python xml的读取和写入

python 复制代码

import xml.etree.ElementTree as ET
from xml.dom import minidom

# 读取XML文档
tree = ET.parse("./xml_3/z_20240827_001.xml")
root = tree.getroot()
# 获取size元素
size_find_0 = root.find("size")
# 获取width子元素
size_w = size_find_0.find("width")
# 获取元素中的文本
print(size_w.text)

# xml里面有多个 object 元素
# 查找 object 元素的全部
objects = root.findall('object')
for object_find_0 in objects:

    # print('Tag:', child.tag)
    # print('Text:', child.text)
    # print('Attributes:', child.attrib)

    # 获取 object 元素的子元素name
    class_name = object_find_0.find("name")
    print(class_name.text)


# 写入
# 保存
# 创建根元素
root = ET.Element("annotation")

folder_save = ET.SubElement(root, "folder")
folder_save.text = "f"

# 创建子元素
size_save = ET.SubElement(root, "size")
# 创建二级子元素 只需输入参数不同即可
size_w_save = ET.SubElement(size_save, "width")

size_w_save.text = "需要写入的内容"

with open("./name_i.xml", 'w', encoding='utf-8') as xml_file:
    # 将 XML 元素树转换为字节串，编码为 utf-8
    rough_string = ET.tostring(root, 'utf-8')
    # 使用 minidom 模块解析生成的字节串，得到一个可操作的 XML 对象
    reparsed = minidom.parseString(rough_string)
    # 将重新解析后的 XML 对象转换为格式打印（pretty-print）的字符串形式，
    # 其中 indent="  "表示使用两个空格作为缩进
    string_ = reparsed.toprettyxml(indent="  ")
    xml_file.write(string_)

xml 标注文件的拆分与合并

目的是方便检测单类别标注的正确性

例子：将xml拆分多个xml文件

python 复制代码

import xml.etree.ElementTree as ET
import os
from xml.dom import minidom

# 全部类别
list_class = ['A1', 'A2', 'A3']
# xml标签路径 (绝对路径)
path_lab = "E:/lab/"

# 拆分保存xml的路径 (绝对路径)
save_xml_path = "E:/lab/ce/"


for xml_name in os.listdir(path_lab):
    # xml_name = 'Camera12_20231001_30.xml'

    # 1. 读取XML文档
    tree = ET.parse(path_lab + xml_name)
    root = tree.getroot()

    # 存储 字典
    dict_class = {}
    for i in list_class:
        dict_class[i] = []
        # 创建单个文件夹
        folder_name = save_xml_path + "/" + i + "/"
        if not os.path.exists(folder_name):
            os.mkdir(folder_name)
        #     print(f"文件夹 '{folder_name}' 创建成功。")
        # else:
        #     print(f"文件夹 '{folder_name}' 已存在。")

    # for i, j in dict_class.items():
    #     print(i, j)

    size_find_0 = root.find("size")
    size_w = size_find_0.find("width")
    size_h = size_find_0.find("height")
    size_d = size_find_0.find("depth")
    #
    # print(size_w.text)
    # print(size_h.text)
    # print(size_d.text)

    # 分离文件名 与 文件后缀
    name_lab, xml_ = os.path.splitext(xml_name)

    folder_jpg = root.find("folder")
    # print(folder_jpg.text)

    path_jpg = root.find("path")
    # print(path_jpg.text)

    filename_jpg = root.find("filename")
    # print(filename_jpg.text)

    # 2. 查找 object 全部
    objects = root.findall('object')
    for object_find_0 in objects:
        # print('Tag:', child.tag)
        # print('Text:', child.text)
        # print('Attributes:', child.attrib)

        class_name = object_find_0.find("name")
        class_bndbox = object_find_0.find("bndbox")
        class_bndbox_xmin = class_bndbox.find("xmin")
        class_bndbox_ymin = class_bndbox.find("ymin")
        class_bndbox_xmax = class_bndbox.find("xmax")
        class_bndbox_ymax = class_bndbox.find("ymax")

        # print(class_name.text)
        # print(class_bndbox_xmin.text)
        # print(class_bndbox_ymin.text)
        # print(class_bndbox_xmax.text)
        # print(class_bndbox_ymax.text)

        dict_class[class_name.text].append(
            (class_name.text,
             class_bndbox_xmin.text,
             class_bndbox_ymin.text,
             class_bndbox_xmax.text,
             class_bndbox_ymax.text,
             )
        )

    for ob_class, ob_list in dict_class.items():

