mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 20:14:47 +00:00
21 lines
1.2 KiB
HTML
Vendored
21 lines
1.2 KiB
HTML
Vendored
<html>
|
|
<body>
|
|
<h1>Introduction to parsing HTML files with <img src="https://docling-project.github.io/docling/assets/logo.png" alt="Docling" height="64"> Docling</h1>
|
|
<p>Docling simplifies document processing, parsing diverse formats — including HTML — and providing seamless integrations with the gen AI ecosystem.</p>
|
|
<h2>Supported file formats</h2>
|
|
<p>Docling supports multiple file formats..</p>
|
|
<ul>
|
|
<li><img src="file://../assets/pdf.png" height="32" alt="PDF">Advanced PDF understanding</li>
|
|
<li><img src="file://../assets/docx.png" height="32" alt="DOCX">Microsoft Office DOCX</li>
|
|
<li><img src="file://../assets/html.png" height="32" alt="HTML">HTML files (with optional support for images)</li>
|
|
</ul>
|
|
<h3>Three backends for handling HTML files</h3>
|
|
<p>Docling has three backends for parsing HTML files:</p>
|
|
<ol>
|
|
<li><b>HTMLDocumentBackend</b> Ignores images</li>
|
|
<li><b>HTMLDocumentBackendImagesInline</b> Extracts images inline</li>
|
|
<li><b>HTMLDocumentBackendImagesReferenced</b> Extracts images as references</li>
|
|
</ol>
|
|
</body>
|
|
</html>
|