读取xml文件中的信息到txt文本中

1.代码

import xml.etree.ElementTree as ET
import os
"""
r''要加上的
"""
source = r'D:\pycharm\pytorch相关\labelImg-master\ori_xlm'  # 文件夹路径
dir = os.listdir(source)

dir为一个列表

查看dir中的第二个元素(index=1)
作为一个N叉树
可以查看其叶子节点

里面出现了多个’obejct’节点
因为源xml文件框了好几个不同的对象

查看xml文件里面的的路径名

当一个root里有多个’object‘属性时，通过双层for循环即可取出来

for i in root.iter('object'):
    print(i)
    for j in i.iter('bndbox'):
        print(j)


<Element 'object' at 0x00000262276779F0>
<Element 'bndbox' at 0x0000026227677B80>
<Element 'object' at 0x0000026227677D10>
<Element 'bndbox' at 0x0000026227677EA0>
<Element 'object' at 0x000002622767F090>
<Element 'bndbox' at 0x000002622767F220>
<Element 'object' at 0x000002622767F3B0>
<Element 'bndbox' at 0x000002622767F540>

把坐标和name写进一个txt文件中

for i in range(len(dir)):
    tree = ET.parse(source + '/' + dir[i])
    rect = {}
    line = ""
    root = tree.getroot()
    with open('D:\pycharm\pytorch相关\labelImg-master\ori_xlm\info.txt', 'a', encoding='utf-8') as f1:
        # 路径信息
        for name in root.iter('path'):
            """
            rect是一个字典，没有key时，会自动生成key以及对应的value
            """
            rect['path'] = name.text
        
        for ob in root.iter('object'):
            for bndbox in ob.iter('bndbox'):
                """
                for i in root:
                    print(i)
                <<<
                <Element 'folder' at 0x0000026227679680>
                <Element 'filename' at 0x00000262276792C0>
                <Element 'path' at 0x0000026227679C70>
                <Element 'source' at 0x0000026227679180>
                <Element 'size' at 0x0000026227677860>
                <Element 'segmented' at 0x00000262276779A0>
                <Element 'object' at 0x00000262276779F0>
                <Element 'object' at 0x0000026227677D10>
                <Element 'object' at 0x000002622767F090>
                <Element 'object' at 0x000002622767F3B0>
                
                出现多个叶子节点object,只需要两层迭代。就能把每一个name和bndbox坐标取出来
                """
                for xmin in bndbox.iter('xmin'):
                    rect['xmin'] = xmin.text
                for ymin in bndbox.iter('ymin'):
                    rect['ymin'] = ymin.text
                for xmax in bndbox.iter('xmax'):
                    rect['xmax'] = xmax.text
                for ymax in bndbox.iter('ymax'):
                    rect['ymax'] = ymax.text
                print(rect['xmin'] + ' ' + rect['ymin'] + ' ' + rect['xmax'] + ' ' + rect['ymax'])
                line = rect['xmin'] + ' ' + rect['ymin'] + ' ' + rect['xmax'] + ' ' + rect['ymax'] + " "
                f1.write(line)
            # 文本信息，这个循环应该在for bndbox 外面的，才合理
            for t in ob.iter('name'):
                print(t.text)
                f1.write(t.text + '\n')

print结果如下

txt文件内容如下：

2.root.iter(‘size’)和root.find(‘size’)

前者为迭代器，还是要靠for才能取出其element
后者为element

for i in root.iter('size'):
    print(i==root.find('size'))

# True

cls_id = classes.index(cls) 这个注意一下

"""
把左上、右下坐标形式转换为
(x,y,h,w)
并且归一化(0,1)之间
"""
def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(year, image_id):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

3.参考链接：

1.使用labelImg标注数据的方法
2.读取labelimg生成的xml标签