml_file)
            # txt_file = str(content[0]).replace('jpg', 'txt')
            # dst_file = os.path.join(xml_path, txt_file)
            # write file
            # 1.创建DOM树对象
            dom = minidom.Document()
            # 2.创建根节点。每次都要用DOM对象来创建任何节点。
            root_node = dom.createElement('ImageInfo')
            # 3.用DOM对象添加根节点
            dom.appendChild(root_node)
            # 设置该节点的属性
            root_node.setAttribute('bModify', '3')

            # file_lineinfo = open(dst_file, 'w', encoding='utf-8')
            list_dict = json.loads(content[1])
            nsize = len(list_dict)
            print(nsize)
            for i in range(nsize):
                print(list_dict[i])
                lin = list_dict[i]
                info = lin['transcription']
                points = lin['points']
                points = [int(y) for x in points for y in x]
                # 用DOM对象创建元素子节点
                info_node = dom.createElement('LineInfo')
                # 用父节点对象添加元素子节点
                root_node.appendChild(info_node)
                # 设置该节点的属性
                info_node.setAttribute('ptLTX', str(points[0]))
                info_node.setAttribute('ptLTY', str(points[1]))
                info_node.setAttribute('ptRTX', str(points[2]))
                info_node.setAttribute('ptRTY', str(points[3]))
                info_node.setAttribute('ptRBX', str(points[4]))
                info_node.setAttribute('ptRBY', str(points[5]))
                info_node.setAttribute('ptLBX', str(points[6]))
                info_node.setAttribute('ptLBY', str(points[7]))
                info_node.setAttribute('Chars', info)
                info_node.setAttribute('bModify', '3')

                pts = ','.join(map(str, points))
                # lineinfo = pts + ',' + info + '\n'
                # file_lineinfo.write(lineinfo)
            # file_lineinfo.close()
            with open(dst_xml_file, 'w', encoding='UTF-8') as fh:
                dom.writexml(fh, indent='', addindent='\t', newl='\n', encoding='UTF-8')


if __name__ == "__main__":
    # src_path = r"C:\Users\WT\Desktop\hkb-bz\Label.txt"
    src_path = r"C:\Users\WT\Desktop\hkb\Cache.cach"
    dst_path = r"C:\Users\WT\Desktop"
    # src_path = r"C:\Users\WT\Desktop\户口本\Cache.cach"
    # dst_path = r"C:\Users\WT\Desktop"
    json_2_xml(src_path, dst_path)