html-to-markdown 1.1.0__tar.gz → 1.2.1__tar.gz

{html_to_markdown-1.1.0 → html_to_markdown-1.2.1}/.gitignore

@@ -5,6 +5,7 @@
 .coverage
 .env
 .idea/
+.run/
 .mypy_cache/
 .pdm-build/
 .pdm-python

{html_to_markdown-1.1.0 → html_to_markdown-1.2.1}/LICENSE

@@ -1,7 +1,7 @@
 The MIT License (MIT)
 
 Copyright 2012-2018 Matthew Tretter
-Copyright 2024 Na'aman Hirschfeld
+Copyright 2024-2025 Na'aman Hirschfeld
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

html_to_markdown-1.2.1/PKG-INFO

@@ -0,0 +1,220 @@
+Metadata-Version: 2.4
+Name: html-to-markdown
+Version: 1.2.1
+Summary: Convert HTML to markdown
+Project-URL: homepage, https://github.com/Goldziher/html-to-markdown
+Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: converter,html,markdown,text-extraction,text-processing
+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 :: 3.9
+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: Topic :: Text Processing
+Classifier: Topic :: Text Processing :: Markup
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Classifier: Topic :: Utilities
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Requires-Dist: beautifulsoup4>=4.12.3
+Description-Content-Type: text/markdown
+
+# html-to-markdown
+
+A modern, fully typed Python library for converting HTML to Markdown. This library is a completely rewritten fork
+of [markdownify](https://pypi.org/project/markdownify/) with a modernized codebase, strict type safety and support for
+Python 3.9+.
+
+## Features
+
+- Full type safety with strict MyPy adherence
+- Functional API design
+- Extensive test coverage
+- Configurable conversion options
+- CLI tool for easy conversions
+- Support for pre-configured BeautifulSoup instances
+- Strict semver versioning
+
+## Installation
+
+```shell
+pip install html-to-markdown
+```
+
+## Quick Start
+
+Convert HTML to Markdown with a single function call:
+
+```python
+from html_to_markdown import convert_to_markdown
+
+html = """
+<article>
+    <h1>Welcome</h1>
+    <p>This is a <strong>sample</strong> with a <a href="https://example.com">link</a>.</p>
+    <ul>
+        <li>Item 1</li>
+        <li>Item 2</li>
+    </ul>
+</article>
+"""
+
+markdown = convert_to_markdown(html)
+print(markdown)
+```
+
+Output:
+
+```markdown
+# Welcome
+
+This is a **sample** with a [link](https://example.com).
+
+* Item 1
+* Item 2
+```
+
+### Working with BeautifulSoup
+
+If you need more control over HTML parsing, you can pass a pre-configured BeautifulSoup instance:
+
+```python
+from bs4 import BeautifulSoup
+from html_to_markdown import convert_to_markdown
+
+# Configure BeautifulSoup with your preferred parser
+soup = BeautifulSoup(html, "lxml")  # Note: lxml requires additional installation
+markdown = convert_to_markdown(soup)
+```
+
+## Advanced Usage
+
+### Customizing Conversion Options
+
+The library offers extensive customization through various options:
+
+```python
+from html_to_markdown import convert_to_markdown
+
+html = "<div>Your content here...</div>"
+markdown = convert_to_markdown(
+    html,
+    heading_style="atx",  # Use # style headers
+    strong_em_symbol="*",  # Use * for bold/italic
+    bullets="*+-",  # Define bullet point characters
+    wrap=True,  # Enable text wrapping
+    wrap_width=100,  # Set wrap width
+    escape_asterisks=True,  # Escape * characters
+    code_language="python",  # Default code block language
+)
+```
+
+### Configuration Options
+
+| Option               | Type | Default        | Description                                            |
+| -------------------- | ---- | -------------- | ------------------------------------------------------ |
+| `autolinks`          | bool | `True`         | Auto-convert URLs to Markdown links                    |
+| `bullets`            | str  | `'*+-'`        | Characters to use for bullet points                    |
+| `code_language`      | str  | `''`           | Default language for code blocks                       |
+| `heading_style`      | str  | `'underlined'` | Header style (`'underlined'`, `'atx'`, `'atx_closed'`) |
+| `escape_asterisks`   | bool | `True`         | Escape * characters                                    |
+| `escape_underscores` | bool | `True`         | Escape _ characters                                    |
+| `wrap`               | bool | `False`        | Enable text wrapping                                   |
+| `wrap_width`         | int  | `80`           | Text wrap width                                        |
+
+For a complete list of options, see the [Configuration](#configuration) section below.
+
+## CLI Usage
+
+Convert HTML files directly from the command line:
+
+```shell
+# Convert a file
+html_to_markdown input.html > output.md
+
+# Process stdin
+cat input.html | html_to_markdown > output.md
+
+# Use custom options
+html_to_markdown --heading-style atx --wrap --wrap-width 100 input.html > output.md
+```
+
+View all available options:
+
+```shell
+html_to_markdown --help
+```
+
+## Migration from Markdownify
+
+For existing projects using Markdownify, a compatibility layer is provided:
+
+```python
+# Old code
+from markdownify import markdownify as md
+
+# New code - works the same way
+from html_to_markdown import markdownify as md
+```
+
+The `markdownify` function is an alias for `convert_to_markdown` and provides identical functionality.
+
+## Configuration
+
+Full list of configuration options:
+
+- `autolinks`: Convert valid URLs to Markdown links automatically
+- `bullets`: Characters to use for bullet points in lists
+- `code_language`: Default language for fenced code blocks
+- `code_language_callback`: Function to determine code block language
+- `convert`: List of HTML tags to convert (None = all supported tags)
+- `default_title`: Use default titles for elements like links
+- `escape_asterisks`: Escape * characters
+- `escape_misc`: Escape miscellaneous Markdown characters
+- `escape_underscores`: Escape _ characters
+- `heading_style`: Header style (underlined/atx/atx_closed)
+- `keep_inline_images_in`: Tags where inline images should be kept
+- `newline_style`: Style for handling newlines (spaces/backslash)
+- `strip`: Tags to remove from output
+- `strong_em_symbol`: Symbol for strong/emphasized text (\* or \_)
+- `sub_symbol`: Symbol for subscript text
+- `sup_symbol`: Symbol for superscript text
+- `wrap`: Enable text wrapping
+- `wrap_width`: Width for text wrapping
+- `convert_as_inline`: Treat content as inline elements
+
+## Contribution
+
+This library is open to contribution. Feel free to open issues or submit PRs. Its better to discuss issues before
+submitting PRs to avoid disappointment.
+
+### Local Development
+
+1. Clone the repo
+
+1. Install the system dependencies
+
+1. Install the full dependencies with `uv sync`
+
+1. Install the pre-commit hooks with:
+
+    ```shell
+    pre-commit install && pre-commit install --hook-type commit-msg
+    ```
+
+1. Make your changes and submit a PR
+
+## License
+
+This library uses the MIT license.
+
+## Acknowledgments
+
+Special thanks to the original [markdownify](https://pypi.org/project/markdownify/) project creators and contributors.

