This program basically flattens an xml file and writes it to csv.
My issue is that the ‘row’ variable in ‘values_loop’ isn’t resetting between calls. Every time I call it the new values are appended to the old ones.
Basically I’m getting this:
A B C
A B C D E F
A B C D E F G H I
When I should get this
A B C
D E F
G H I
My code:
import csv
import xml.etree.ElementTree as ET
file_name = '2.xml'
root = ET.ElementTree(file=file_name).getroot()
csv_file_name = '.'.join(file_name.split('.')[:-1]) + ".txt"
print csv_file_name
with open(csv_file_name, 'w') as file_:
writer = csv.writer(file_, delimiter="\t")
def header_loop(root, i=0, row=[]):
for child in root:
#print "\t"*i, child.tag.replace("{http://www.tes.com/aps/response}",""), child.attrib, i
row.extend([child.tag.replace("{http://www.tes.com/aps/response}","")])
header_loop(child,i+1)
if i==0: return row
def values_loop(root, i=0, row=[]):
for child in root:
#print "\t"*i, child.tag.replace("{http://www.tes.com/aps/response}",""), child.attrib, i
row.extend([child.text])
#print child.text
values_loop(child,i+1)
if i==0: return row
#write the header
writer.writerow(header_loop(root[3]))
#write the values
writer.writerow(values_loop(root[3]))
writer.writerow(values_loop(root[4]))