Convert all xml files of a directory to CSV in python

-1

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 directory in ['train','test']:

        image_path = os.path.join(os.getcwd(), 'images/{}'.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()

So, I took this code from somewhere. It is supposed to convert CSV file from xml files.

I do have the directory 'train' and 'test' in the same place where this python file is located. And have a bunch of xml files in both directories.

When I run this it does create two csv files inside 'Data' directory. But when I open these csv files, I see them empty.

asked Nov 22 '18 at 14:06

Azazel

878

add a comment |

-1

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 directory in ['train','test']:

        image_path = os.path.join(os.getcwd(), 'images/{}'.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()

So, I took this code from somewhere. It is supposed to convert CSV file from xml files.

I do have the directory 'train' and 'test' in the same place where this python file is located. And have a bunch of xml files in both directories.

When I run this it does create two csv files inside 'Data' directory. But when I open these csv files, I see them empty.

asked Nov 22 '18 at 14:06

Azazel

878

add a comment |

-1

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 directory in ['train','test']:

        image_path = os.path.join(os.getcwd(), 'images/{}'.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()

So, I took this code from somewhere. It is supposed to convert CSV file from xml files.

I do have the directory 'train' and 'test' in the same place where this python file is located. And have a bunch of xml files in both directories.

When I run this it does create two csv files inside 'Data' directory. But when I open these csv files, I see them empty.

asked Nov 22 '18 at 14:06

Azazel

878

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 directory in ['train','test']:

        image_path = os.path.join(os.getcwd(), 'images/{}'.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()

So, I took this code from somewhere. It is supposed to convert CSV file from xml files.

I do have the directory 'train' and 'test' in the same place where this python file is located. And have a bunch of xml files in both directories.

When I run this it does create two csv files inside 'Data' directory. But when I open these csv files, I see them empty.

python python-3.x

asked Nov 22 '18 at 14:06

Azazel

878

asked Nov 22 '18 at 14:06

Azazel

878

asked Nov 22 '18 at 14:06

Azazel

878

asked Nov 22 '18 at 14:06

Azazel

878

asked Nov 22 '18 at 14:06

Azazel

878

add a comment |

1 Answer
1

active

oldest

votes

Your XML parsing loop returned no relevant results.

You say the *.xml glob matches a "bunch" of files. Ok, let's assume that is so. Add a debugging print(value) statement just before the .append().

If it turns out that it never executes, then you will want to debug why the tree root lacks an 'object' node.

answered Nov 22 '18 at 21:53

J_H

3,3051617

add a comment |

Your Answer

StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});

}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53432738%2fconvert-all-xml-files-of-a-directory-to-csv-in-python%23new-answer', 'question_page');
}
);

Post as a guest

Name

Required, but never shown

1 Answer
1

active

oldest

votes

1 Answer
1

active

oldest

votes

Your XML parsing loop returned no relevant results.

You say the *.xml glob matches a "bunch" of files. Ok, let's assume that is so. Add a debugging print(value) statement just before the .append().

If it turns out that it never executes, then you will want to debug why the tree root lacks an 'object' node.

answered Nov 22 '18 at 21:53

J_H

3,3051617

add a comment |

Your XML parsing loop returned no relevant results.

You say the *.xml glob matches a "bunch" of files. Ok, let's assume that is so. Add a debugging print(value) statement just before the .append().

If it turns out that it never executes, then you will want to debug why the tree root lacks an 'object' node.

answered Nov 22 '18 at 21:53

J_H

3,3051617

add a comment |

Your XML parsing loop returned no relevant results.

You say the *.xml glob matches a "bunch" of files. Ok, let's assume that is so. Add a debugging print(value) statement just before the .append().

If it turns out that it never executes, then you will want to debug why the tree root lacks an 'object' node.

answered Nov 22 '18 at 21:53

J_H

3,3051617

Your XML parsing loop returned no relevant results.

You say the *.xml glob matches a "bunch" of files. Ok, let's assume that is so. Add a debugging print(value) statement just before the .append().

If it turns out that it never executes, then you will want to debug why the tree root lacks an 'object' node.

answered Nov 22 '18 at 21:53

J_H

3,3051617

answered Nov 22 '18 at 21:53

J_H

3,3051617

answered Nov 22 '18 at 21:53

J_H

3,3051617

answered Nov 22 '18 at 21:53

J_H

3,3051617

add a comment |

draft saved

draft discarded

Thanks for contributing an answer to Stack Overflow!

Please be sure to answer the question. Provide details and share your research!

But avoid …

Asking for help, clarification, or responding to other answers.

Making statements based on opinion; back them up with references or personal experience.

To learn more, see our tips on writing great answers.

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Name

Required, but never shown

Name

Required, but never shown

This page is only for reference, If you need detailed information, please check here

搜尋此網誌

Tukukkk