html_to_markdown-1.2.1/README.md

@@ -0,0 +1,192 @@
+# html-to-markdown
+
+A modern, fully typed Python library for converting HTML to Markdown. This library is a completely rewritten fork
+of [markdownify](https://pypi.org/project/markdownify/) with a modernized codebase, strict type safety and support for
+Python 3.9+.
+
+## Features
+
+- Full type safety with strict MyPy adherence
+- Functional API design
+- Extensive test coverage
+- Configurable conversion options
+- CLI tool for easy conversions
+- Support for pre-configured BeautifulSoup instances
+- Strict semver versioning
+
+## Installation
+
+```shell
+pip install html-to-markdown
+```
+
+## Quick Start
+
+Convert HTML to Markdown with a single function call:
+
+```python
+from html_to_markdown import convert_to_markdown
+
+html = """
+<article>
+    <h1>Welcome</h1>
+    <p>This is a <strong>sample</strong> with a <a href="https://example.com">link</a>.</p>
+    <ul>
+        <li>Item 1</li>
+        <li>Item 2</li>
+    </ul>
+</article>
+"""
+
+markdown = convert_to_markdown(html)
+print(markdown)
+```
+
+Output:
+
+```markdown
+# Welcome
+
+This is a **sample** with a [link](https://example.com).
+
+* Item 1
+* Item 2
+```
+
+### Working with BeautifulSoup
+
+If you need more control over HTML parsing, you can pass a pre-configured BeautifulSoup instance:
+
+```python
+from bs4 import BeautifulSoup
+from html_to_markdown import convert_to_markdown
+
+# Configure BeautifulSoup with your preferred parser
+soup = BeautifulSoup(html, "lxml")  # Note: lxml requires additional installation
+markdown = convert_to_markdown(soup)
+```
+
+## Advanced Usage
+
+### Customizing Conversion Options
+
+The library offers extensive customization through various options:
+
+```python
+from html_to_markdown import convert_to_markdown
+
+html = "<div>Your content here...</div>"
+markdown = convert_to_markdown(
+    html,
+    heading_style="atx",  # Use # style headers
+    strong_em_symbol="*",  # Use * for bold/italic
+    bullets="*+-",  # Define bullet point characters
+    wrap=True,  # Enable text wrapping
+    wrap_width=100,  # Set wrap width
+    escape_asterisks=True,  # Escape * characters
+    code_language="python",  # Default code block language
+)
+```
+
+### Configuration Options
+
+| Option               | Type | Default        | Description                                            |
+| -------------------- | ---- | -------------- | ------------------------------------------------------ |
+| `autolinks`          | bool | `True`         | Auto-convert URLs to Markdown links                    |
+| `bullets`            | str  | `'*+-'`        | Characters to use for bullet points                    |
+| `code_language`      | str  | `''`           | Default language for code blocks                       |
+| `heading_style`      | str  | `'underlined'` | Header style (`'underlined'`, `'atx'`, `'atx_closed'`) |
+| `escape_asterisks`   | bool | `True`         | Escape * characters                                    |
+| `escape_underscores` | bool | `True`         | Escape _ characters                                    |
+| `wrap`               | bool | `False`        | Enable text wrapping                                   |
+| `wrap_width`         | int  | `80`           | Text wrap width                                        |
+
+For a complete list of options, see the [Configuration](#configuration) section below.
+
+## CLI Usage
+
+Convert HTML files directly from the command line:
+
+```shell
+# Convert a file
+html_to_markdown input.html > output.md
+
+# Process stdin
+cat input.html | html_to_markdown > output.md
+
+# Use custom options
+html_to_markdown --heading-style atx --wrap --wrap-width 100 input.html > output.md
+```
+
+View all available options:
+
+```shell
+html_to_markdown --help
+```
+
+## Migration from Markdownify
+
+For existing projects using Markdownify, a compatibility layer is provided:
+
+```python
+# Old code
+from markdownify import markdownify as md
+
+# New code - works the same way
+from html_to_markdown import markdownify as md
+```
+
+The `markdownify` function is an alias for `convert_to_markdown` and provides identical functionality.
+
+## Configuration
+
+Full list of configuration options:
+
+- `autolinks`: Convert valid URLs to Markdown links automatically
+- `bullets`: Characters to use for bullet points in lists
+- `code_language`: Default language for fenced code blocks
+- `code_language_callback`: Function to determine code block language
+- `convert`: List of HTML tags to convert (None = all supported tags)
+- `default_title`: Use default titles for elements like links
+- `escape_asterisks`: Escape * characters
+- `escape_misc`: Escape miscellaneous Markdown characters
+- `escape_underscores`: Escape _ characters
+- `heading_style`: Header style (underlined/atx/atx_closed)
+- `keep_inline_images_in`: Tags where inline images should be kept
+- `newline_style`: Style for handling newlines (spaces/backslash)
+- `strip`: Tags to remove from output
+- `strong_em_symbol`: Symbol for strong/emphasized text (\* or \_)
+- `sub_symbol`: Symbol for subscript text
+- `sup_symbol`: Symbol for superscript text
+- `wrap`: Enable text wrapping
+- `wrap_width`: Width for text wrapping
+- `convert_as_inline`: Treat content as inline elements
+
+## Contribution
+
+This library is open to contribution. Feel free to open issues or submit PRs. Its better to discuss issues before
+submitting PRs to avoid disappointment.
+
+### Local Development
+
+1. Clone the repo
+
+1. Install the system dependencies
+
+1. Install the full dependencies with `uv sync`
+
+1. Install the pre-commit hooks with:
+
+    ```shell
+    pre-commit install && pre-commit install --hook-type commit-msg
+    ```
+
+1. Make your changes and submit a PR
+
+## License
+
+This library uses the MIT license.
+
+## Acknowledgments
+
+Special thanks to the original [markdownify](https://pypi.org/project/markdownify/) project creators and contributors.

