This tutorial shows Python developers how to create, read, and edit HTML files with Aspose.HTML for Python via .NET. You'll learn prerequisites, code examples, configuration options, performance tuning, and validation techniques for building content tools.
Read the full guide here: https://blog.aspose.com/html/create-read-and-edit-html-in-python/
| import os | |
| import sys | |
| from aspose.html import HtmlDocument, HtmlLoadOptions, HtmlSaveOptions, HtmlLoadOptions | |
| def create_html(output_path: str): | |
| # Create a new empty HTML document | |
| doc = HtmlDocument() | |
| try: | |
| # Build <html><head><title>...</title></head><body>...</body></html> | |
| html = doc.create_element("html") | |
| doc.append_child(html) | |
| head = doc.create_element("head") | |
| html.append_child(head) | |
| title = doc.create_element("title") | |
| title.inner_html = "Sample Document" | |
| head.append_child(title) | |
| body = doc.create_element("body") | |
| html.append_child(body) | |
| h1 = doc.create_element("h1") | |
| h1.id = "mainHeader" | |
| h1.inner_html = "Welcome to Aspose.HTML" | |
| body.append_child(h1) | |
| p = doc.create_element("p") | |
| p.inner_html = "This document was generated programmatically." | |
| body.append_child(p) | |
| # Save with pretty printing for readability | |
| save_opts = HtmlSaveOptions() | |
| save_opts.pretty_print = True | |
| doc.save(output_path, save_opts) | |
| finally: | |
| doc.dispose() | |
| def read_and_edit_html(input_path: str, output_path: str): | |
| load_opts = HtmlLoadOptions() | |
| # Enable lazy loading of external resources for large files | |
| load_opts.resource_loading = HtmlLoadOptions.ResourceLoadingMode.LAZY | |
| doc = HtmlDocument(input_path, load_opts) | |
| try: | |
| # Edit the <title> element if it exists | |
| title_elem = doc.get_elements_by_tag_name("title") | |
| if title_elem.length > 0: | |
| title_elem.item(0).inner_html = "Edited Document Title" | |
| # Change header text by id | |
| header = doc.get_element_by_id("mainHeader") | |
| if header: | |
| header.inner_html = "Edited Header via Aspose.HTML" | |
| # Append a new paragraph at the end of <body> | |
| body = doc.get_elements_by_tag_name("body").item(0) | |
| if body: | |
| new_para = doc.create_element("p") | |
| new_para.inner_html = "Additional paragraph added during edit." | |
| body.append_child(new_para) | |
| # Insert a new <div> with a class attribute | |
| new_div = doc.create_element("div") | |
| new_div.set_attribute("class", "highlight") | |
| new_div.inner_html = "<strong>Important notice:</strong> This is a dynamically inserted div." | |
| body.append_child(new_div) | |
| # Save edited HTML with compression disabled for faster I/O on large files | |
| save_opts = HtmlSaveOptions() | |
| save_opts.compression = HtmlSaveOptions.CompressionMode.NONE | |
| doc.save(output_path, save_opts) | |
| finally: | |
| doc.dispose() | |
| def validate_edited_html(file_path: str): | |
| doc = HtmlDocument(file_path) | |
| try: | |
| # Simple validation: ensure the edited header exists and contains expected text | |
| header = doc.get_element_by_id("mainHeader") | |
| if not header: | |
| raise ValueError("Validation failed: 'mainHeader' element missing.") | |
| if "Edited Header" not in header.inner_html: | |
| raise ValueError("Validation failed: Header text was not updated correctly.") | |
| # Ensure the newly added div exists | |
| divs = doc.get_elements_by_class_name("highlight") | |
| if divs.length == 0: | |
| raise ValueError("Validation failed: Highlight div not found.") | |
| print("Validation succeeded: edited HTML structure is as expected.") | |
| finally: | |
| doc.dispose() | |
| def main(): | |
| # Paths (use generic names; adjust as needed) | |
| created_path = os.path.abspath("created.html") | |
| input_path = os.path.abspath("input.html") # Assume this file exists | |
| edited_path = os.path.abspath("edited.html") | |
| try: | |
| # Step 1: Create a new HTML file | |
| create_html(created_path) | |
| print(f"Created HTML saved to: {created_path}") | |
| # Step 2: Read existing HTML and edit it | |
| if not os.path.isfile(input_path): | |
| raise FileNotFoundError(f"Input HTML file not found: {input_path}") | |
| read_and_edit_html(input_path, edited_path) | |
| print(f"Edited HTML saved to: {edited_path}") | |
| # Step 3: Validate the edited HTML | |
| validate_edited_html(edited_path) | |
| except Exception as e: | |
| # Centralized error handling | |
| print(f"An error occurred: {e}", file=sys.stderr) | |
| sys.exit(1) | |
| if __name__ == "__main__": | |
| main() |