html-to-markdown 2.0.1__tar.gz → 2.1.0__tar.gz

{html_to_markdown-2.0.1 → html_to_markdown-2.1.0}/Cargo.lock

@@ -2,6 +2,12 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "adler2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
+
 [[package]]
 name = "aho-corasick"
 version = "1.1.3"
@@ -131,6 +137,18 @@ version = "3.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43"
 
+[[package]]
+name = "bytemuck"
+version = "1.24.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fbdf580320f38b612e485521afda1ee26d10cc9884efaaa750d383e13e3c5f4"
+
+[[package]]
+name = "byteorder-lite"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495"
+
 [[package]]
 name = "cast"
 version = "0.3.0"
@@ -229,12 +247,27 @@ dependencies = [
  "roff",
 ]
 
+[[package]]
+name = "color_quant"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d7b894f5411737b7867f4827955924d7c254fc9f4d91a6aad6b097804b1018b"
+
 [[package]]
 name = "colorchoice"
 version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b05b61dc5112cbb17e4b6cd61790d9845d13888356391624cbe7e41efeac1e75"
 
+[[package]]
+name = "crc32fast"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
+dependencies = [
+ "cfg-if",
+]
+
 [[package]]
 name = "criterion"
 version = "0.5.1"
@@ -394,6 +427,25 @@ version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
+[[package]]
+name = "fdeflate"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e6853b52649d4ac5c0bd02320cddc5ba956bdb407c4b75a2c6b75bf51500f8c"
+dependencies = [
+ "simd-adler32",
+]
+
+[[package]]
+name = "flate2"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc5a4e564e38c699f2880d3fda590bedc2e69f3f84cd48b457bd892ce61d0aa9"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "float-cmp"
 version = "0.10.0"
@@ -434,6 +486,16 @@ dependencies = [
  "wasi",
 ]
 
+[[package]]
+name = "gif"
+version = "0.13.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ae047235e33e2829703574b54fdec96bfbad892062d97fed2f76022287de61b"
+dependencies = [
+ "color_quant",
+ "weezl",
+]
+
 [[package]]
 name = "half"
 version = "2.7.0"
@@ -468,7 +530,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-cli"
-version = "2.0.1"
+version = "2.1.0"
 dependencies = [
  "assert_cmd",
  "clap",
@@ -482,20 +544,23 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-py"
-version = "2.0.1"
+version = "2.1.0"
 dependencies = [
+ "base64",
  "html-to-markdown-rs",
+ "image",
  "pyo3",
 ]
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "2.0.1"
+version = "2.1.0"
 dependencies = [
  "ammonia",
  "base64",
  "criterion",
  "html-escape",
+ "image",
  "once_cell",
  "regex",
  "serde",
@@ -622,6 +687,34 @@ dependencies = [
  "icu_properties",
 ]
 
+[[package]]
+name = "image"
+version = "0.25.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "529feb3e6769d234375c4cf1ee2ce713682b8e76538cb13f9fc23e1400a591e7"
+dependencies = [
+ "bytemuck",
+ "byteorder-lite",
+ "color_quant",
+ "gif",
+ "image-webp",
+ "moxcms",
+ "num-traits",
+ "png",
+ "zune-core",
+ "zune-jpeg",
+]
+
+[[package]]
+name = "image-webp"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "525e9ff3e1a4be2fbea1fdf0e98686a6d98b4d8f937e1bf7402245af1909e8c3"
+dependencies = [
+ "byteorder-lite",
+ "quick-error",
+]
+
 [[package]]
 name = "indoc"
 version = "2.0.6"
@@ -752,6 +845,26 @@ dependencies = [
  "autocfg",
 ]
 
+[[package]]
+name = "miniz_oxide"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
+dependencies = [
+ "adler2",
+ "simd-adler32",
+]
+
+[[package]]
+name = "moxcms"
+version = "0.7.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c588e11a3082784af229e23e8e4ecf5bcc6fbe4f69101e0421ce8d79da7f0b40"
+dependencies = [
+ "num-traits",
+ "pxfm",
+]
+
 [[package]]
 name = "new_debug_unreachable"
 version = "1.0.6"
@@ -900,6 +1013,19 @@ dependencies = [
  "plotters-backend",
 ]
 