html_to_markdown-1.2.1/html_to_markdown/__init__.py

@@ -0,0 +1,5 @@
+from html_to_markdown.processing import convert_to_markdown
+
+markdownify = convert_to_markdown
+
+__all__ = ["convert_to_markdown", "markdownify"]

html_to_markdown-1.2.1/html_to_markdown/__main__.py

@@ -0,0 +1,11 @@
+import sys
+
+if __name__ == "__main__":
+    from html_to_markdown.cli import main
+
+    try:
+        result = main(sys.argv[1:])
+        print(result)  # noqa: T201
+    except ValueError as e:
+        print(str(e), file=sys.stderr)  # noqa: T201
+        sys.exit(1)

html_to_markdown-1.2.1/html_to_markdown/constants.py

@@ -0,0 +1,18 @@
+from __future__ import annotations
+
+import re
+from re import Pattern
+from typing import Final
+
+convert_heading_re: Final[Pattern[str]] = re.compile(r"convert_h(\d+)")
+line_beginning_re: Final[Pattern[str]] = re.compile(r"^", re.MULTILINE)
+whitespace_re: Final[Pattern[str]] = re.compile(r"[\t ]+")
+html_heading_re: Final[Pattern[str]] = re.compile(r"h[1-6]")
+
+ASTERISK: Final = "*"
+ATX: Final = "atx"
+ATX_CLOSED: Final = "atx_closed"
+BACKSLASH: Final = "backslash"
+UNDERLINED: Final = "underlined"
+SPACES: Final = "spaces"
+UNDERSCORE: Final = "_"

{html_to_markdown-1.1.0 → html_to_markdown-1.2.1}/html_to_markdown/converters.py

@@ -55,17 +55,19 @@ SupportedElements = Literal[
     "kbd",
 ]
 
-ConverterssMap = Mapping[SupportedElements, Callable[[str, Tag], str]]
+ConvertersMap = Mapping[SupportedElements, Callable[[str, Tag], str]]
 
 T = TypeVar("T")
 
 
 def _create_inline_converter(markup_prefix: str) -> Callable[[Tag, str], str]:
-    """This abstracts all simple inline tags like b, em, del, ...
-    Returns a function that wraps the chomped text in a pair of the string
-    that is returned by markup_fn, with '/' inserted in the string used after
-    the text if it looks like an HTML tag. markup_fn is necessary to allow for
-    references to self.strong_em_symbol etc.
+    """Create an inline converter for a markup pattern or tag.
+
+    Args:
+        markup_prefix: The markup prefix to insert.
+
+    Returns:
+        A function that can be used to convert HTML to Markdown.
     """
 
     def implementation(*, tag: Tag, text: str) -> str:
@@ -83,7 +85,7 @@ def _create_inline_converter(markup_prefix: str) -> Callable[[Tag, str], str]:
 
         return f"{prefix}{markup_prefix}{text}{markup_suffix}{suffix}"
 
