我正在尝试使用包含以下文本的 file.txt：
<a> hello
<a>world
how <a>are
</a>you?</a><a></a></a>
并将其转换为如下文本：
<a>
hello
<a>
world how
<a>
are
</a>
you?
</a>
<a>
</a>
我最初的想法是创建一个包含标签和内容（列表）的 XML 项目，然后在该列表中嵌套更多包含内容的 XML 项目，但是在花了一些时间之后，我觉得我走错了路。
为此我不能使用元素树之类的库，我想从头开始解决问题。我不是在寻找所有答案，我只是希望有人可以帮助我选择正确的前进方向，这样我就不会浪费更多时间来编写无用的代码库。
------------------------------------下面回答------------- -------------
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
没有人提供答案，所以这是我解析 xml 的基本方法，它没有处理诸如