Extracting Text / Parse Text with html.parser (Python)

user_14332862 0
Viewed 2136

I want to extract text from a html file, specifically from the <p> and <h1> Tag. I did see the code from the python doc regarding this topic: from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        print("Encountered a start tag:", tag)

    def handle_endtag(self, tag):
        print("Encountered an end tag :", tag)

    def handle_data(self, data):
        print("Encountered some data  :", data)

parser = MyHTMLParser()
parser.feed('<html><head><title>Test</title></head>'
            '<body><h1>Parse me!</h1></body></html>')

But I'm not sure how to go from here, in order to extract only texts within certain tags (

and . Any hint and advice in the right direction is welcomed! (I do not want to use beautiful soup or any external libraries)

web-crawler html-parsing python
1 Answers

You can use this example how to parse the text from <h1> and <p> tags:

from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):

    def __init__(self):
        super().__init__()
        self.data = []
        self.capture = False

    def handle_starttag(self, tag, attrs):
        if tag in ('p', 'h1'):
            self.capture = True

    def handle_endtag(self, tag):
        if tag in ('p', 'h1'):
            self.capture = False

    def handle_data(self, data):
        if self.capture:
            self.data.append(data)

parser = MyHTMLParser()
parser.feed('<html><head><title>Test</title></head>'
            '<body><h1>Parse me!</h1><p>This is P tag</p></body></html>')

print(parser.data)

Prints:

['Parse me!', 'This is P tag']
user_100359850
Related