-    return cast(Callable[[Tag, str], str], implementation)
+    return cast("Callable[[Tag, str], str]", implementation)
 
 
 def _get_colspan(tag: Tag) -> int:
@@ -185,7 +187,7 @@ def _convert_li(*, tag: Tag, text: str, bullets: str) -> str:
     parent = tag.parent
     if parent is not None and parent.name == "ol":
         start = (
-            int(cast(str, parent["start"]))
+            int(cast("str", parent["start"]))
             if isinstance(parent.get("start"), str) and str(parent.get("start")).isnumeric()
             else 1
         )
@@ -261,7 +263,6 @@ def _convert_tr(*, tag: Tag, text: str) -> str:
     overline = ""
     underline = ""
     if is_headrow and not tag.previous_sibling:
-        # first row and is headline: print headline underline
         full_colspan = 0
         for cell in cells:
             if "colspan" in cell.attrs and cell["colspan"].isdigit():
@@ -270,12 +271,8 @@ def _convert_tr(*, tag: Tag, text: str) -> str:
                 full_colspan += 1
         underline += "| " + " | ".join(["---"] * full_colspan) + " |" + "\n"
     elif not tag.previous_sibling and (
-        parent_name == "table" or (parent_name == "tbody" and not cast(Tag, tag.parent).previous_sibling)
+        parent_name == "table" or (parent_name == "tbody" and not cast("Tag", tag.parent).previous_sibling)
     ):
-        # first row, not headline, and:
-        # - the parent is table or
-        # - the parent is tbody at the beginning of a table.
-        # print empty headline above this row
         overline += "| " + " | ".join([""] * len(cells)) + " |" + "\n"
         overline += "| " + " | ".join(["---"] * len(cells)) + " |" + "\n"
     return overline + "|" + text + "\n" + underline
@@ -295,7 +292,7 @@ def create_converters_map(
     sup_symbol: str,
     wrap: bool,
     wrap_width: int,
-) -> ConverterssMap:
+) -> ConvertersMap:
     """Create a mapping of HTML elements to their corresponding conversion functions.
 
     Args:
@@ -332,7 +329,7 @@ def create_converters_map(
                 return func(**kwargs)
             return func(text)
 
-        return cast(Callable[[str, Tag], T], _inner)
+        return cast("Callable[[str, Tag], T]", _inner)
 
     return {
         "a": _wrapper(partial(_convert_a, autolinks=autolinks, default_title=default_title)),

{html_to_markdown-1.1.0 → html_to_markdown-1.2.1}/html_to_markdown/processing.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from itertools import chain
 from typing import TYPE_CHECKING, Any, Callable, Literal, cast
 
 from bs4 import BeautifulSoup, Comment, Doctype, NavigableString, Tag
@@ -11,7 +12,7 @@ from html_to_markdown.constants import (
     html_heading_re,
     whitespace_re,
 )
-from html_to_markdown.converters import ConverterssMap, create_converters_map
+from html_to_markdown.converters import ConvertersMap, create_converters_map
 from html_to_markdown.utils import escape
 
 if TYPE_CHECKING:
@@ -76,18 +77,23 @@ def _is_nested_tag(el: PageElement) -> bool:
 
 def _process_tag(
     tag: Tag,
-    converters_map: ConverterssMap,
+    converters_map: ConvertersMap,
     *,
-    convert: Iterable[str] | None,
+    convert: set[str] | None,
     convert_as_inline: bool = False,
     escape_asterisks: bool,
     escape_misc: bool,
     escape_underscores: bool,
-    strip: Iterable[str] | None,
+    strip: set[str] | None,
 ) -> str:
+    should_convert_tag = _should_convert_tag(tag_name=tag.name, strip=strip, convert=convert)
+    tag_name: SupportedTag | None = (
+        cast("SupportedTag", tag.name.lower()) if tag.name.lower() in converters_map else None
+    )
     text = ""
+
     is_heading = html_heading_re.match(tag.name) is not None
-    is_cell = tag.name in {"td", "th"}
+    is_cell = tag_name in {"td", "th"}
     convert_children_as_inline = convert_as_inline or is_heading or is_cell
 
     if _is_nested_tag(tag):
@@ -121,9 +127,7 @@ def _process_tag(
                 strip=strip,
             )
 
-    tag_name: SupportedTag | None = cast(SupportedTag, tag.name.lower()) if tag.name.lower() in converters_map else None
-
-    if tag_name and _should_convert_tag(tag_name=tag.name, strip=strip, convert=convert):
+    if tag_name and should_convert_tag:
         return converters_map[tag_name](  # type: ignore[call-arg]
             tag=tag, text=text, convert_as_inline=convert_as_inline
         )
@@ -140,11 +144,9 @@ def _process_text(
 ) -> str:
     text = str(el) or ""
 
-    # normalize whitespace if we're not inside a preformatted element
     if not el.find_parent("pre"):
         text = whitespace_re.sub(" ", text)
 
-    # escape special characters if we're not inside a preformatted or code element
     if not el.find_parent(["pre", "code", "kbd", "samp"]):
         text = escape(
             text=text,
@@ -153,9 +155,6 @@ def _process_text(
             escape_underscores=escape_underscores,
         )
 
