Python 将 xml 文件转换为 csv

Question

I have a directory that contain several xml files that I would like to able to treat all of them, one by one and export them as CSV files. Individually, It works perfectly with the script below:

import xml.etree.ElementTree as ET
import csv
tree = ET.parse('D:/scripts/xml/download_xml_1.xml')
data_out = open('D:/scripts/csv/output_1.csv', 'w',newline='', errors='ignore')
csvwriter = csv.writer(data_out)
col_names = ['Fichier','No. de document','Titre']
csvwriter.writerow(col_names)
root = tree.getroot()

for elem in root.iter(tag='Document'):
        row = []
        filetype = elem.find('FileType').text
        row.append(filetype)
        documentnumber = elem.find('DocumentNumber').text
        row.append(documentnumber)
        title = elem.find('Title').text
        row.append(title)
        csvwriter.writerow(row)
data_out.close()

But I'm going crazy to find the solution to do it, one by one and this where I am so far:

import xml.etree.ElementTree as ET
import csv
import os
for my_files in os.listdir('D:/scripts/xml/'):
    tree = ET.parse(my_files)
    data_out = open('D:/scripts/csv/'+ my_files[:-4] +'.csv', 'w',newline='', errors='ignore')
    csvwriter = csv.writer(data_out)
    col_names = ['Fichier','No. de document','Titre']
    csvwriter.writerow(col_names)
    root = tree.getroot()
    for elem in root.iter(tag='Document'):
        row = []
        filetype = elem.find('FileType').text
        row.append(filetype)
        documentnumber = elem.find('DocumentNumber').text
        row.append(documentnumber)
        title = elem.find('Title').text
        row.append(title)
        csvwriter.writerow(row)
data_out.close()

Any help would be greatly appreciated.

Answer 1

Simply generalize your process in a defined method that receives a file name as input. Then, iteratively pass file names to it. Also, consider with context manager to open text connection without need to close .

import os
import csv
import xml.etree.ElementTree as ET

xml_path = r'D:\scripts\xml'
csv_path = r'D:\scripts\csv'

# DEFINED METHOD
def xml_to_csv(xml_file):
    csv_file = os.path.join(csv_path, f'Output_{xml_file[:-4]}.csv')
    tree = ET.parse(os.path.join(xml_path, xml_file))

    with open(csv_file, 'w', newline='', errors='ignore') as data_out:
        csvwriter = csv.writer(data_out)
        col_names = ['Fichier', 'No. de document', 'Titre']
        csvwriter.writerow(col_names)
    
        root = tree.getroot()
        for elem in root.iter(tag='Document'):
            row = [elem.find('FileType').text,
                   elem.find('DocumentNumber').text,
                   elem.find('Title').text]
            csvwriter.writerow(row)

# FILE ITERATION
for f in os.listdir(xml_path):
    xml_to_csv(f)