为什么我总是让孩子超出范围错误？

Question

我正在使用这个 python 脚本将 xml 转换为 csv：

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),
                     int(member[4][4].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 directory in ['train', 'test']:
        image_path = os.path.join(os.getcwd(), 'papers/{}'.format(directory))
        xml_df = xml_to_csv(image_path)
        xml_df.to_csv('data/{}_labels.csv'.format(directory), index=None)
        print('Successfully converted xml to csv.')


main()

当我在看起来像这样的 xml 上运行它时：

<annotation>
    <folder>images</folder>
    <filename>BROWN, M M-1.jpg</filename>
    <size>
        <width>2200</width>
        <height>3217</height>
        <depth>3</depth>
    </size>
    <segmented>0</segmented>
    <object>
        <name>DOB</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <occluded>0</occluded>
        <difficult>0</difficult>
        <bndbox>
            <xmin>121</xmin>
            <ymin>296</ymin>
            <xmax>625</xmax>
            <ymax>346</ymax>
        </bndbox>
    </object>
</annotation>

我不断收到这个

int(member[4][0].text), IndexError: child index out of range' 错误

谁能帮我找出问题所在？我不确定为什么会不断弹出错误。

Answer 1

根据示例 XML，bundbox 元素位于节点 5，而不是 4。顺便说一下，不需要使用 pandas 进行 csv 迁移。考虑csv（Python 3 的内置模块）。下面还显示了您可以对节点使用编号索引、[##] 或 find()：xmin、ymin、xmin 和 xmax.

# ALL STANDARD LIBRARY MODULES
import os, glob, csv
import xml.etree.ElementTree as ET

def xml_to_csv(path):

    with open("Output.csv", "w") as f:
        cw = csv.writer(f, lineterminator="\n")
        cw.writerow(['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax'])

        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[5][0].text),
                         int(member[5][1].text),
                         int(member[5].find('ymin').text),
                         int(member[5].find('ymax').text)
                        )
                cw.writerow(value)