        # 创建根元素
        root = ET.Element("annotation")

        folder_save = ET.SubElement(root, "folder")
        folder_save.text = folder_jpg.text

        filename_jpg_save = ET.SubElement(root, "filename")
        filename_jpg_save.text = filename_jpg.text

        path_save_xml = ET.SubElement(root, "path")
        path_save_xml.text = path_jpg.text

        # 创建子元素
        size_save = ET.SubElement(root, "size")
        # 创建二级子元素 只需输入参数不同即可
        size_w_save = ET.SubElement(size_save, "width")
        size_w_save.text = size_w.text
        size_h_save = ET.SubElement(size_save, "height")
        size_h_save.text = size_h.text
        size_d_save = ET.SubElement(size_save, "depth")
        size_d_save.text = size_d.text

        for ob_list_i in ob_list:
            object_save = ET.SubElement(root, "object")
            name_save = ET.SubElement(object_save, "name")
            name_save.text = str(ob_list_i[0])

            bndbox_save = ET.SubElement(object_save, "bndbox")
            xmin_save = ET.SubElement(bndbox_save, "xmin")
            xmin_save.text = str(ob_list_i[1])

            ymin_save = ET.SubElement(bndbox_save, "ymin")
            ymin_save.text = str(ob_list_i[2])

            xmax_save = ET.SubElement(bndbox_save, "xmax")
            xmax_save.text = str(ob_list_i[3])

            ymax_save = ET.SubElement(bndbox_save, "ymax")
            ymax_save.text = str(ob_list_i[4])

        # 写入文件
        if len(dict_class[ob_class]) != 0:
            if ob_class in list_class:
                path_save_i = save_xml_path + "/" + ob_class + "/" + xml_name
                print(path_save_i)
                # tree.write(path_save_i, encoding="utf-8", xml_declaration=True)
                with open(path_save_i, 'w', encoding='utf-8') as xml_file:
                    # 将 XML 元素树转换为字节串，编码为 utf-8
                    rough_string = ET.tostring(root, 'utf-8')
                    # 使用 minidom 模块解析生成的字节串，得到一个可操作的 XML 对象
                    reparsed = minidom.parseString(rough_string)
                    # 将重新解析后的 XML 对象转换为格式打印（pretty-print）的字符串形式，
                    # 其中 indent="  "表示使用两个空格作为缩进
                    string_ = reparsed.toprettyxml(indent="  ")
                    xml_file.write(string_)

将拆分的xml合并为1个

python 复制代码

import xml.etree.ElementTree as ET
import os
from xml.dom import minidom

# 合并和拆分的类别要一致
list_class = ['A1', 'A2', 'A3'']
# 标注图片路径
path_img = "E:/zyk_lab/ce/img/"
# xml 拆分的总路径
path_lab = "E:/zyk_lab/ce/ce/"
# xml 合并后保存的路径
path_lab_save = "E:/zyk_lab/ce/lab_ce/"

for img_name in os.listdir(path_img):
    # img_name = "Camera12_20231001_31"
    img_name = os.path.splitext(img_name)[0]

    dict_class = {}
    for i in list_class:
        dict_class[i] = []

    dict_class["width"] = 0
    dict_class["height"] = 0
    dict_class["depth"] = 0
    dict_class["folder"] = "null"
    dict_class["path"] = "null"
    dict_class["filename"] = "null"

    for file_1 in os.listdir(path_lab):
        path_i = os.path.join(path_lab, file_1)
        for xml_name in os.listdir(path_i):
            if img_name == os.path.splitext(xml_name)[0]:

                # 1. 读取XML文档
                xml_path = os.path.join(path_i, xml_name)
                tree = ET.parse(xml_path)
                root = tree.getroot()

                size_find_0 = root.find("size")
                size_w = size_find_0.find("width").text
                size_h = size_find_0.find("height").text
                size_d = size_find_0.find("depth").text

                folder_jpg = root.find("folder").text
                # print(folder_jpg.text)
                path_jpg = root.find("path").text
                # print(path_jpg.text)
                filename_jpg = root.find("filename").text
                # print(filename_jpg.text)

                dict_class["width"] = size_w
                dict_class["height"] = size_h
                dict_class["depth"] = size_d
                dict_class["folder"] = folder_jpg
                dict_class["path"] = path_jpg
                dict_class["filename"] = filename_jpg

