Problem with newlines when I use toprettyxml()

Question

I\'m currently using the toprettyxml() function of the xml.dom module in a Python script and I\'m having some trouble with the newlines. If don\'t

Answer 1

This gives me nice XML on Python 3.6, haven't tried on Windows:

dom = xml.dom.minidom.parseString(xml_string)

pretty_xml_as_string = dom.toprettyxml(newl='').replace("\n\n", "\n")

Answer 2

Following function worked for my problem. I had to use python 2.7 and i was not allowed to install any 3rd party additional package.

The crux of implementation is as follows:

1. Use dom.toprettyxml()
2. Remove all white spaces
3. Add new lines and tabs as per your requirement.

~

import os
import re
import xml.dom.minidom
import sys

class XmlTag:
    opening = 0
    closing = 1
    self_closing = 2
    closing_tag = "</"
    self_closing_tag = "/>"
    opening_tag = "<"

def to_pretty_xml(xml_file_path):
    pretty_xml = ""
    space_or_tab_count = "  " # Add spaces or use \t
    tab_count = 0
    last_tag = -1

    dom = xml.dom.minidom.parse(xml_file_path)

    # get pretty-printed version of input file
    string_xml = dom.toprettyxml(' ', os.linesep)

    # remove version tag
    string_xml = string_xml.replace("<?xml version=\"1.0\" ?>", '')

    # remove empty lines and spaces
    string_xml = "".join(string_xml.split())

    # move each tag to new line
    string_xml = string_xml.replace('>', '>\n')

    for line in string_xml.split('\n'):
        if line.__contains__(XmlTag.closing_tag):

            # For consecutive closing tags decrease the indentation
            if last_tag == XmlTag.closing:
                tab_count = tab_count - 1

            # Move closing element to next line
            if last_tag == XmlTag.closing or last_tag == XmlTag.self_closing:
                pretty_xml = pretty_xml + '\n' + (space_or_tab_count * tab_count)

            pretty_xml = pretty_xml + line
            last_tag = XmlTag.closing

        elif line.__contains__(XmlTag.self_closing_tag):

            # Print self closing on next line with one indentation from parent node
            pretty_xml = pretty_xml + '\n' + (space_or_tab_count * (tab_count+1)) + line
            last_tag = XmlTag.self_closing

        elif line.__contains__(XmlTag.opening_tag):

            # For consecutive opening tags increase the indentation
            if last_tag == XmlTag.opening:
                tab_count = tab_count + 1

            # Move opening element to next line
            if last_tag == XmlTag.opening or last_tag == XmlTag.closing:
                pretty_xml = pretty_xml + '\n' + (space_or_tab_count * tab_count)

            pretty_xml = pretty_xml + line
            last_tag = XmlTag.opening

    return pretty_xml

pretty_xml = to_pretty_xml("simple.xml")

with open("pretty.xml", 'w') as f:
    f.write(pretty_xml)