+[[package]]
+name = "png"
+version = "0.18.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97baced388464909d42d89643fe4361939af9b7ce7a31ee32a168f832a70f2a0"
+dependencies = [
+ "bitflags",
+ "crc32fast",
+ "fdeflate",
+ "flate2",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "portable-atomic"
 version = "1.11.1"
@@ -960,6 +1086,15 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "pxfm"
+version = "0.1.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3cbdf373972bf78df4d3b518d07003938e2c7d1fb5891e55f9cb6df57009d84"
+dependencies = [
+ "num-traits",
+]
+
 [[package]]
 name = "pyo3"
 version = "0.26.0"
@@ -1021,6 +1156,12 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "quick-error"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
+
 [[package]]
 name = "quote"
 version = "1.0.41"
@@ -1082,9 +1223,9 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.11.3"
+version = "1.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8b5288124840bee7b386bc413c487869b360b2b4ec421ea56425128692f2a82c"
+checksum = "4a52d8d02cacdb176ef4678de6c052efb4b3da14b78e4db683a4252762be5433"
 dependencies = [
  "aho-corasick",
  "memchr",
@@ -1094,9 +1235,9 @@ dependencies = [
 
 [[package]]
 name = "regex-automata"
-version = "0.4.11"
+version = "0.4.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "833eb9ce86d40ef33cb1306d8accf7bc8ec2bfea4355cbdebb3df68b40925cad"
+checksum = "722166aa0d7438abbaa4d5cc2c649dac844e8c56d82fb3d33e9c34b5cd268fc6"
 dependencies = [
  "aho-corasick",
  "memchr",
@@ -1105,9 +1246,9 @@ dependencies = [
 
 [[package]]
 name = "regex-syntax"
-version = "0.8.6"
+version = "0.8.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "caf4aa5b0f434c91fe5c7f1ecb6a5ece2130b02ad2a590589dda5146df959001"
+checksum = "c3160422bbd54dd5ecfdca71e5fd59b7b8fe2b1697ab2baf64f6d05dcc66d298"
 
 [[package]]
 name = "roff"
@@ -1198,6 +1339,12 @@ dependencies = [
  "serde_core",
 ]
 
+[[package]]
+name = "simd-adler32"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d66dc143e6b11c1eddc06d5c423cfc97062865baf299914ab64caa38182078fe"
+
 [[package]]
 name = "siphasher"
 version = "1.0.1"
@@ -1517,6 +1664,12 @@ dependencies = [
  "string_cache_codegen",
 ]
 
+[[package]]
+name = "weezl"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a751b3277700db47d3e574514de2eced5e54dc8a5436a3bf7a0b248b2cee16f3"
+
 [[package]]
 name = "winapi-util"
 version = "0.1.11"
@@ -1797,3 +1950,18 @@ dependencies = [
  "quote",
  "syn",
 ]
+
+[[package]]
+name = "zune-core"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f423a2c17029964870cfaabb1f13dfab7d092a62a29a89264f4d36990ca414a"
+
+[[package]]
+name = "zune-jpeg"
+version = "0.4.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29ce2c8a9384ad323cf564b67da86e21d3cfdff87908bc1223ed5c99bc792713"
+dependencies = [
+ "zune-core",
+]

{html_to_markdown-2.0.1 → html_to_markdown-2.1.0}/Cargo.toml

@@ -3,7 +3,7 @@ resolver = "2"
 members = ["crates/html-to-markdown-py"]
 
 [workspace.package]
-version = "2.0.1"
+version = "2.1.0"
 edition = "2021"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
 license = "MIT"
@@ -15,7 +15,7 @@ rust-version = "1.80"
 
 [workspace.dependencies]
 # Core library
-html-to-markdown-rs = { version = "2.0.1", path = "crates/html-to-markdown" }
+html-to-markdown-rs = { version = "2.1.0", path = "crates/html-to-markdown" }
 
