html-to-markdown 1.3.2__tar.gz → 1.4.0__tar.gz

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/PKG-INFO

@@ -1,11 +1,16 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.3.2
-Summary: Convert HTML to markdown
+Version: 1.4.0
+Summary: A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options
 Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
 License: MIT
-Project-URL: homepage, https://github.com/Goldziher/html-to-markdown
-Keywords: converter,html,markdown,text-extraction,text-processing
+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
+Keywords: beautifulsoup,cli-tool,converter,html,html2markdown,markdown,markup,text-extraction,text-processing
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -15,6 +20,8 @@ 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 :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Markup
 Classifier: Topic :: Text Processing :: Markup :: HTML

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/html_to_markdown/__main__.py

@@ -1,11 +1,17 @@
 import sys
 
-if __name__ == "__main__":
-    from html_to_markdown.cli import main
+from html_to_markdown.cli import main
+
 
+def cli() -> None:
+    """Main CLI entrypoint."""
     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)
+
+
+if __name__ == "__main__":
+    cli()

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/html_to_markdown/cli.py

@@ -1,11 +1,12 @@
-def main(argv: list[str]) -> str:
-    """Command-line entry point."""
-    from argparse import ArgumentParser, FileType
-    from sys import stdin
+from argparse import ArgumentParser, FileType
+from sys import stdin
+
+from html_to_markdown.constants import ASTERISK, ATX, ATX_CLOSED, BACKSLASH, SPACES, UNDERLINED, UNDERSCORE
+from html_to_markdown.processing import convert_to_markdown
 
-    from html_to_markdown.constants import ASTERISK, ATX, ATX_CLOSED, BACKSLASH, SPACES, UNDERLINED, UNDERSCORE
-    from html_to_markdown.processing import convert_to_markdown
 
+def main(argv: list[str]) -> str:
+    """Command-line entry point."""
     parser = ArgumentParser(
         prog="html_to_markdown",
         description="Converts HTML to Markdown.",
@@ -127,6 +128,12 @@ def main(argv: list[str]) -> str:
         help="The number of characters at which text paragraphs should wrap. Defaults to 80.",
     )
 
+    parser.add_argument(
+        "--strip-newlines",
+        action="store_true",
+        help="Remove newlines from HTML input before processing. This helps flatten janky output from HTML with unnecessary line breaks.",
+    )
+
     args = parser.parse_args(argv)
 
     return convert_to_markdown(
@@ -147,4 +154,5 @@ def main(argv: list[str]) -> str:
         keep_inline_images_in=args.keep_inline_images_in,
         wrap=args.wrap,
         wrap_width=args.wrap_width,
+        strip_newlines=args.strip_newlines,
     )

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/html_to_markdown/converters.py

@@ -156,11 +156,17 @@ def _convert_img(*, tag: Tag, convert_as_inline: bool, keep_inline_images_in: It
     alt = tag.attrs.get("alt", "")
     src = tag.attrs.get("src", "")
     title = tag.attrs.get("title", "")
+    width = tag.attrs.get("width", "")
+    height = tag.attrs.get("height", "")
     title_part = ' "{}"'.format(title.replace('"', r"\"")) if title else ""
     parent_name = tag.parent.name if tag.parent else ""
-    if convert_as_inline and parent_name not in (keep_inline_images_in or []):
+    # Always preserve images in table cells (td, th) by default
+    default_preserve_in = ["td", "th"]
+    preserve_in = set(keep_inline_images_in or []) | set(default_preserve_in)
+    if convert_as_inline and parent_name not in preserve_in:
         return alt
-
+    if width or height:
+        return f"<img src='{src}' alt='{alt}' title='{title}' width='{width}' height='{height}' />"
     return f"![{alt}]({src}{title_part})"
 
 

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/html_to_markdown/processing.py

@@ -213,6 +213,7 @@ def convert_to_markdown(
     keep_inline_images_in: Iterable[str] | None = None,
     newline_style: Literal["spaces", "backslash"] = SPACES,
     strip: str | Iterable[str] | None = None,
+    strip_newlines: bool = False,
     strong_em_symbol: Literal["*", "_"] = ASTERISK,
     sub_symbol: str = "",
     sup_symbol: str = "",
@@ -238,6 +239,7 @@ def convert_to_markdown(
         keep_inline_images_in: Tags in which inline images should be preserved. Defaults to None.
         newline_style: Style for handling newlines in text content. Defaults to "spaces".
         strip: Tags to strip from the output. Defaults to None.
+        strip_newlines: Remove newlines from HTML input before processing. Defaults to False.
         strong_em_symbol: Symbol to use for strong/emphasized text. Defaults to "*".
         sub_symbol: Custom symbol for subscript text. Defaults to an empty string.
         sup_symbol: Custom symbol for superscript text. Defaults to an empty string.
@@ -259,6 +261,10 @@ def convert_to_markdown(
         ):
             return source
 
