Created
November 11, 2023 17:44
-
-
Save EteimZ/e68127f619ffc8ca74b022a3e31ead10 to your computer and use it in GitHub Desktop.
Experimenting with the DOM in python
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from html.parser import HTMLParser | |
| class SimpleHTMLParser(HTMLParser): | |
| def __init__(self): | |
| super().__init__() | |
| self.dom_tree = [] | |
| def handle_starttag(self, tag, attrs): | |
| element = {'tag': tag, 'attributes': dict(attrs), 'content': []} | |
| if not self.dom_tree: | |
| self.dom_tree.append(element) | |
| else: | |
| parent = self.dom_tree[-1] | |
| parent['content'].append(element) | |
| self.dom_tree.append(element) | |
| def handle_endtag(self, tag): | |
| self.dom_tree.pop() | |
| def handle_data(self, data): | |
| if data.strip(): | |
| parent = self.dom_tree[-1] | |
| parent['content'].append(data.strip()) | |
| def parse_html(html_content): | |
| parser = SimpleHTMLParser() | |
| parser.feed(html_content) | |
| return parser.dom_tree[0] | |
| def print_dom_tree(element, indent=0): | |
| if isinstance(element, dict): | |
| print(' ' * indent + f"<{element['tag']} {element['attributes']}>") | |
| for content in element['content']: | |
| print_dom_tree(content, indent + 2) | |
| print(' ' * indent + f"</{element['tag']}>") | |
| elif isinstance(element, str): | |
| print(' ' * indent + element) | |
| html_content = """ | |
| <html> | |
| <head> | |
| <title>Test</title> | |
| </head> | |
| <body> | |
| <h1>Parse me!</h1> | |
| </body> | |
| </html> | |
| """ | |
| dom_tree = parse_html(html_content) | |
| print_dom_tree(dom_tree) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment