html-to-markdown 1.1.0__tar.gz → 1.2.0__tar.gz

{html_to_markdown-1.1.0 → html_to_markdown-1.2.0}/PKG-INFO

@@ -1,14 +1,15 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.1.0
+Version: 1.2.0
 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
+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
@@ -69,20 +70,20 @@ convert_to_markdown(soup)  # > '**Yay** [GitHub](http://github.com)'
 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 '*+-'.
+- 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_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.
+- 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 "*".
+- 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.

{html_to_markdown-1.1.0 → html_to_markdown-1.2.0}/README.md

@@ -43,20 +43,20 @@ convert_to_markdown(soup)  # > '**Yay** [GitHub](http://github.com)'
 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 '*+-'.
+- 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_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.
+- 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 "*".
+- 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.

html_to_markdown-1.2.0/html_to_markdown/__init__.py

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

html_to_markdown-1.2.0/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-1.2.0/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-1.2.0}/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:
@@ -295,7 +297,7 @@ 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:

html_to_markdown-1.2.0/html_to_markdown/legacy.py

@@ -0,0 +1,89 @@
+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-1.1.0 → html_to_markdown-1.2.0}/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 +77,21 @@ 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 +125,7 @@ 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
         )
@@ -166,7 +168,7 @@ 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 +176,14 @@ 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 +191,7 @@ 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 +199,7 @@ 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 +231,22 @@ 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 +267,10 @@ 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-1.2.0/pyproject.toml

@@ -0,0 +1,113 @@
+[build-system]
+build-backend = "hatchling.build"
+
+requires = [ "hatchling" ]
+
+[project]
+name = "html-to-markdown"
+version = "1.2.0"
+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",
+]
+
+[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/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"