Bilişim dünyasına kaliteli, özgün ve Türkçe içerikler kazandırmayı hedefleyen bir platform..

XML Dosyası

<annotation>
	<folder>test</folder>
	<filename>10_split_no_flash_nt_IMG_0009.jpg</filename>
	<path>\images\10_split_no_flash_nt_IMG_0009.jpg</path>
	<source>
		<database>Unknown</database>
	</source>
	<size>
		<width>692</width>
		<height>692</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>split</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>225</xmin>
			<ymin>191</ymin>
			<xmax>260</xmax>
			<ymax>222</ymax>
		</bndbox>
	</object>
	<object>
		<name>split</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>294</xmin>
			<ymin>456</ymin>
			<xmax>319</xmax>
			<ymax>476</ymax>
		</bndbox>
	</object>
	<object>
		<name>split</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>478</xmin>
			<ymin>380</ymin>
			<xmax>515</xmax>
			<ymax>411</ymax>
		</bndbox>
	</object>
</annotation>

Python XML İşlemleri işlemleri için xml.etree.ElementTree kütüphanesini kullanacağız.

İmport

import xml.etree.ElementTree as ET
mytree = ET.parse('sample.xml')
myroot = mytree.getroot()
print(myroot)
#<Element 'annotation' at 0x0000023962F5B680>

findall

import xml.etree.ElementTree as ET
mytree = ET.parse('sample.xml')
myroot = mytree.getroot()
print(myroot)#<Element 'annotation' at 0x000001FEEDCE7D10>
print(myroot.tag)#annotation
print(myroot.tag[0:4])#anno
print(myroot.attrib)#{}


for x in myroot.findall('object'):
    name = x.find('name').text
    pose = x.find('pose').text
    truncated = x.find('truncated').text
    difficult = x.find('difficult').text
    #print(name, pose, truncated, difficult)
    for y in x.find('bndbox'):
        print("\t", y.tag, ":", y.text)

Find and Replace in XML files

import glob
import xml.etree.ElementTree as ET

#file dizininde sadece .xml uzantılı dosyaları okumak istersek
PATH="C:\\Users\\MAHMUT-PC\\Desktop\\doktora\\goruntu-isleme\\2023\\allXMLfilesandImages\\test\\*.xml"

#file dizininde tüm dosyaları okuyacak
#PATH="C:\\Users\\USER-PC\\Desktop\\file\\"


path=glob.glob(PATH)

for file in path:
    mytree = ET.parse(file)
    myroot = mytree.getroot()
    #print(myroot)
    print(myroot)
    #print(file)
    for x in myroot.findall('path'):
        name = x.text
        try:
            x.text = x.text.replace('my-project-name', 'test')
            #x.text = x.text.replace('FEATURE NUMBER', '123456')
        except AttributeError:
            pass
        mytree.write(file, encoding='latin-1')
        print("\t", name)

XML to csv

# based on https://github.com/datitran/raccoon_dataset/blob/master/xml_to_csv.py

import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET


def xml_to_csv(path):
    xml_list = []
    for xml_file in glob.glob(path + '/*.xml'):
        tree = ET.parse(xml_file)
        root = tree.getroot()
        for member in root.findall('object'):
            value = (root.find('filename').text,
                     int(root.find('size')[0].text),
                     int(root.find('size')[1].text),
                     member[0].text,
                     int(member[4][0].text),
                     int(member[4][1].text),
                     int(member[4][2].text),
                     int(member[4][3].text)
                     )
            xml_list.append(value)
    column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
    xml_df = pd.DataFrame(xml_list, columns=column_name)
    return xml_df


def main():
    for folder in ['train', 'test']:
        image_path = os.path.join(os.getcwd(), ('images/' + folder))
        xml_df = xml_to_csv(image_path)
        xml_df.to_csv(('images/'+folder+'_labels.csv'), index=None)
    print('Successfully converted xml to csv.')


main()