-    # remove trailing whitespaces if any of the following condition is true:
-    # - current text node is the last node in li
-    # - current text node is followed by an embedded list
     if (
         el.parent
         and el.parent.name == "li"
@@ -166,7 +165,7 @@ def _process_text(
     return text
 
 
-def _should_convert_tag(*, tag_name: str, strip: Iterable[str] | None, convert: Iterable[str] | None) -> bool:
+def _should_convert_tag(*, tag_name: str, strip: set[str] | None, convert: set[str] | None) -> bool:
     if strip is not None:
         return tag_name not in strip
     if convert is not None:
@@ -174,6 +173,14 @@ def _should_convert_tag(*, tag_name: str, strip: Iterable[str] | None, convert:
     return True
 
 
+def _as_optional_set(value: str | Iterable[str] | None) -> set[str] | None:
+    if value is None:
+        return None
+    if isinstance(value, str):
+        return set(",".split(value))
+    return {*chain(*[v.split(",") for v in value])}
+
+
 def convert_to_markdown(
     source: str | BeautifulSoup,
     *,
@@ -181,7 +188,7 @@ def convert_to_markdown(
     bullets: str = "*+-",
     code_language: str = "",
     code_language_callback: Callable[[Any], str] | None = None,
-    convert: Iterable[str] | None = None,
+    convert: str | Iterable[str] | None = None,
     default_title: bool = False,
     escape_asterisks: bool = True,
     escape_misc: bool = True,
@@ -189,7 +196,7 @@ def convert_to_markdown(
     heading_style: Literal["underlined", "atx", "atx_closed"] = UNDERLINED,
     keep_inline_images_in: Iterable[str] | None = None,
     newline_style: Literal["spaces", "backslash"] = SPACES,
-    strip: Iterable[str] | None = None,
+    strip: str | Iterable[str] | None = None,
     strong_em_symbol: Literal["*", "_"] = ASTERISK,
     sub_symbol: str = "",
     sup_symbol: str = "",
@@ -221,13 +228,22 @@ def convert_to_markdown(
         wrap_width: The number of characters at which to wrap text. Defaults to 80.
         convert_as_inline: Treat the content as inline elements (no block elements like paragraphs). Defaults to False.
 
+    Raises:
+        ValueError: If both 'strip' and 'convert' are specified, or when the input HTML is empty.
+
     Returns:
         str: A string of Markdown-formatted text converted from the given HTML.
     """
     if isinstance(source, str):
         from bs4 import BeautifulSoup
 
-        source = BeautifulSoup(source, "html.parser")
+        if "".join(source.split("\n")):
+            source = BeautifulSoup(source, "html.parser")
+        else:
+            raise ValueError("The input HTML is empty.")
+
+    if strip is not None and convert is not None:
+        raise ValueError("Only one of 'strip' and 'convert' can be specified.")
 
     converters_map = create_converters_map(
         autolinks=autolinks,
@@ -248,10 +264,10 @@ def convert_to_markdown(
     return _process_tag(
         source,
         converters_map,
-        convert=convert,
+        convert=_as_optional_set(convert),
         convert_as_inline=convert_as_inline,
         escape_asterisks=escape_asterisks,
         escape_misc=escape_misc,
         escape_underscores=escape_underscores,
-        strip=strip,
+        strip=_as_optional_set(strip),
     )

html_to_markdown-1.2.1/pyproject.toml

@@ -0,0 +1,115 @@
+[build-system]
+build-backend = "hatchling.build"
+
+requires = [ "hatchling" ]
+
+[project]
+name = "html-to-markdown"
+version = "1.2.1"
+description = "Convert HTML to markdown"
+readme = "README.md"
+keywords = [ "converter", "html", "markdown", "text-extraction", "text-processing" ]
+license = { text = "MIT" }
+authors = [ { name = "Na'aman Hirschfeld", email = "nhirschfeld@gmail.com" } ]
+requires-python = ">=3.9"
+classifiers = [
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Text Processing",
+  "Topic :: Text Processing :: Markup",
+  "Topic :: Text Processing :: Markup :: HTML",
+  "Topic :: Text Processing :: Markup :: Markdown",
+  "Topic :: Utilities",
+  "Typing :: Typed",
+]
+
+dependencies = [
+  "beautifulsoup4>=4.12.3",
+]
+
+urls.homepage = "https://github.com/Goldziher/html-to-markdown"
+
+[dependency-groups]
+dev = [
+  "covdefaults>=2.3",
+  "mypy>=1.14.1",
+  "pre-commit>=4.1",
+  "pytest>=8.3.4",
+  "pytest-cov>=6",
+  "pytest-mock>=3.14",
+  "ruff>=0.9.3",
+  "types-beautifulsoup4>=4.12.0.20241020",
+]
+
+[tool.hatch.build]
+skip-excluded-dirs = true
+
+[tool.hatch.build.targets.sdist]
+only-include = [ "html_to_markdown" ]
+
+[tool.hatch.build.targets.wheel]
+only-include = [ "html_to_markdown" ]
+
+[tool.ruff]
+target-version = "py39"
+line-length = 120
+src = [ "html_to_markdown", "tests" ]
+
+format.docstring-code-line-length = 120
+format.docstring-code-format = true
+lint.select = [ "ALL" ]
+lint.ignore = [
+  "ANN401",  # dynamically typed ANY
+  "COM812",  # Conflicts with formatter
+  "D100",    # # pydocstyle - missing docstring in public module
+  "D104",    # pydocstyle - missing docstring in public package
+  "D107",    # pydocstyle - missing docstring in __init__
+  "D205",    # pydocstyle - 1 blank line required between summary line and description
+  "E501",    # pycodestyle line too long, handled by ruff format
+  "EM",      # Exception messages,
+  "FBT",     # Boolean Args
+  "FIX",     # we allow todo and fixme comments
+  "ISC001",  # Conflicts with formatter
+  "PLR0913", # Pylint - too many arguments.
+  "PLR2004", # Magic variables, we allow them
+  "TD",      # we allow todo and fixme comments
+  "TRY",     # Try except block, rules are too strict
+]
+lint.per-file-ignores."tests/**/*.*" = [ "ARG", "D", "PD", "PT006", "PT013", "S" ]
+lint.isort.known-first-party = [ "html_to_markdown", "tests" ]
+lint.pydocstyle.convention = "google"
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+
+[tool.coverage.run]
+omit = [ "tests/*" ]
+plugins = [ "covdefaults" ]
+source = [ "html_to_markdown" ]
+
+[tool.coverage.report]
+exclude_lines = [ 'if TYPE_CHECKING:' ]
+fail_under = 100
+
+[tool.mypy]
+packages = [ "html_to_markdown", "tests" ]
+python_version = "3.9"
+implicit_reexport = false
+show_error_codes = true
+strict = true
+
+[[tool.mypy.overrides]]
+module = "tests.*"
+disallow_any_generics = false
+disallow_untyped_decorators = false
+
+[tool.uv]
+default-groups = [ "dev" ]

