python使用xml.dom解析xml并写入txt

最新推荐文章于 2023-04-27 18:45:48 发布

BetterHLH

最新推荐文章于 2023-04-27 18:45:48 发布

阅读量719

点赞数

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/u012955739/article/details/89382350

本文介绍了一种将XML标注文件转换为TXT格式的方法，通过解析XML文件中的图像路径、对象边界框等信息，并将其写入TXT文件，适用于批量处理图像标注数据集。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

xml文件示例：

<annotation verified="no">
<folder>crossroad</folder>
<filename>000329</filename>
<path>D:\测试\人脸\crossroad\000329.jpg</path>
<source>
<database>Unknown</database>
</source>
<size>
<width>1920</width>
<height>1080</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>face</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<Difficult>0</Difficult>
<bndbox>
<xmin>1735</xmin>
<ymin>98</ymin>
<xmax>1884</xmax>
<ymax>280</ymax>
</bndbox>
</object>
<object>
<name>face</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<Difficult>0</Difficult>
<bndbox>
<xmin>789</xmin>
<ymin>480</ymin>
<xmax>838</xmax>
<ymax>537</ymax>
</bndbox>
</object>
</annotation>

解析xml，并写入txt

#coding=utf-8
import xml.dom.minidom as xmldom
import os


def openXml(filepath,txtpath):
    for root,dirs,files in os.walk(filepath):
        for file in files:
            if os.path.splitext(file)[1] == '.xml':
                str1 = root.split("\\")[1]

                path = os.path.join(root,file)
                # 打开xml文档
                dom = xmldom.parse(path)
                #得到根节点
                annotation = dom.documentElement
                filename = annotation.getElementsByTagName("filename")[0].childNodes[0].data
                str1 = str1 + "/" + filename
                objects = annotation.getElementsByTagName("object")

                for object in objects:
                    xmin = object.getElementsByTagName("xmin")[0].childNodes[0].nodeValue
                    ymin = object.getElementsByTagName("ymin")[0].childNodes[0].nodeValue
                    xmax = object.getElementsByTagName("xmax")[0].childNodes[0].nodeValue
                    ymax = object.getElementsByTagName("ymax")[0].childNodes[0].nodeValue

                    str1 = str1 + " " + xmin + " " + ymin + " " + xmax + " " + ymax
                str1 = str1 + "\n"

                #以追加的形式写入txt
                f = open(txtpath,"a+")
                f.write(str1)
                f.close()

if __name__ == '__main__':
    #xml所在文件夹路径
    filepath = "H:\crossroad"
    #txt路径
    txtpath = "H:\crossroad\data.txt"
    openXml(filepath,txtpath)