                # 2. 查找 object 全部
                objects = root.findall('object')
                for object_find_0 in objects:
                    # print('Tag:', child.tag)
                    # print('Text:', child.text)
                    # print('Attributes:', child.attrib)

                    class_name = object_find_0.find("name")
                    class_bndbox = object_find_0.find("bndbox")
                    class_bndbox_xmin = class_bndbox.find("xmin")
                    class_bndbox_ymin = class_bndbox.find("ymin")
                    class_bndbox_xmax = class_bndbox.find("xmax")
                    class_bndbox_ymax = class_bndbox.find("ymax")

                    # print(class_name.text)
                    # print(class_bndbox_xmin.text)
                    # print(class_bndbox_ymin.text)
                    # print(class_bndbox_xmax.text)
                    # print(class_bndbox_ymax.text)

                    dict_class[class_name.text].append(
                        (class_name.text,
                         class_bndbox_xmin.text,
                         class_bndbox_ymin.text,
                         class_bndbox_xmax.text,
                         class_bndbox_ymax.text,
                         )
                    )

    # 保存
    # 创建根元素
    root = ET.Element("annotation")

    folder_save = ET.SubElement(root, "folder")
    if dict_class["folder"] != "null":
        folder_save.text = dict_class["folder"]

    filename_jpg_save = ET.SubElement(root, "filename")
    if dict_class["filename"] != "null":
        filename_jpg_save.text = dict_class["filename"]

    path_save_xml = ET.SubElement(root, "path")
    if dict_class["path"] != "null":
        path_save_xml.text = dict_class["path"]

    # 创建子元素
    size_save = ET.SubElement(root, "size")
    # 创建二级子元素 只需输入参数不同即可
    size_w_save = ET.SubElement(size_save, "width")
    if dict_class["width"] != "null":
        size_w_save.text = dict_class["width"]
    size_h_save = ET.SubElement(size_save, "height")
    if dict_class["height"] != "null":
        size_h_save.text = dict_class["height"]
    size_d_save = ET.SubElement(size_save, "depth")
    if dict_class["depth"] != "null":
        size_d_save.text = dict_class["depth"]

    for ob_class, ob_list in dict_class.items():
        print(ob_class, ob_list)
        # 跳过你不需要写入的类别
        if ob_class in ["b1", "b2"]:
            continue
        for ob_list_i in ob_list:
            # print(ob_list_i)
            object_save = ET.SubElement(root, "object")
            name_save = ET.SubElement(object_save, "name")
            name_save.text = str(ob_list_i[0])

            bndbox_save = ET.SubElement(object_save, "bndbox")
            xmin_save = ET.SubElement(bndbox_save, "xmin")
            xmin_save.text = str(ob_list_i[1])

            ymin_save = ET.SubElement(bndbox_save, "ymin")
            ymin_save.text = str(ob_list_i[2])

            xmax_save = ET.SubElement(bndbox_save, "xmax")
            xmax_save.text = str(ob_list_i[3])

            ymax_save = ET.SubElement(bndbox_save, "ymax")
            ymax_save.text = str(ob_list_i[4])

    # 写入文件
    # if len(dict_class[ob_class]) != 0:
    #     if ob_class in list_class:
    path_save_i = path_lab_save + img_name + ".xml"
    print(path_save_i)

    # tree.write(path_save_i, encoding="utf-8", xml_declaration=True)
    with open(path_save_i, 'w', encoding='utf-8') as xml_file:
        # 将 XML 元素树转换为字节串，编码为 utf-8
        rough_string = ET.tostring(root, 'utf-8')
        # 使用 minidom 模块解析生成的字节串，得到一个可操作的 XML 对象
        reparsed = minidom.parseString(rough_string)
        # 将重新解析后的 XML 对象转换为格式打印（pretty-print）的字符串形式，
        # 其中 indent="  "表示使用两个空格作为缩进
        string_ = reparsed.toprettyxml(indent="  ")
        xml_file.write(string_)