如何从input.txt中拆分Python中的xml标记，然后对其进行很好的格式化（制表符，换行符，嵌套）？

Question

I'm trying to take file.txt that contains text like:

<a> hello 
<a>world 

how <a>are 
</a>you?</a><a></a></a>

and turn it into text like:

<a> 
    hello 
    <a> 
        world how 
        <a> 
            are 
        </a> 
        you? 
    </a> 
<a> 
</a> 

my original thought was to create an XML item that holds a tag and content(list) and then just nest more XML items inside that list that hold content, but after spending some time I feel like I'm going about it the wrong way.

For this I can't use an libraries like Element tree, I want to solve the problem from scratch . I'm not looking for all the answers I'm just hoping someone can help me choose the right direction to head in so I don't waste more hours coming up with a useless code base.

-----------------------------------Answer Below--------------------------

from stack import Stack
import re
import sys

def findTag(string):
    # checks to see if a string has an xml tag returns the tag or none
    try:
        match = re.search(r"\<(.+?)\>", string)
        return match.group(0), match.start(0)
    except:
        return None

def isTag(string):
    # checks to see if a string is a tag and returns true or false.
    try:
        match = re.search(r"\<(.+?)\>", string)
        match.group(0)
        return True
    except:
        return False
    else:
        return False


def split_tags_and_string(string):
    #splits up tag and string into a list
    L = []
    for line in s.split("\n"):
        temp = line
        while len(temp) >0: #string still has some characters
            #print("line: " + temp)
            tag_tuple = (findTag(temp)) #returns a tuple with tag and starting index
            #print("tag_tuple: "+ str(tag_tuple))
            if tag_tuple is not None: #there is a tag in the temp string
                if tag_tuple[1] == 0: #tag is the front of temp string
                    L.append(tag_tuple[0].strip())
                    temp = temp.replace(tag_tuple[0], '', 1)
                    temp = temp.strip()
                else: #tag is somewhere else other than the front of the temp string
                    L.append(temp[0:tag_tuple[1]].strip())
                    temp = temp.replace(temp[0:tag_tuple[1]], '', 1)
                    temp = temp.strip()
            else: #there is no tag in the temp string
                L.append(temp.strip())
                temp = temp.replace(temp, '')
    return L


def check_tags(formatted_list):
    # verifies that the xml is valid
    stack = Stack()
    x=0
    try:
        #print(formatted_list)
        for item in formatted_list:
            tag = findTag(item)

            #print("tag: "+ str(tag))
            if tag is not None:
                if tag[0].find('/') == -1:
                    endtag = tag[0][0:1] + '/' +tag[0][1:]
                    #print(endtag)
                    if formatted_list.count(tag[0]) != formatted_list.count(endtag):
                        #print("tag count doesn't match")
                        return False, x
                if tag[0].find('/') == -1:
                    #print("pushing: "+tag[0])
                    stack.push(tag[0])
                else:
                    #print("popping: "+tag[0])
                    stack.pop()
            x+=1
    except:
        return False,x
    if stack.isEmpty():
        return True,x
    else:
        return False,x

def print_xml_list(formatted_list):

    indent = 0
    string = str()
    previousIsString = False
    #print(formatted_list)
    for item in formatted_list:
      #print("previous = " + str(previousIsString))
      #print(item)
        if len(item) > 0:
            if isTag(item) == True and item.find('/') == -1:#the item is a tag and not and end tag
                if previousIsString == True and string[len(string)-5:].find('\n') == -1:
                    #add a newline if there isn't one already
                    string+='\n'
                string+=('    '*indent+item+'\n')
                indent+=1 #increases indent
                previousIsString = False #previous isn't a string
            if isTag(item) == True and item.find('/') != -1: #the item is a tag and also an end tag
                if previousIsString == True:
                    string+='\n'
                indent-=1 # reduces indent
                string+=('    '*indent+item+'\n')
                previousIsString = False #previous isn't a string
            if isTag(item) == False:
                if previousIsString:
                    string+=(' '+item+' ') #adds item and no tab space
                else:
                    string+=('    '*indent+item+' ') #adds item with tabs before
                previousIsString = True # previous is a string


    return string


if __name__ == "__main__":

    filename = input("enter file name:  ")
    file = open(filename, 'r')
    s = file.read()


    formatted = split_tags_and_string(s) #formats the string and tags into a list called formatted
    isGood = check_tags(formatted) # makes sure the xml is valid
    if isGood[0] == False: #if the xml is bad it says so and ends the program
        print("The xml file is bad.")
    else:
        string = print_xml_list(formatted) #adds indentation and formatting to the list and turns it into a string
        print(string) #prints the final result

No one provided an answer so here is my basic way to parse xml, it does not have the functionality to handle things like

Answer 1

I provided the answer above. Hopefully this will be useful to someone with a similar curiosity.