firecrawl · xianjianlf2 · Aug 7, 2026 · Aug 7, 2026 · Aug 11, 2026
diff --git a/Cargo.toml b/Cargo.toml
@@ -9,7 +9,7 @@ version = "0.1.8"
 edition = "2024"
 # Edition 2024 needs 1.85; zip and calamine both raise it to 1.88.
 rust-version = "1.88"
-description = "Convert documents (doc, docx, odt, rtf, epub, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown"
+description = "Convert documents (doc, docx, odt, rtf, epub, html, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown"
 license = "MIT"
 repository = "https://github.com/firecrawl/anydoc"
 readme = "README.md"

diff --git a/README.md b/README.md
@@ -6,7 +6,7 @@
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![skills.sh](https://skills.sh/b/firecrawl/anydoc)](https://skills.sh/firecrawl/anydoc)
 
-Fast Rust library that converts documents (Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF) into clean GitHub-Flavored Markdown. Includes bindings for [Node.js](node/README.md), [Python](python/README.md), and the [browser](wasm/README.md) (WebAssembly).
+Fast Rust library that converts documents (Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, HTML, CSV, and PDF) into clean GitHub-Flavored Markdown. Includes bindings for [Node.js](node/README.md), [Python](python/README.md), and the [browser](wasm/README.md) (WebAssembly).
 
 Built by [Firecrawl](https://firecrawl.dev) to turn any office document into LLM-ready Markdown in single-digit milliseconds, with one consistent output no matter which format goes in. It powers [Firecrawl Parse](https://firecrawl.dev/parse), so if you'd rather not run it yourself, the hosted API gives you the same conversion plus our OCR models for the scanned pages anydoc can't read on its own.
 
@@ -130,7 +130,7 @@ let document = anydoc::to_document(&bytes, None)?;
 - **One output for every format.** Each format parses into a shared document model and renders through a single Markdown serializer, so escaping, tables, heading anchors, and footnotes behave identically whether the input was a `.doc` from 2003 or a `.pptx` from yesterday.
 - **Full document structure.** Headings with anchors, bold/italic/strikethrough, inline code and code blocks, links and internal cross-references, bulleted/numbered/nested/task lists with the source's own numbering, tables with merged cells and header rows, block quotes, footnotes and endnotes, and speaker notes.
 - **Embedded assets.** Images and embedded objects render as their alt text in the Markdown, and the raw bytes stay available on the document model, tagged with their media type. Images with an external URL become ordinary Markdown images.
-- **Content-based format detection.** The format is read from the bytes themselves (PDF header, RTF open group, OLE stream names, ZIP package mimetype), so mislabeled files still convert correctly.
+- **Content-based format detection.** The format is read from the bytes themselves (PDF header, RTF open group, OLE stream names, ZIP package mimetype, or an HTML doctype/root element), so mislabeled files still convert correctly.
 - **Fast.** Pure Rust, no ML models, no external services. Median conversion time is under 5ms per document.
 - **Bindings that stay out of the way.** Node.js conversion runs on the libuv thread pool and never blocks the event loop; Python releases the GIL so other threads keep running. TypeScript types and Python stubs ship with the packages.
 - **PDF support built in.** Text-based PDFs convert locally through [pdf-inspector](https://github.com/firecrawl/pdf-inspector), no OCR service required.
@@ -146,6 +146,7 @@ let document = anydoc::to_document(&bytes, None)?;
 | OpenDocument     | `.odt`, `.ods`, `.odp`                                     |
 | Rich Text Format | `.rtf`                                                     |
 | EPUB             | `.epub`                                                    |
+| HTML             | `.html`, `.htm`                                            |
 | CSV              | `.csv`                                                     |
 | PDF              | `.pdf`                                                     |
 
@@ -189,7 +190,7 @@ Speed is one warm conversion per document on a Ryzen 9 9950X3D (Windows 11, 64 G
 
