批量修改LabelImg生成的xml文件

批量修改LabelImg生成的xml文件

xml文件是由LabelImg标注生成的文件，但有时需要对xml文件内容进行修改，本文提供以下思路：

xml格式

下面是由LabelImg标注生成文件的具体内容，这里对filename和path进行修改

<annotation>
	<folder>Defect</folder>
	<filename>Image_0000.bmp</filename>
	<path>C:\Users\13357\Desktop\Pictures\Pictures\Defect\Image_0000.bmp</path>
	<source>
		<database>Unknown</database>
	</source>
	<size>
		<width>2592</width>
		<height>1944</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>defect</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>2086</xmin>
			<ymin>300</ymin>
			<xmax>2166</xmax>
			<ymax>376</ymax>
		</bndbox>
	</object>
	<object>
		<name>defect</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1997</xmin>
			<ymin>690</ymin>
			<xmax>2043</xmax>
			<ymax>1015</ymax>
		</bndbox>
	</object>
	<object>
		<name>defect</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>2051</xmin>
			<ymin>729</ymin>
			<xmax>2096</xmax>
			<ymax>1039</ymax>
		</bndbox>
	</object>
	<object>
		<name>case</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>1897</xmin>
			<ymin>188</ymin>
			<xmax>2317</xmax>
			<ymax>1619</ymax>
		</bndbox>
	</object>
</annotation>

实现代码

import os
import xml.dom.minidom

path = 'Datasets/Test_of_xml_rectify/xmls'
files = os.listdir(path)

s = []
num = 0
i = 0
j = 0

for xmlFile in files:
    if not os.path.isdir(xmlFile):
        print(xmlFile)
    if xmlFile.endswith('.xml'):
        dom = xml.dom.minidom.parse(os.path.join(path, xmlFile))
        root = dom.documentElement
        xml_name = root.getElementsByTagName('filename')
        xml_path = root.getElementsByTagName('path')

        for i in range(len(xml_name)):
            print(xml_name[i].firstChild.data)
            if num < 10:
                xml_name[i].firstChild.data = '00000000000' + str(num) + '.bmp'
            elif 10 <= num < 100:
                xml_name[i].firstChild.data = '0000000000' + str(num) + '.bmp'
            else:
                xml_name[i].firstChild.data = '000000000' + str(num) + '.bmp'
            print(xml_name[i].firstChild.data)

        for j in range(len(xml_path)):
            print(xml_name[j].firstChild.data)
            if num < 10:
                xml_path[j].firstChild.data = './coco/2017/annotations/xml/' + '00000000000' + str(num) + '.bmp'
            elif 10 <= num < 100:
                xml_path[j].firstChild.data = './coco/2017/annotations/xml/' + '0000000000' + str(num) + '.bmp'
            else:
                xml_path[j].firstChild.data = './coco/2017/annotations/xml/' + '0000000000' + str(num) + '.bmp'
            print(xml_path[j].firstChild.data)
            num += 1

        with open(os.path.join(path, xmlFile), 'w') as fh:
            dom.writexml(fh)
            print('写入filename/path OK！')