去除XML标注文件中的多余标签类别_python去除文本中的xml标签

需求：

        XML标注文件中有多个标签类别，如果只需要其中几种标签类别，就需要去除多余的其他标签类别。

解决方案：

        使用python中的xml.etree.ElementTree库批量去除标注文件所在文件夹所有XML标注文件中的多余标签类别。

具体代码如下：

import os
import glob
import xml.etree.ElementTree as et
 
def delete_bbox(dir_path,labels):
    file_list = glob.glob(os.path.join(dir_path, "*.xml"))
    index = 0
    for file in file_list:
        print(file,index)
        index += 1
        tree_ = et.parse(file)
        root_ = tree_.getroot()
 
        root = et.Element("annotation")
        folder = et.SubElement(root, "folder")
        folder.text = "images"
        filename = et.SubElement(root, "filename")
        filename.text = root_.find(".//filename").text
        source = et.SubElement(root, "source")
        database = et.SubElement(source, "database")
        database.text = "Unknown"
        size = et.SubElement(root, "size")
        width = et.SubElement(size, "width")
        width.text = root_.find(".//width").text
        height = et.SubElement(size, "height")
        height.text = root_.find(".//height").text
        depth = et.SubElement(size, "depth")
        depth.text = "3"
        segmented = et.SubElement(root, "segmented")
        segmented.text = "0"
 
        for object in root_.iter("object"):
            name_ = object.find("name").text
            if name_ in labels:
                object_ = et.SubElement(root, "object")
                name = et.SubElement(object_,"name")
                name.text = name_
                pose = et.SubElement(object_,"pose")
                pose.text = "Unspecified"
                truncated = et.SubElement(object_,"truncated")
                truncated.text = "0"
                difficult = et.SubElement(object_,"difficult")
                difficult.text = "0"
                bndbox = et.SubElement(object_,"bndbox")
                xmin = et.SubElement(bndbox,"xmin")
                xmin.text = object.find(".//xmin").text
                ymin = et.SubElement(bndbox,"ymin")
                ymin.text = object.find(".//ymin").text
                xmax = et.SubElement(bndbox,"xmax")
                xmax.text = object.find(".//xmax").text
                ymax = et.SubElement(bndbox,"ymax")
                ymax.text = object.find(".//ymax").text
        pretty_xml(root, '  ', '\n')
        tree = et.ElementTree(root)
        tree.write(file, encoding="utf-8")
 
def pretty_xml(element, indent, newline, level=0):  # elemnt为传进来的Elment类，参数indent用于缩进，newline用于换行
    if element:  # 判断element是否有子元素
        if (element.text is None) or element.text.isspace():  # 如果element的text没有内容
            element.text = newline + indent * (level + 1)
        else:
            element.text = newline + indent * (level + 1) + element.text.strip() + newline + indent * (level + 1)
            # else:  # 此处两行如果把注释去掉，Element的text也会另起一行
            # element.text = newline + indent * (level + 1) + element.text.strip() + newline + indent * level
    temp = list(element)  # 将element转成list
    for subelement in temp:
        if temp.index(subelement) < (len(temp) - 1):  # 如果不是list的最后一个元素，说明下一个行是同级别元素的起始，缩进应一致
            subelement.tail = newline + indent * (level + 1)
        else:  # 如果是list的最后一个元素， 说明下一行是母元素的结束，缩进应该少一个
            subelement.tail = newline + indent * level
        pretty_xml(subelement, indent, newline, level=level + 1)  # 对子元素进行递归操作
 
if __name__ == '__main__':
    dir_path = "./Annotations" # xml标注文件所在文件夹
    labels = ["red","green","blue"] # 需要保留的标签类别
    delete_bbox(dir_path,labels)

以上脚本，需要修改xml标注文件所在文件夹路径（dir_path）和需要保留的标签类别（labels），亲测可用。