html-to-markdown 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

html_to_markdown/__init__.py

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

html_to_markdown/converters.py

@@ -85,7 +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:
@@ -187,7 +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
         )
@@ -263,7 +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():
@@ -272,12 +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
@@ -334,7 +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/processing.py

@@ -87,7 +87,9 @@ def _process_tag(
     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
+    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
@@ -142,11 +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,
@@ -155,9 +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"

html_to_markdown-1.2.1.dist-info/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,12 @@
+html_to_markdown/__init__.py,sha256=95S7_7mR_g88uTnFI0FaRNykrtAaSKb6sJbwSea2zjk,145
+html_to_markdown/__main__.py,sha256=u5xevySlT5eIGyLUaethdDQIKJygaKnc3F2sHWoz75g,264
+html_to_markdown/cli.py,sha256=HVnzmcyrYwah_yWhZ87mZcG0VgnKYp6y89fJh2R-Rlw,4532
+html_to_markdown/constants.py,sha256=Usk67k18tuRovJpKDsiEXdgH20KgqI9KOnK4Fbx-M5c,547
+html_to_markdown/converters.py,sha256=W6Dq2PAwVe5nxE3LSaeO8_hm0eWzSBlRLxf0ryasL6Q,11844
+html_to_markdown/processing.py,sha256=nh_Or-4faI_qh6gF8-xY2qNiqX4eH-jCnBnFpHJbc2M,8632
+html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+html_to_markdown/utils.py,sha256=HJUDej5HSpXRtYv-OkCyD0hwnPnVfQCwY6rBRlIOt9s,1989
+html_to_markdown-1.2.1.dist-info/METADATA,sha256=-raxzt9vDtzHOOsR0nkbQN-r80V5gRFfeHjDOLWrDwk,6902
+html_to_markdown-1.2.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+html_to_markdown-1.2.1.dist-info/licenses/LICENSE,sha256=3J_HR5BWvUM1mlIrlkF32-uC1FM64gy8JfG17LBuheQ,1122
+html_to_markdown-1.2.1.dist-info/RECORD,,

{html_to_markdown-1.2.0.dist-info → html_to_markdown-1.2.1.dist-info}/licenses/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/legacy.py

@@ -1,89 +0,0 @@
-from __future__ import annotations
-
-from typing import TYPE_CHECKING, Literal
-
-from html_to_markdown.constants import ASTERISK, SPACES, UNDERLINED
-from html_to_markdown.converters import create_converters_map
-
-if TYPE_CHECKING:
-    from collections.abc import Callable, Iterable
-
-    from bs4 import Tag
-
-
-def _create_legacy_class(
-    autolinks: bool,
-    bullets: str,
-    code_language: str,
-    code_language_callback: Callable[[Tag], str] | None,
-    default_title: bool,
-    heading_style: Literal["atx", "atx_closed", "underlined"],
-    keep_inline_images_in: Iterable[str] | None,
-    newline_style: str,
-    strong_em_symbol: str,
-    sub_symbol: str,
-    sup_symbol: str,
-    wrap: bool,
-    wrap_width: int,
-) -> type:
-    """Create a legacy class for Markdownify.
-
-    Deprecated: Use the new hooks api instead.
-
-    Args:
-        autolinks: Whether to convert URLs into links.
-        bullets: The bullet characters to use for unordered lists.
-        code_language: The default code language to use.
-        code_language_callback: A callback to get the code language.
-        default_title: Whether to use the URL as the title for links.
-        heading_style: The style of headings.
-        keep_inline_images_in: The tags to keep inline images in.
-        newline_style: The style of newlines.
-        strong_em_symbol: The symbol to use for strong and emphasis text.
-        sub_symbol: The symbol to use for subscript text.
-        sup_symbol: The symbol to use for superscript text.
-        wrap: Whether to wrap text.
-        wrap_width: The width to wrap text at.
-
-    Returns:
-        A class that can be used to convert HTML to Markdown.
-    """
-    return type(
-        "Markdownify",
-        (),
-        {
-            k.removeprefix("_"): v
-            for k, v in create_converters_map(
-                autolinks=autolinks,
-                bullets=bullets,
-                code_language=code_language,
-                code_language_callback=code_language_callback,
-                default_title=default_title,
-                heading_style=heading_style,
-                keep_inline_images_in=keep_inline_images_in,
-                newline_style=newline_style,
-                strong_em_symbol=strong_em_symbol,
-                sub_symbol=sub_symbol,
-                sup_symbol=sup_symbol,
-                wrap=wrap,
-                wrap_width=wrap_width,
-            ).items()
-        },
-    )
-
-
-Markdownify = _create_legacy_class(
-    autolinks=True,
-    bullets="*+-",
-    code_language="",
-    code_language_callback=None,
-    default_title=False,
-    heading_style=UNDERLINED,
-    keep_inline_images_in=None,
-    newline_style=SPACES,
-    strong_em_symbol=ASTERISK,
-    sub_symbol="",
-    sup_symbol="",
-    wrap=False,
-    wrap_width=80,
-)

html_to_markdown-1.2.0.dist-info/METADATA

@@ -1,102 +0,0 @@
-Metadata-Version: 2.4
-Name: html-to-markdown
-Version: 1.2.0
-Summary: Convert 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
-
-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-1.2.0.dist-info/RECORD

@@ -1,13 +0,0 @@
-html_to_markdown/__init__.py,sha256=cXm4YOyrAp2HKHMDfnVA5e75zg6wdqpyXugjBYvBMFc,143
-html_to_markdown/__main__.py,sha256=u5xevySlT5eIGyLUaethdDQIKJygaKnc3F2sHWoz75g,264
-html_to_markdown/cli.py,sha256=HVnzmcyrYwah_yWhZ87mZcG0VgnKYp6y89fJh2R-Rlw,4532
-html_to_markdown/constants.py,sha256=Usk67k18tuRovJpKDsiEXdgH20KgqI9KOnK4Fbx-M5c,547
-html_to_markdown/converters.py,sha256=hW4RqAbgx0tdTzfUSvAGQg1OgQUmHL1cekZtJLFq_Ns,12080
-html_to_markdown/legacy.py,sha256=vL-MVKPXOue-JJafXFtmGcVIPylwmPOly0CELTSzWRQ,2773
-html_to_markdown/processing.py,sha256=L1wZwUm7WA8wN4GA5zjCStwACb-8S2scQZPbzeHgdY8,8951
-html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-html_to_markdown/utils.py,sha256=HJUDej5HSpXRtYv-OkCyD0hwnPnVfQCwY6rBRlIOt9s,1989
-html_to_markdown-1.2.0.dist-info/METADATA,sha256=Dg2ZibNWNW_GyszXG2bxT-oOtOJc8iryVxlLn38eMww,4709
-html_to_markdown-1.2.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-html_to_markdown-1.2.0.dist-info/licenses/LICENSE,sha256=06BS7zd6oPCrbzAqrThGFboRlbssgBsqDJGqKyZW2Og,1117
-html_to_markdown-1.2.0.dist-info/RECORD,,