Using argparse to convert csv to xml in python

Question

A really quick quesiton, basically my program takes an inputfile which is a csv file and then converts it into a xml file. However, the name of the xml file can either be set by the user input or if the user doesn't specify the name, then the xml file will have the same name as the csv file except with a .xml extension. I need help with the latter. So far my program works when the output file is given a name but i don't know how to set the xml file name when the user doesn't input a name. I know that if the user doesn't set a name then argparse.outputfile is none and i can write a simple if statement to check but i do not know how to set the name to be the same as the csv file name after. Here is my code:

import sys, argparse
import csv
import indent
from xml.etree.ElementTree import ElementTree, Element, SubElement, Comment, tostring

parser=argparse.ArgumentParser(description='Convert wordlist text files to various formats.', prog='Text Converter')
parser.add_argument('-v','--verbose',action='store_true',dest='verbose',help='Increases messages being printed to stdout')
parser.add_argument('-c','--csv',action='store_true',dest='readcsv',help='Reads CSV file and converts to XML file with same name')
parser.add_argument('-x','--xml',action='store_true',dest='toxml',help='Convert CSV to XML with different name')
parser.add_argument('-i','--inputfile',type=argparse.FileType('r'),dest='inputfile',help='Name of file to be imported',required=True)
parser.add_argument('-o','--outputfile',type=argparse.FileType('w'),dest='outputfile',help='Output file name')
args = parser.parse_args()

def main(argv):
    reader = read_csv(args.inputfile)
    if args.verbose: 
        print ('Verbose Selected')
    if args.toxml:
        if args.verbose:
            print ('Convert to XML Selected')
        generate_xml(reader, args.outputfile)
    if args.readcsv:
        if args.verbose:
            print ('Reading CSV file')
    if not (args.toxml or args.readcsv):
        parser.error('No action requested')
    return 1

def read_csv(inputfile):
      return list(csv.reader(inputfile))

def generate_xml(reader,outfile):
    root = Element('Solution')
    root.set('version','1.0')
    tree = ElementTree(root)

    head = SubElement(root, 'DrillHoles')
    head.set('total_holes', '238')

    description = SubElement(head,'description')
    current_group = None
    i = 0
    for row in reader:
        if i > 0:
            x1,y1,z1,x2,y2,z2,cost = row
            if current_group is None or i != current_group.text:
                current_group = SubElement(description, 'hole',{'hole_id':"%s"%i})

                collar = SubElement (current_group, 'collar',{'':', '.join((x1,y1,z1))}),
                toe = SubElement (current_group, 'toe',{'':', '.join((x2,y2,z2))})                                       
                cost = SubElement(current_group, 'cost',{'':cost})
        i+=1    
    indent.indent(root)
    tree.write(outfile)

if (__name__ == "__main__"):
    sys.exit(main(sys.argv))

I think your code would be much simpler if you simply make the input file a required positional argument, and the output file an optional positional argument that defaults to the modified input name: script INPUT [OUTPUT]. -c (as shown, anyway) is a no-op which is only required to avoid a parser error if -x isn't specified. — chepner
– chepner, Commented Jun 12, 2013 at 15:18

tdelaney · Accepted Answer · 2013-06-12 17:27:37Z

1

Add "import os" to the list of imports at the top of the file. Then, right after parsing, you can check and set the argument:

if args.outputfile is None:
    args.outputfile = os.path.splitext(args.inputfile)[0] + '.xml'

By the way, arguments default to their long option name. You only need the 'dest' keyword when you want to use a different name. So, for example, 'verbose' could be:

parser.add_argument('-v', '--verbose', action='store_true',
    help='Increases messages being printed to stdout')

EDIT: Here is the example reworked with outputfile handling and with chepner's suggestion to use positional arguments for the file names.

import os
import sys
import argparse
import csv
import indent
from xml.etree.ElementTree import ElementTree, Element, SubElement, Comment, tostring

def get_args(args):
    parser=argparse.ArgumentParser(description='Convert wordlist text files to various formats.', prog='Text Converter')
    parser.add_argument('-v','--verbose',action='store_true',dest='verbose',help='Increases messages being printed to stdout')
    parser.add_argument('-c','--csv',action='store_true',dest='readcsv',help='Reads CSV file and converts to XML file with same name')
    parser.add_argument('-x','--xml',action='store_true',dest='toxml',help='Convert CSV to XML with different name')
    #parser.add_argument('-i','--inputfile',type=str,help='Name of file to be imported',required=True)
    #parser.add_argument('-o','--outputfile',help='Output file name')
    parser.add_argument('inputfile',type=str,help='Name of file to be imported')
    parser.add_argument('outputfile',help='(optional) Output file name',nargs='?')
    args = parser.parse_args()
    if not (args.toxml or args.readcsv):
        parser.error('No action requested')
        return None
    if args.outputfile is None:
        args.outputfile = os.path.splitext(args.inputfile)[0] + '.xml'
    return args

def main(argv):
    args = get_args(argv[1:])
    if args is None:
        return 1
    inputfile = open(args.inputfile, 'r')
    outputfile = open(args.outputfile, 'w')
    reader = read_csv(inputfile)
    if args.verbose:
        print ('Verbose Selected')
    if args.toxml:
        if args.verbose:
            print ('Convert to XML Selected')
        generate_xml(reader, outputfile)
    if args.readcsv:
        if args.verbose:
            print ('Reading CSV file')
    return 1 # you probably want to return 0 on success

def read_csv(inputfile):
      return list(csv.reader(inputfile))

def generate_xml(reader,outfile):
    root = Element('Solution')
    root.set('version','1.0')
    tree = ElementTree(root)

    head = SubElement(root, 'DrillHoles')
    head.set('total_holes', '238')

    description = SubElement(head,'description')
    current_group = None
    i = 0
    for row in reader:
        if i > 0:
            x1,y1,z1,x2,y2,z2,cost = row
            if current_group is None or i != current_group.text:
                current_group = SubElement(description, 'hole',{'hole_id':"%s"%i})

                collar = SubElement (current_group, 'collar',{'':', '.join((x1,y1,z1))}),
                toe = SubElement (current_group, 'toe',{'':', '.join((x2,y2,z2))})
                cost = SubElement(current_group, 'cost',{'':cost})
        i+=1
    indent.indent(root)
    tree.write(outfile)

if (__name__ == "__main__"):
    sys.exit(main(sys.argv))

edited Jun 12, 2013 at 17:27

answered Jun 12, 2013 at 15:06

tdelaney

77.9k6 gold badges91 silver badges129 bronze badges

Sign up to request clarification or add additional context in comments.

7 Comments

tdelaney Over a year ago

No, you can change the variables or add new ones.

tdelaney Over a year ago

@Andy, Okay, added a comment to "import os".

Andy Over a year ago

yes i tried that as well, but i also receive: Attribute error: file object has no attribute 'rfind'

tdelaney Over a year ago

@Andy which version of python are you using? Which line gets the error?

Andy Over a year ago

python 2.7 and it has something to do with the splitext part

|

Collectives™ on Stack Overflow

Using argparse to convert csv to xml in python

1 Answer 1

7 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

7 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related