html_to_markdown-1.1.0/PKG-INFO

@@ -1,101 +0,0 @@
-Metadata-Version: 2.3
-Name: html-to-markdown
-Version: 1.1.0
-Summary: Convert HTML to markdown
-Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
-License: MIT
-License-File: LICENSE
-Keywords: beautifulsoup,converter,html,markdown,text-processing
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.9
-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: Topic :: Text Processing
-Classifier: Topic :: Text Processing :: Markup
-Classifier: Topic :: Text Processing :: Markup :: HTML
-Classifier: Topic :: Text Processing :: Markup :: Markdown
-Classifier: Topic :: Utilities
-Classifier: Typing :: Typed
-Requires-Python: >=3.9
-Requires-Dist: beautifulsoup4>=4.12.3
-Description-Content-Type: text/markdown
-
-# html_to_markdown
-
-This library is a refactored and modernized fork of [markdownify](https://pypi.org/project/markdownify/), supporting
-Python 3.9 and above.
-
-### Differences with the Markdownify
-
-- The refactored codebase uses a strict functional approach - no classes are involved.
-- There is full typing with strict MyPy strict adherence and a py.typed file included.
-- The `convert_to_markdown` function allows passing a pre-configured instance of `BeautifulSoup` instead of html.
-- This library releases follows standard semver. Its version v1.0.0 was branched from markdownify's v0.13.1, at which
-  point versioning is no longer aligned.
-
-## Installation
-
-```shell
-pip install html_to_markdown
-```
-
-## Usage
-
-Convert an string HTML to Markdown:
-
-```python
-from html_to_markdown import convert_to_markdown
-
-convert_to_markdown('<b>Yay</b> <a href="http://github.com">GitHub</a>')  # > '**Yay** [GitHub](http://github.com)'
-```
-
-Or pass a pre-configured instance of `BeautifulSoup`:
-
-```python
-from bs4 import BeautifulSoup
-from html_to_markdown import convert_to_markdown
-
-soup = BeautifulSoup('<b>Yay</b> <a href="http://github.com">GitHub</a>', 'lxml')  # lxml requires an extra dependency.
-
-convert_to_markdown(soup)  # > '**Yay** [GitHub](http://github.com)'
-```
-
-### Options
-
-The `convert_to_markdown` function accepts the following kwargs:
-
-- autolinks (bool): Automatically convert valid URLs into Markdown links. Defaults to True.
-- bullets (str): A string of characters to use for bullet points in lists. Defaults to '*+-'.
-- code_language (str): Default language identifier for fenced code blocks. Defaults to an empty string.
-- code_language_callback (Callable[[Any], str] | None): Function to dynamically determine the language for code blocks.
-- convert (Iterable[str] | None): A list of tag names to convert to Markdown. If None, all supported tags are converted.
-- default_title (bool): Use the default title when converting certain elements (e.g., links). Defaults to False.
-- escape_asterisks (bool): Escape asterisks (*) to prevent unintended Markdown formatting. Defaults to True.
-- escape_misc (bool): Escape miscellaneous characters to prevent conflicts in Markdown. Defaults to True.
-- escape_underscores (bool): Escape underscores (_) to prevent unintended italic formatting. Defaults to True.
-- heading_style (Literal["underlined", "atx", "atx_closed"]): The style to use for Markdown headings. Defaults to "
-  underlined".
-- keep_inline_images_in (Iterable[str] | None): Tags in which inline images should be preserved. Defaults to None.
-- newline_style (Literal["spaces", "backslash"]): Style for handling newlines in text content. Defaults to "spaces".
-- strip (Iterable[str] | None): Tags to strip from the output. Defaults to None.
-- strong_em_symbol (Literal["*", "_"]): Symbol to use for strong/emphasized text. Defaults to "*".
-- sub_symbol (str): Custom symbol for subscript text. Defaults to an empty string.
-- sup_symbol (str): Custom symbol for superscript text. Defaults to an empty string.
-- wrap (bool): Wrap text to the specified width. Defaults to False.
-- wrap_width (int): The number of characters at which to wrap text. Defaults to 80.
-- convert_as_inline (bool): Treat the content as inline elements (no block elements like paragraphs). Defaults to False.
-
-## CLI
-
-For compatibility with the original markdownify, a CLI is provided. Use `html_to_markdown example.html > example.md` or
-pipe input from stdin:
-
-```shell
-cat example.html | html_to_markdown > example.md
-```
-
-Use `html_to_markdown -h` to see all available options. They are the same as listed above and take the same arguments.