 ## Format detection
 
-The format is read from the file content, using the marker its specification designates: the PDF header, the RTF open group, OLE stream names, the ZIP package mimetype and content types. CSV has no such marker, so the extension or an explicit format names it instead.
+The format is read from the file content, using the marker its specification designates: the PDF header, the RTF open group, OLE stream names, the ZIP package mimetype and content types, or an HTML doctype/root element. CSV has no such marker, so the extension or an explicit format names it instead. Standalone HTML files can therefore be recognized even when an exporter gives them a `.doc` extension; MHTML is not yet supported.
 
 ```rust
 Format::from_bytes(&bytes); // Some(Format::Docx), or None when nothing matches
@@ -234,7 +235,7 @@ document bytes
   ├─► format detection      → content markers, not the extension
   │
   ├─► format parser          → one per format (doc, docx, ppt, pptx, xls,
-  │                            xlsx, odt/ods/odp, rtf, epub, csv)
+  │                            xlsx, odt/ods/odp, rtf, epub, html, csv)
   │         │
   │         └─► Document     → shared model: blocks, inlines, tables,
   │                            footnotes, assets

diff --git a/node/README.md b/node/README.md
@@ -3,7 +3,7 @@
 [![npm](https://img.shields.io/npm/v/@firecrawl/anydoc.svg)](https://www.npmjs.com/package/@firecrawl/anydoc)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/firecrawl/anydoc/blob/main/LICENSE)
 
-Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files into clean GitHub-Flavored Markdown. Node.js bindings for the [anydoc](https://github.com/firecrawl/anydoc) Rust crate, built by [Firecrawl](https://firecrawl.dev). Also available as a hosted API through [Firecrawl Parse](https://firecrawl.dev/parse), which adds our OCR models for the scanned pages anydoc can't read on its own.
+Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, HTML, CSV, and PDF files into clean GitHub-Flavored Markdown. Node.js bindings for the [anydoc](https://github.com/firecrawl/anydoc) Rust crate, built by [Firecrawl](https://firecrawl.dev). Also available as a hosted API through [Firecrawl Parse](https://firecrawl.dev/parse), which adds our OCR models for the scanned pages anydoc can't read on its own.
 
 Every format parses into one shared document model and renders through a single Markdown serializer, so headings, tables, lists, and footnotes come out the same no matter which format goes in. Conversion runs on the libuv thread pool and never blocks the event loop. TypeScript types ship with the package.
 
@@ -21,6 +21,7 @@ npm install @firecrawl/anydoc
 | OpenDocument     | `.odt`, `.ods`, `.odp`                                     |
 | Rich Text Format | `.rtf`                                                     |
 | EPUB             | `.epub`                                                    |
+| HTML             | `.html`, `.htm`                                            |
 | CSV              | `.csv`                                                     |
 | PDF              | `.pdf`                                                     |
 
@@ -84,7 +85,7 @@ try {
 
 ## Format detection
 
-The format is read from the file content, using the marker its specification designates: the PDF header, the RTF open group, OLE stream names, the ZIP package mimetype and content types. CSV has no such marker, so detection returns `null` for it and the extension, or an explicit format, names it instead.
+The format is read from the file content, using the marker its specification designates: the PDF header, the RTF open group, OLE stream names, the ZIP package mimetype and content types, or an HTML doctype/root element. CSV has no such marker, so detection returns `null` for it and the extension, or an explicit format, names it instead. Standalone HTML is supported; MHTML is not yet supported.
 