 # HTML parsing and sanitization
 tl = "0.7"

html_to_markdown-2.1.0/PKG-INFO

@@ -0,0 +1,196 @@
+Metadata-Version: 2.4
+Name: html-to-markdown
+Version: 2.1.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Rust
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing
+Classifier: Topic :: Text Processing :: Markup
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Classifier: Typing :: Typed
+License-File: LICENSE
+Summary: High-performance HTML to Markdown converter powered by Rust with a clean Python API
+Keywords: cli-tool,converter,html,html2markdown,html5,markdown,markup,parser,rust,text-processing
+Home-Page: https://github.com/Goldziher/html-to-markdown
+Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Changelog, https://github.com/Goldziher/html-to-markdown/releases
+Project-URL: Homepage, https://github.com/Goldziher/html-to-markdown
+Project-URL: Issues, https://github.com/Goldziher/html-to-markdown/issues
+Project-URL: Repository, https://github.com/Goldziher/html-to-markdown.git
+
+# html-to-markdown
+
+High-performance HTML to Markdown converter with a clean Python API (powered by a Rust core). Wheels are published for Linux, macOS, and Windows.
+
+[![PyPI version](https://badge.fury.io/py/html-to-markdown.svg)](https://github.com/Goldziher/html-to-markdown)
+[![Rust crate](https://img.shields.io/crates/v/html-to-markdown-rs.svg)](https://github.com/Goldziher/html-to-markdown)
+[![Python Versions](https://img.shields.io/pypi/pyversions/html-to-markdown.svg)](https://github.com/Goldziher/html-to-markdown)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/Goldziher/html-to-markdown/blob/main/LICENSE)
+
+## Installation
+
+```bash
+pip install html-to-markdown
+```
+
+## Performance Snapshot
+
+Apple M4 • Real Wikipedia documents • `convert()` (Python)
+
+| Document            | Size  | Latency | Throughput | Docs/sec |
+| ------------------- | ----- | ------- | ---------- | -------- |
+| Lists (Timeline)    | 129KB | 0.62ms  | 208 MB/s   | 1,613    |
+| Tables (Countries)  | 360KB | 2.02ms  | 178 MB/s   | 495      |
+| Mixed (Python wiki) | 656KB | 4.56ms  | 144 MB/s   | 219      |
+
+> V1 averaged ~2.5 MB/s (Python/BeautifulSoup). V2’s Rust engine delivers 60–80× higher throughput.
+
+## Quick Start
+
+```python
+from html_to_markdown import convert
+
+html = """
+<h1>Welcome</h1>
+<p>This is <strong>fast</strong> Rust-powered conversion!</p>
+<ul>
+    <li>Blazing fast</li>
+    <li>Type safe</li>
+    <li>Easy to use</li>
+</ul>
+"""
+
+markdown = convert(html)
+print(markdown)
+```
+
+## Configuration (v2 API)
+
+```python
+from html_to_markdown import ConversionOptions, convert
+
+options = ConversionOptions(
+    heading_style="atx",
+    list_indent_width=2,
+    bullets="*+-",
+)
+options.escape_asterisks = True
+options.code_language = "python"
+options.extract_metadata = True
+
+markdown = convert(html, options)
+```
+
+### HTML Preprocessing
+
+```python
+from html_to_markdown import ConversionOptions, PreprocessingOptions, convert
+
+options = ConversionOptions(
+    preprocessing=PreprocessingOptions(enabled=True, preset="aggressive"),
+)
+
+markdown = convert(scraped_html, options)
+```
+
+### Inline Image Extraction
+
+```python