html_to_markdown-1.1.0/README.md

@@ -1,75 +0,0 @@
-# html_to_markdown
-
-This library is a refactored and modernized fork of [markdownify](https://pypi.org/project/markdownify/), supporting
-Python 3.9 and above.
-
-### Differences with the Markdownify
-
-- The refactored codebase uses a strict functional approach - no classes are involved.
-- There is full typing with strict MyPy strict adherence and a py.typed file included.
-- The `convert_to_markdown` function allows passing a pre-configured instance of `BeautifulSoup` instead of html.
-- This library releases follows standard semver. Its version v1.0.0 was branched from markdownify's v0.13.1, at which
-  point versioning is no longer aligned.
-
-## Installation
-
-```shell
-pip install html_to_markdown
-```
-
-## Usage
-
-Convert an string HTML to Markdown:
-
-```python
-from html_to_markdown import convert_to_markdown
-
-convert_to_markdown('<b>Yay</b> <a href="http://github.com">GitHub</a>')  # > '**Yay** [GitHub](http://github.com)'
-```
-
-Or pass a pre-configured instance of `BeautifulSoup`:
-
-```python
-from bs4 import BeautifulSoup
-from html_to_markdown import convert_to_markdown
-
-soup = BeautifulSoup('<b>Yay</b> <a href="http://github.com">GitHub</a>', 'lxml')  # lxml requires an extra dependency.
-
-convert_to_markdown(soup)  # > '**Yay** [GitHub](http://github.com)'
-```
-
-### Options
-
-The `convert_to_markdown` function accepts the following kwargs:
-
-- autolinks (bool): Automatically convert valid URLs into Markdown links. Defaults to True.
-- bullets (str): A string of characters to use for bullet points in lists. Defaults to '*+-'.
-- code_language (str): Default language identifier for fenced code blocks. Defaults to an empty string.
-- code_language_callback (Callable[[Any], str] | None): Function to dynamically determine the language for code blocks.
-- convert (Iterable[str] | None): A list of tag names to convert to Markdown. If None, all supported tags are converted.
-- default_title (bool): Use the default title when converting certain elements (e.g., links). Defaults to False.
-- escape_asterisks (bool): Escape asterisks (*) to prevent unintended Markdown formatting. Defaults to True.
-- escape_misc (bool): Escape miscellaneous characters to prevent conflicts in Markdown. Defaults to True.
-- escape_underscores (bool): Escape underscores (_) to prevent unintended italic formatting. Defaults to True.
-- heading_style (Literal["underlined", "atx", "atx_closed"]): The style to use for Markdown headings. Defaults to "
-  underlined".
-- keep_inline_images_in (Iterable[str] | None): Tags in which inline images should be preserved. Defaults to None.
-- newline_style (Literal["spaces", "backslash"]): Style for handling newlines in text content. Defaults to "spaces".
-- strip (Iterable[str] | None): Tags to strip from the output. Defaults to None.
-- strong_em_symbol (Literal["*", "_"]): Symbol to use for strong/emphasized text. Defaults to "*".
-- sub_symbol (str): Custom symbol for subscript text. Defaults to an empty string.
-- sup_symbol (str): Custom symbol for superscript text. Defaults to an empty string.
-- wrap (bool): Wrap text to the specified width. Defaults to False.
-- wrap_width (int): The number of characters at which to wrap text. Defaults to 80.
-- convert_as_inline (bool): Treat the content as inline elements (no block elements like paragraphs). Defaults to False.
-
-## CLI
-
-For compatibility with the original markdownify, a CLI is provided. Use `html_to_markdown example.html > example.md` or
-pipe input from stdin:
-
-```shell
-cat example.html | html_to_markdown > example.md
-```
-
-Use `html_to_markdown -h` to see all available options. They are the same as listed above and take the same arguments.