 ```js
 formatFromBytes(bytes); // 'docx', or null when nothing matches

diff --git a/node/cli.js b/node/cli.js
@@ -3,7 +3,7 @@
 
 const { readFile, writeFile } = require('node:fs/promises')
 
-const FORMATS = 'doc, docx, odt, pdf, ppt, pptx, rtf, epub, xlsx, ods, odp, csv'
+const FORMATS = 'doc, docx, odt, pdf, ppt, pptx, rtf, epub, html, xlsx, ods, odp, csv'
 
 const HELP = `anydoc: convert documents to GitHub-Flavored Markdown
 

diff --git a/node/index.d.ts b/node/index.d.ts
@@ -110,6 +110,7 @@ export declare const enum Format {
   pptx = 'pptx',
   rtf = 'rtf',
   epub = 'epub',
+  html = 'html',
   xlsx = 'xlsx',
   ods = 'ods',
   odp = 'odp',
@@ -119,8 +120,9 @@ export declare const enum Format {
 /**
  * Detect the format from the content itself: the signature and identity each
  * container specification designates (PDF header, RTF open group, OLE stream
- * names, ZIP package mimetype/content types). Plain-text formats (CSV) carry
- * no signature and return `null`; so does anything unrecognized.
+ * names, ZIP package mimetype/content types, or an HTML doctype/root element).
+ * Plain-text formats (CSV) carry no signature and return `null`; so does
+ * anything unrecognized.
  */
 export declare function formatFromBytes(bytes: Uint8Array): Format | null
 

diff --git a/node/package.json b/node/package.json
@@ -1,7 +1,7 @@
 {
   "name": "@firecrawl/anydoc",
   "version": "0.1.8",
-  "description": "Convert documents (doc, docx, odt, rtf, epub, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown",
+  "description": "Convert documents (doc, docx, odt, rtf, epub, html, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown",
   "license": "MIT",
   "homepage": "https://github.com/firecrawl/anydoc#readme",
   "repository": {

diff --git a/node/src/lib.rs b/node/src/lib.rs
@@ -25,6 +25,7 @@ pub enum Format {
     pptx,
     rtf,
     epub,
+    html,
     xlsx,
     ods,
     odp,
@@ -42,6 +43,7 @@ impl From<Format> for anydoc::Format {
             Format::pptx => anydoc::Format::Pptx,
             Format::rtf => anydoc::Format::Rtf,
             Format::epub => anydoc::Format::Epub,
+            Format::html => anydoc::Format::Html,
             Format::xlsx => anydoc::Format::Excel,
             Format::ods => anydoc::Format::Ods,
             Format::odp => anydoc::Format::Odp,
@@ -61,6 +63,7 @@ impl From<anydoc::Format> for Format {
             anydoc::Format::Pptx => Format::pptx,
             anydoc::Format::Rtf => Format::rtf,
             anydoc::Format::Epub => Format::epub,
+            anydoc::Format::Html => Format::html,
             anydoc::Format::Excel => Format::xlsx,
             anydoc::Format::Ods => Format::ods,
             anydoc::Format::Odp => Format::odp,
@@ -71,8 +74,9 @@ impl From<anydoc::Format> for Format {
 
 /// Detect the format from the content itself: the signature and identity each
 /// container specification designates (PDF header, RTF open group, OLE stream
-/// names, ZIP package mimetype/content types). Plain-text formats (CSV) carry
-/// no signature and return `null`; so does anything unrecognized.
+/// names, ZIP package mimetype/content types, or an HTML doctype/root element).
+/// Plain-text formats (CSV) carry no signature and return `null`; so does
+/// anything unrecognized.
 #[napi]
 pub fn format_from_bytes(bytes: Uint8Array) -> Option<Format> {
     anydoc::Format::from_bytes(&bytes).map(Format::from)

diff --git a/node/test.mjs b/node/test.mjs
@@ -23,6 +23,7 @@ const OUTLINE = fixture('docx/handmade-outline.docx')
 const RICH = fixture('docx/handmade-rich.docx')
 const CSV = fixture('csv/sheet.csv')
 const ENCRYPTED = fixture('malformed/encrypted--errors.odt')
+const HTML = Buffer.from('<!doctype html><html><body><h1>HTML input</h1></body></html>')
 