+from html_to_markdown import InlineImageConfig, convert_with_inline_images
+
+markdown, inline_images, warnings = convert_with_inline_images(
+    '<p><img src="data:image/png;base64,...==" alt="Pixel" width="1" height="1"></p>',
+    image_config=InlineImageConfig(max_decoded_size_bytes=1024, infer_dimensions=True),
+)
+
+if inline_images:
+    first = inline_images[0]
+    print(first["format"], first["dimensions"], first["attributes"])  # e.g. "png", (1, 1), {"width": "1"}
+```
+
+Each inline image is returned as a typed dictionary (`bytes` payload, metadata, and relevant HTML attributes). Warnings are human-readable skip reasons.
+
+### hOCR (HTML OCR) Support
+
+```python
+from html_to_markdown import ConversionOptions, convert
+
+# Default: emit structured Markdown directly
+markdown = convert(hocr_html)
+
+# hOCR documents are detected automatically; tables are reconstructed without extra configuration.
+markdown = convert(hocr_html)
+```
+
+## CLI (same engine)
+
+```bash
+pipx install html-to-markdown  # or: pip install html-to-markdown
+
+html-to-markdown page.html > page.md
+cat page.html | html-to-markdown --heading-style atx > page.md
+```
+
+## API Surface
+
+### `ConversionOptions`
+
+Key fields (see docstring for full matrix):
+
+- `heading_style`: `"underlined" | "atx" | "atx_closed"`
+- `list_indent_width`: spaces per indent level (default 2)
+- `bullets`: cycle of bullet characters (`"*+-"`)
+- `strong_em_symbol`: `"*"` or `"_"`
+- `code_language`: default fenced code block language
+- `wrap`, `wrap_width`: wrap Markdown output
+- `strip_tags`: remove specific HTML tags
+- `preprocessing`: `PreprocessingOptions`
+- `encoding`: input character encoding (informational)
+
+### `PreprocessingOptions`
+
+- `enabled`: enable HTML sanitisation
+- `preset`: `"minimal" | "standard" | "aggressive"`
+- `remove_navigation`, `remove_forms`
+
+### `InlineImageConfig`
+
+- `max_decoded_size_bytes`: reject larger payloads
+- `filename_prefix`: generated name prefix (`embedded_image` default)
+- `capture_svg`: collect inline `<svg>` (default `True`)
+- `infer_dimensions`: decode raster images to obtain dimensions (default `False`)
+
+## v1 Compatibility
+
+- **Performance**: V1 averaged ~2.5 MB/s; V2 sustains 150–210 MB/s with identical Markdown output.
+- **Compat shim**: `html_to_markdown.v1_compat` exposes `convert_to_markdown`, `convert_to_markdown_stream`, and `markdownify` to ease migration. Keyword mappings are listed in the [changelog](CHANGELOG.md#v200).
+- **CLI**: The Rust CLI replaces the Python script. New flags are documented via `html-to-markdown --help`.
+- **Removed options**: `code_language_callback`, `strip`, and streaming APIs were removed; use `ConversionOptions`, `PreprocessingOptions`, and the inline-image helpers instead.
+
+## Links
+
+- GitHub: [https://github.com/Goldziher/html-to-markdown](https://github.com/Goldziher/html-to-markdown)
+- Discord: [https://discord.gg/pXxagNK2zN](https://discord.gg/pXxagNK2zN)
+- Kreuzberg ecosystem: [https://kreuzberg.dev](https://kreuzberg.dev)
+
+## License
+
+MIT License – see [LICENSE](https://github.com/Goldziher/html-to-markdown/blob/main/LICENSE).
+
+## Support
+
+If you find this library useful, consider [sponsoring the project](https://github.com/sponsors/Goldziher).
+

