Python解决xml文件中存在中文字符的问题

参考自https://blog.youkuaiyun.com/pursuit_zhangyu/article/details/107719037

import os
import os.path
import xml.etree.ElementTree as ET
 
 
headstr = """\
<annotation>
    <folder>VOC</folder>
    <filename>%s</filename>
    <path>zhangyt</path>
    <source>
        <database>My Database</database>
    </source>
    <size>
        <width>%d</width>
        <height>%d</height>
        <depth>%d</depth>
    </size>
    <segmented>0</segmented>
"""
objstr = """\
    <object>
        <name>%s</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>%d</xmin>
            <ymin>%d</ymin>
            <xmax>%d</xmax>
            <ymax>%d</ymax>
        </bndbox>
    </object>
"""
 
tailstr = '''\
</annotation>
'''
 
def write_xml(anno_path,head, objs, tail):
    f = open(anno_path, "w")
    f.write(head)
    for obj in objs:
        f.write(objstr%(obj[0],obj[1],obj[2],obj[3],obj[4]))
    f.write(tail)
 
 
def convertxml(path_xml,files, save_xml):
 
	for xmlFile in files:
		dataset = []
		print(xmlFile)
		f = open(os.path.join(path_xml,xmlFile))
		xml_text = f.read()
		root = ET.fromstring(xml_text)
		f.close()
 
		image_name = xmlFile.replace("xml", "jpg")
		# name = root.find('path').text
		width = int(root.findtext("./size/width"))
		height = int(root.findtext("./size/height"))
		depth = int(root.findtext("./size/depth"))
 
		head=headstr % (image_name, width, height, depth)
 
		for obj in root.iter("object"):
			name = str(obj.findtext("name"))
			xmin = int(obj.findtext("bndbox/xmin"))
			ymin = int(obj.findtext("bndbox/ymin"))
			xmax = int(obj.findtext("bndbox/xmax"))
			ymax = int(obj.findtext("bndbox/ymax"))
 
			if xmax == xmin or ymax == ymin:
				print(xmlFile)
			dataset.append([name, xmin, ymin, xmax, ymax])
		tail = tailstr
		write_xml(os.path.join(save_xml, xmlFile),head, dataset, tail)
 
 
if __name__ == "__main__":
	path_xml = "Annotations/"
	save_xml =  "Annotations_name/"
	if not os.path.exists(save_xml):
		os.mkdir(save_xml)
	xmlFile = os.listdir(path_xml)
	convertxml(path_xml,xmlFile,save_xml)