html_to_markdown-1.1.0/html_to_markdown/__init__.py

@@ -1,3 +0,0 @@
-from html_to_markdown.processing import convert_to_markdown
-
-__all__ = ["convert_to_markdown"]

html_to_markdown-1.1.0/html_to_markdown/__main__.py

@@ -1,7 +0,0 @@
-import sys
-
-from html_to_markdown.dli import cli
-
-if __name__ == "__main__":
-    result = cli(sys.argv[1:])
-    print(result)  # noqa: T201

html_to_markdown-1.1.0/html_to_markdown/constants.py

@@ -1,18 +0,0 @@
-from __future__ import annotations
-
-import re
-from re import Pattern
-from typing import Final, Literal
-
-convert_heading_re: Final[Pattern[str]] = re.compile(r"convert_h(\d+)")
-line_beginning_re: Final[Pattern[str]] = re.compile(r"^", re.MULTILINE)
-whitespace_re: Final[Pattern[str]] = re.compile(r"[\t ]+")
-html_heading_re: Final[Pattern[str]] = re.compile(r"h[1-6]")
-
-ASTERISK: Final[Literal["*"]] = "*"
-ATX: Final[Literal["atx"]] = "atx"
-ATX_CLOSED: Final[Literal["atx_closed"]] = "atx_closed"
-BACKSLASH: Final[Literal["backslash"]] = "backslash"
-UNDERLINED: Final[Literal["underlined"]] = "underlined"
-SPACES: Final[Literal["spaces"]] = "spaces"
-UNDERSCORE: Final[Literal["_"]] = "_"

html_to_markdown-1.1.0/pyproject.toml

@@ -1,137 +0,0 @@
-[project]
-name = "html-to-markdown"
-version = "1.1.0"
-description = "Convert HTML to markdown"
-authors = [{ name = "Na'aman Hirschfeld", email = "nhirschfeld@gmail.com" }]
-requires-python = ">=3.9"
-readme = "README.md"
-license = { text = "MIT" }
-classifiers = [
-    "Intended Audience :: Developers",
-    "License :: OSI Approved :: MIT License",
-    "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
-    "Topic :: Text Processing :: Markup :: HTML",
-    "Topic :: Text Processing :: Markup :: Markdown",
-    "Topic :: Text Processing :: Markup",
-    "Topic :: Text Processing",
-    "Topic :: Utilities",
-    "Typing :: Typed",
-]
-keywords = ["markdown", "html", "beautifulsoup", "converter", "text-processing"]
-
-dependencies = [
-    "beautifulsoup4>=4.12.3",
-]
-
-[project.scripts]
-html_to_markdown = "html_to_markdown.__main__:cli"
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-[tool.hatch.build]
-skip-excluded-dirs = true
-
-[tool.hatch.build.targets.sdist]
-only-include = ["html_to_markdown"]
-
-[tool.hatch.build.targets.wheel]
-only-include = ["html_to_markdown"]
-
-[tool.pdm]
-distribution = true
-
-[tool.pdm.dev-dependencies]
-dev = [
-    "covdefaults>=2.3.0",
-    "pre-commit>=3.7.0",
-    "pytest>=8.1.1",
-    "ruff>=0.4.0",
-    "pytest-mock>=3.14.0",
-    "pytest-cov>=5.0.0",
-    "types-beautifulsoup4>=4.12.0.20240907",
-    "mypy>=1.11.2",
-]
-
-[tool.pdm.scripts]
-setup = { composite = [
-    "pre-commit install --install-hooks",
-    "pre-commit install --hook-type commit-msg",
-    "pdm install"
-] }
-lint = "pre-commit run --all-files"
-test.cmd = "pytest"
-test.env = { "PYTHONPATH" = "." }
-coverage.cmd = "pytest --disable-warnings --cov --cov-report xml"
-coverage.env = { "PYTHONPATH" = "." }
-
-# linters configuration below
-[tool.ruff]
-line-length = 120
-target-version = "py39"
-lint.select = ["ALL"]
-lint.ignore = [
-    "ANN401", # dynamically typed ANY
-    "D100", # # pydocstyle - missing docstring in public module
-    "D104", # pydocstyle - missing docstring in public package
-    "D107", # pydocstyle - missing docstring in __init__
-    "D205", # pydocstyle - 1 blank line required between summary line and description
-    "E501", # pycodestyle line too long, handled by ruff format
-    "EM", # Exception messages,
-    "FIX", # we allow todo and fixme comments
-    "PLR2004", # Magic variables, we allow them
-    "TD", # we allow todo and fixme comments
-    "TRY", # Try except block, rules are too strict
-    "COM812", # Conflicts with formatter
-    "ISC001", # Conflicts with formatter
-    "FBT", # Boolean Args
-]
-src = ["html_to_markdown", "tests"]
-
-[tool.ruff.lint.per-file-ignores]
-"tests/**/*.*" = ["S", "D", "PT006", "PT013", "PD", "ARG"]
-
-[tool.ruff.format]
-docstring-code-format = true
-docstring-code-line-length = 120
-
-[tool.ruff.lint.pydocstyle]
-convention = "google"
-
-[tool.ruff.lint.isort]
-known-first-party = ["html_to_markdown", "tests"]
-
-[tool.ruff.lint.pylint]
-max-args = 25
-max-returns = 10
-
-[tool.mypy]
-packages = ["html_to_markdown", "tests"]
-python_version = "3.9"
-implicit_reexport = false
-show_error_codes = true
-strict = true
-
-[[tool.mypy.overrides]]
-module = "tests.*"
-disallow_any_generics = false
-disallow_untyped_decorators = false
-
-[tool.coverage.run]
-omit = ["tests/*"]
-plugins = ["covdefaults"]
-source = ["html_to_markdown"]
-
-[tool.coverage.report]
-exclude_lines = ['if TYPE_CHECKING:']
-fail_under = 100
-
-[tool.pytest.ini_options]
-asyncio_mode = "auto"
-asyncio_default_fixture_loop_scope = "function"