我正在使用此python脚本将xml转换为csv:
contentSize
当我在xml上运行它时,如下所示:
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()
我不断得到这个
int(member [4] [0] .text),IndexError:子索引超出范围'错误
谁能帮助我找出问题所在?我不确定为什么错误不断弹出。
答案 0 :(得分:1)
根据示例XML, bundbox 元素位于节点5而不是4处。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)