We use cookies to ensure you have the best browsing experience on our website. Please read our cookie policy for more information about how we use cookies.
  1. Prepare
  2. Python
  3. Regex and Parsing
  4. HTML Parser - Part 1
  5. Discussions

HTML Parser - Part 1

Sort by

recency

|

180 Discussions

|

  • dilajevolves
     + 0 comments
    class MyHTMLParser(HTMLParser):
    
    def print_attrs(self,attrs):
        for name,value in attrs:
            print(f"-> {name} > {value if value is not None else 'None'}")
            
    def handle_starttag(self,tag,attrs):
        print("Start :",tag)
        self.print_attrs(attrs)
      
    def handle_startendtag(self,tag,attrs):
        print("Empty :",tag)
        self.print_attrs(attrs)
            
    def handle_endtag(self,tag):
        print("End   :",tag)
    
    def handle_comment(self,data):
        pass
        
html = '\n'.join(input() for _ in range(int(input())))

MyHTMLParser().feed(html)

  • maxence_qnt
     + 0 comments

    I was stuck during 10 minutes because I got "None" value in my output... Because this is the return value of the parse function if nothing...

    Nevermind, I finally fix this problem.

    Here the code :

    from html.parser import HTMLParser

N = int(input())

class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        print("Start :", tag)
        if attrs:
            for element in attrs:
                attribute_name = element[0]
                attribute_value = element[1]
                print(f"-> {attribute_name} > {attribute_value}")

    def handle_endtag(self, tag):
        print("End   :", tag)

    def handle_startendtag(self, tag, attrs):
        print("Empty :", tag)
        if attrs:
            for element in attrs:
                attribute_name = element[0]
                attribute_value = element[1]
                print(f"-> {attribute_name} > {attribute_value}")


parser = MyHTMLParser()

for _ in range(N):
    current_line = input()
    if parser.feed(current_line):
        print(parser.feed(current_line))

  • BlancLadyDior
     + 0 comments

    I need to follow number of different spaces when printing the output. ~~~

    from html.parser import HTMLParser

    class MyHTMLParser(HTMLParser): def handle_starttag(self, tag, attrs): print("Start :", tag) for attr in attrs: print("->", attr[0], ">", attr[1])

    def handle_endtag(self, tag):
    print("End   :", tag)

def handle_startendtag(self, tag, attrs):
    print("Empty :", tag)
    for attr in attrs:
       print("->", attr[0], ">", attr[1])

    parser = MyHTMLParser() n = int(input()) for _ in range(n): s = input()

    parser.feed(s)

    ~~~

  • rohitambasta_ii1
     + 0 comments
    from html.parser import HTMLParser

class myHTMLParser(HTMLParser):
    def __init__(self):
        super().__init__()
        N = int(input())
        for _ in range(N):
            html_text = input()
            self.feed(html_text)

    def handle_starttag(self, tag, attrs):
        print("Start :", tag)
        for name, value in attrs:
            print("->", name, ">", value)

    def handle_endtag(self, tag):
        print("End   :", tag)

    def handle_startendtag(self, tag, attrs):  
        print("Empty :", tag)
        for name, value in attrs:
            print("->", name, ">", value)
              
parser = myHTMLParser()

  • yashdeora98294
     + 0 comments

    Here is HackerRank HTML Parser - Part 1 in Python solution - https://programmingoneonone.com/hackerrank-html-parser-part-1-solution-in-python.html