 test('toMarkdown detects the format from the file content', async () => {
   const markdown = await toMarkdown(OUTLINE)
@@ -40,6 +41,7 @@ test('toMarkdownBytes detects the format when none is named', async () => {
   // CSV carries no signature, so it has to be named.
   await assert.rejects(toMarkdownBytes(await readFile(CSV)), /unrecognized file content/)
   assert.match(await toMarkdownBytes(await readFile(CSV), 'csv'), /\| --- \|/)
+  assert.match(await toMarkdownBytes(HTML), /^# HTML input/m)
 })
 
 test('toDocument exposes the document model', async () => {
@@ -61,10 +63,12 @@ test('toDocument carries embedded assets as buffers', async () => {
 
 test('format detection reads content, extension, and path', async () => {
   assert.equal(formatFromBytes(await readFile(RICH)), 'docx')
+  assert.equal(formatFromBytes(HTML), 'html')
   // CSV carries no signature: only the extension names it.
   assert.equal(formatFromBytes(await readFile(CSV)), null)
   assert.equal(formatFromExtension('.pptm'), 'pptx')
   assert.equal(formatFromExtension('xls'), 'xlsx')
+  assert.equal(formatFromExtension('htm'), 'html')
   assert.equal(formatFromPath('/tmp/report.odt'), 'odt')
   assert.equal(formatFromPath('/tmp/report.unknown'), null)
 })

diff --git a/python/README.md b/python/README.md
@@ -3,7 +3,7 @@
 [![PyPI](https://img.shields.io/pypi/v/firecrawl-anydoc.svg)](https://pypi.org/project/firecrawl-anydoc/)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/firecrawl/anydoc/blob/main/LICENSE)
 
-Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files into clean GitHub-Flavored Markdown. Python bindings for the [anydoc](https://github.com/firecrawl/anydoc) Rust crate, built by [Firecrawl](https://firecrawl.dev). Also available as a hosted API through [Firecrawl Parse](https://firecrawl.dev/parse), which adds our OCR models for the scanned pages anydoc can't read on its own.
+Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, HTML, CSV, and PDF files into clean GitHub-Flavored Markdown. Python bindings for the [anydoc](https://github.com/firecrawl/anydoc) Rust crate, built by [Firecrawl](https://firecrawl.dev). Also available as a hosted API through [Firecrawl Parse](https://firecrawl.dev/parse), which adds our OCR models for the scanned pages anydoc can't read on its own.
 
 Every format parses into one shared document model and renders through a single Markdown serializer, so headings, tables, lists, and footnotes come out the same no matter which format goes in. Conversion releases the GIL, so other threads keep running. Type stubs ship with the package.
 
@@ -23,6 +23,7 @@ The package installs as `firecrawl-anydoc` and imports as `anydoc`.
 | OpenDocument     | `.odt`, `.ods`, `.odp`                                     |
 | Rich Text Format | `.rtf`                                                     |
 | EPUB             | `.epub`                                                    |
+| HTML             | `.html`, `.htm`                                            |
 | CSV              | `.csv`                                                     |
 | PDF              | `.pdf`                                                     |
 
@@ -70,7 +71,7 @@ The five conversion failures subclass `anydoc.ConvertError`, so catching that ha
 