html_to_markdown-2.1.0/README_PYPI.md

@@ -0,0 +1,162 @@
+# html-to-markdown
+
+High-performance HTML to Markdown converter with a clean Python API (powered by a Rust core). Wheels are published for Linux, macOS, and Windows.
+
+[![PyPI version](https://badge.fury.io/py/html-to-markdown.svg)](https://github.com/Goldziher/html-to-markdown)
+[![Rust crate](https://img.shields.io/crates/v/html-to-markdown-rs.svg)](https://github.com/Goldziher/html-to-markdown)
+[![Python Versions](https://img.shields.io/pypi/pyversions/html-to-markdown.svg)](https://github.com/Goldziher/html-to-markdown)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/Goldziher/html-to-markdown/blob/main/LICENSE)
+
+## Installation
+
+```bash
+pip install html-to-markdown
+```
+
+## Performance Snapshot
+
+Apple M4 • Real Wikipedia documents • `convert()` (Python)
+
+| Document            | Size  | Latency | Throughput | Docs/sec |
+| ------------------- | ----- | ------- | ---------- | -------- |
+| Lists (Timeline)    | 129KB | 0.62ms  | 208 MB/s   | 1,613    |
+| Tables (Countries)  | 360KB | 2.02ms  | 178 MB/s   | 495      |
+| Mixed (Python wiki) | 656KB | 4.56ms  | 144 MB/s   | 219      |
+
+> V1 averaged ~2.5 MB/s (Python/BeautifulSoup). V2’s Rust engine delivers 60–80× higher throughput.
+
+## Quick Start
+
+```python
+from html_to_markdown import convert
+
+html = """
+<h1>Welcome</h1>
+<p>This is <strong>fast</strong> Rust-powered conversion!</p>
+<ul>
+    <li>Blazing fast</li>
+    <li>Type safe</li>
+    <li>Easy to use</li>
+</ul>
+"""
+
+markdown = convert(html)
+print(markdown)
+```
+
+## Configuration (v2 API)
+
+```python
+from html_to_markdown import ConversionOptions, convert
+
+options = ConversionOptions(
+    heading_style="atx",
+    list_indent_width=2,
+    bullets="*+-",
+)
+options.escape_asterisks = True
+options.code_language = "python"
+options.extract_metadata = True
+
+markdown = convert(html, options)
+```
+
+### HTML Preprocessing
+
+```python
+from html_to_markdown import ConversionOptions, PreprocessingOptions, convert
+
+options = ConversionOptions(
+    preprocessing=PreprocessingOptions(enabled=True, preset="aggressive"),
+)
+
+markdown = convert(scraped_html, options)
+```
+
+### Inline Image Extraction
+
+```python
+from html_to_markdown import InlineImageConfig, convert_with_inline_images
+
+markdown, inline_images, warnings = convert_with_inline_images(
+    '<p><img src="data:image/png;base64,...==" alt="Pixel" width="1" height="1"></p>',
+    image_config=InlineImageConfig(max_decoded_size_bytes=1024, infer_dimensions=True),
+)
+
+if inline_images:
+    first = inline_images[0]
+    print(first["format"], first["dimensions"], first["attributes"])  # e.g. "png", (1, 1), {"width": "1"}
+```
+
+Each inline image is returned as a typed dictionary (`bytes` payload, metadata, and relevant HTML attributes). Warnings are human-readable skip reasons.
+
+### hOCR (HTML OCR) Support
+
+```python
+from html_to_markdown import ConversionOptions, convert
+
+# Default: emit structured Markdown directly
+markdown = convert(hocr_html)
+
+# hOCR documents are detected automatically; tables are reconstructed without extra configuration.
+markdown = convert(hocr_html)
+```
+
+## CLI (same engine)
+
+```bash
+pipx install html-to-markdown  # or: pip install html-to-markdown
+
+html-to-markdown page.html > page.md
+cat page.html | html-to-markdown --heading-style atx > page.md
+```
+
+## API Surface
+
+### `ConversionOptions`
+
+Key fields (see docstring for full matrix):
+
+- `heading_style`: `"underlined" | "atx" | "atx_closed"`
+- `list_indent_width`: spaces per indent level (default 2)
+- `bullets`: cycle of bullet characters (`"*+-"`)
+- `strong_em_symbol`: `"*"` or `"_"`
+- `code_language`: default fenced code block language
+- `wrap`, `wrap_width`: wrap Markdown output
+- `strip_tags`: remove specific HTML tags
+- `preprocessing`: `PreprocessingOptions`
+- `encoding`: input character encoding (informational)
+
+### `PreprocessingOptions`
+
+- `enabled`: enable HTML sanitisation
+- `preset`: `"minimal" | "standard" | "aggressive"`
+- `remove_navigation`, `remove_forms`
+
+### `InlineImageConfig`
+
+- `max_decoded_size_bytes`: reject larger payloads
+- `filename_prefix`: generated name prefix (`embedded_image` default)
+- `capture_svg`: collect inline `<svg>` (default `True`)
+- `infer_dimensions`: decode raster images to obtain dimensions (default `False`)
+
+## v1 Compatibility
+
+- **Performance**: V1 averaged ~2.5 MB/s; V2 sustains 150–210 MB/s with identical Markdown output.
+- **Compat shim**: `html_to_markdown.v1_compat` exposes `convert_to_markdown`, `convert_to_markdown_stream`, and `markdownify` to ease migration. Keyword mappings are listed in the [changelog](CHANGELOG.md#v200).
+- **CLI**: The Rust CLI replaces the Python script. New flags are documented via `html-to-markdown --help`.
+- **Removed options**: `code_language_callback`, `strip`, and streaming APIs were removed; use `ConversionOptions`, `PreprocessingOptions`, and the inline-image helpers instead.
+
+## Links
+
+- GitHub: [https://github.com/Goldziher/html-to-markdown](https://github.com/Goldziher/html-to-markdown)
+- Discord: [https://discord.gg/pXxagNK2zN](https://discord.gg/pXxagNK2zN)
+- Kreuzberg ecosystem: [https://kreuzberg.dev](https://kreuzberg.dev)
+
+## License
+
+MIT License – see [LICENSE](https://github.com/Goldziher/html-to-markdown/blob/main/LICENSE).
+
+## Support
+
+If you find this library useful, consider [sponsoring the project](https://github.com/sponsors/Goldziher).