 ## Format detection
 
-The format is read from the file content, using the marker its specification designates: the PDF header, the RTF open group, OLE stream names, the ZIP package mimetype and content types. CSV has no such marker, so detection returns `None` for it and the extension, or an explicit format, names it instead.
+The format is read from the file content, using the marker its specification designates: the PDF header, the RTF open group, OLE stream names, the ZIP package mimetype and content types, or an HTML doctype/root element. CSV has no such marker, so detection returns `None` for it and the extension, or an explicit format, names it instead. Standalone HTML is supported; MHTML is not yet supported.
 
 ```python
 anydoc.format_from_bytes(data)  # 'docx', or None when nothing matches

diff --git a/python/anydoc/__init__.py b/python/anydoc/__init__.py
@@ -31,7 +31,7 @@
 )
 
 Format = Literal[
-    "doc", "docx", "odt", "pdf", "ppt", "pptx", "rtf", "epub", "xlsx", "ods", "odp", "csv"
+    "doc", "docx", "odt", "pdf", "ppt", "pptx", "rtf", "epub", "html", "xlsx", "ods", "odp", "csv"
 ]
 """Input format, named after the extension that identifies it. Container
 variants that share a parser (`.docm`, `.xlsm`, `.ppsx`, ...) map onto these

diff --git a/python/anydoc/_anydoc.pyi b/python/anydoc/_anydoc.pyi
@@ -4,7 +4,7 @@ import os
 from typing import Literal, final
 
 Format = Literal[
-    "doc", "docx", "odt", "pdf", "ppt", "pptx", "rtf", "epub", "xlsx", "ods", "odp", "csv"
+    "doc", "docx", "odt", "pdf", "ppt", "pptx", "rtf", "epub", "html", "xlsx", "ods", "odp", "csv"
 ]
 
 class ConvertError(Exception):
@@ -43,9 +43,9 @@ class MissingPartError(ConvertError):
 def format_from_bytes(data: bytes | bytearray) -> Format | None:
     """Detect the format from the content itself: the signature and identity
     each container specification designates (PDF header, RTF open group, OLE
-    stream names, ZIP package mimetype/content types). Plain-text formats
-    (CSV) carry no signature and return `None`; so does anything
-    unrecognized."""
+    stream names, ZIP package mimetype/content types, or an HTML doctype/root
+    element). Plain-text formats (CSV) carry no signature and return `None`; so
+    does anything unrecognized."""
 
 def format_from_extension(extension: str) -> Format | None:
     """The format an extension names, with or without a leading dot."""

diff --git a/python/pyproject.toml b/python/pyproject.toml
@@ -6,7 +6,7 @@ build-backend = "maturin"
 # PyPI is held by an unrelated package) and imports as `anydoc`.
 [project]
 name = "firecrawl-anydoc"
-description = "Convert documents (doc, docx, odt, rtf, epub, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown"
+description = "Convert documents (doc, docx, odt, rtf, epub, html, pdf, presentations, spreadsheets, csv) to GitHub-Flavored Markdown"
 readme = "README.md"
 license = "MIT"
 requires-python = ">=3.10"

diff --git a/python/src/lib.rs b/python/src/lib.rs
@@ -59,7 +59,7 @@ create_exception!(
 /// Format names, as the extension that identifies each format. Container
 /// variants that share a parser (`.docm`, `.xlsm`, `.ppsx`, ...) map onto
 /// these via `format_from_bytes` or `format_from_extension`.
-const FORMATS: [(&str, anydoc::Format); 12] = [
+const FORMATS: [(&str, anydoc::Format); 13] = [
     ("doc", anydoc::Format::Doc),
     ("docx", anydoc::Format::Docx),
     ("odt", anydoc::Format::Odt),
@@ -68,6 +68,7 @@ const FORMATS: [(&str, anydoc::Format); 12] = [
     ("pptx", anydoc::Format::Pptx),
     ("rtf", anydoc::Format::Rtf),
     ("epub", anydoc::Format::Epub),
+    ("html", anydoc::Format::Html),
     ("xlsx", anydoc::Format::Excel),
     ("ods", anydoc::Format::Ods),
     ("odp", anydoc::Format::Odp),
@@ -127,8 +128,9 @@ fn convert_error(py: Python<'_>, error: anydoc::ConvertError) -> PyErr {
 
 /// Detect the format from the content itself: the signature and identity each
 /// container specification designates (PDF header, RTF open group, OLE stream
-/// names, ZIP package mimetype/content types). Plain-text formats (CSV) carry
-/// no signature and return `None`; so does anything unrecognized.
+/// names, ZIP package mimetype/content types, or an HTML doctype/root element).
+/// Plain-text formats (CSV) carry no signature and return `None`; so does
+/// anything unrecognized.
 #[pyfunction]
 fn format_from_bytes(data: Vec<u8>) -> Option<&'static str> {
     anydoc::Format::from_bytes(&data).map(format_name)