+        if strip_newlines:
+            # Replace all newlines with spaces before parsing
+            source = source.replace("\n", " ").replace("\r", " ")
+
         if "".join(source.split("\n")):
             source = BeautifulSoup(source, "html.parser")
         else:

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/html_to_markdown.egg-info/PKG-INFO

@@ -1,11 +1,16 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.3.2
-Summary: Convert HTML to markdown
+Version: 1.4.0
+Summary: A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options
 Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
 License: MIT
-Project-URL: homepage, https://github.com/Goldziher/html-to-markdown
-Keywords: converter,html,markdown,text-extraction,text-processing
+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
+Keywords: beautifulsoup,cli-tool,converter,html,html2markdown,markdown,markup,text-extraction,text-processing
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -15,6 +20,8 @@ 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 :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Markup
 Classifier: Topic :: Text Processing :: Markup :: HTML

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/html_to_markdown.egg-info/SOURCES.txt

@@ -12,5 +12,6 @@ html_to_markdown/utils.py
 html_to_markdown.egg-info/PKG-INFO
 html_to_markdown.egg-info/SOURCES.txt
 html_to_markdown.egg-info/dependency_links.txt
+html_to_markdown.egg-info/entry_points.txt
 html_to_markdown.egg-info/requires.txt
 html_to_markdown.egg-info/top_level.txt

html_to_markdown-1.4.0/html_to_markdown.egg-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+html-to-markdown = html_to_markdown.__main__:cli
+html_to_markdown = html_to_markdown.__main__:cli

{html_to_markdown-1.3.2 → html_to_markdown-1.4.0}/pyproject.toml

@@ -5,14 +5,26 @@ requires = [ "setuptools>=78.1" ]
 
 [project]
 name = "html-to-markdown"
-version = "1.3.2"
-description = "Convert HTML to markdown"
+version = "1.4.0"
+description = "A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options"
 readme = "README.md"
-keywords = [ "converter", "html", "markdown", "text-extraction", "text-processing" ]
+keywords = [
+  "beautifulsoup",
+  "cli-tool",
+  "converter",
+  "html",
+  "html2markdown",
+  "markdown",
+  "markup",
+  "text-extraction",
+  "text-processing",
+]
 license = { text = "MIT" }
 authors = [ { name = "Na'aman Hirschfeld", email = "nhirschfeld@gmail.com" } ]
 requires-python = ">=3.9"
 classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Environment :: Console",
   "Intended Audience :: Developers",
   "License :: OSI Approved :: MIT License",
   "Operating System :: OS Independent",
@@ -22,6 +34,8 @@ classifiers = [
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
+  "Topic :: Internet :: WWW/HTTP",
+  "Topic :: Software Development :: Libraries :: Python Modules",
   "Topic :: Text Processing",
   "Topic :: Text Processing :: Markup",
   "Topic :: Text Processing :: Markup :: HTML",
@@ -29,23 +43,27 @@ classifiers = [
   "Topic :: Utilities",
   "Typing :: Typed",
 ]
-
 dependencies = [
   "beautifulsoup4>=4.13.4",
 ]
 
-urls.homepage = "https://github.com/Goldziher/html-to-markdown"
+urls.Changelog = "https://github.com/Goldziher/html-to-markdown/releases"
+urls.Homepage = "https://github.com/Goldziher/html-to-markdown"
+urls.Issues = "https://github.com/Goldziher/html-to-markdown/issues"
+urls.Repository = "https://github.com/Goldziher/html-to-markdown.git"
+scripts.html-to-markdown = "html_to_markdown.__main__:cli"
+scripts.html_to_markdown = "html_to_markdown.__main__:cli"
 
 [dependency-groups]
 dev = [
   "covdefaults>=2.3",
-  "mypy>=1.14.1",
+  "mypy>=1.16.1",
   "pre-commit>=4.1",
-  "pytest>=8.3.4",
-  "pytest-cov>=6.1.1",
-  "pytest-mock>=3.14",
-  "ruff>=0.11.6",
-  "types-beautifulsoup4>=4.12.0.20241020",
+  "pytest>=8.4.1",
+  "pytest-cov>=6.2.1",
+  "pytest-mock>=3.14.1",
+  "ruff>=0.12",
+  "types-beautifulsoup4>=4.12.0.20250516",
   "uv-bump",
 ]
 
@@ -58,8 +76,6 @@ html_to_markdown = [ "py.typed" ]
 [tool.hatch.build]
 skip-excluded-dirs = true
 
-scripts.html_to_markdown = "html_to_markdown.__main__:cli"
-
 [tool.ruff]
 target-version = "py39"
 line-length = 120
@@ -71,16 +87,16 @@ lint.select = [ "ALL" ]
 lint.ignore = [
   "ANN401",  # dynamically typed ANY
   "COM812",  # Conflicts with formatter
-  "D100",    # # pydocstyle - missing docstring in public module
+  "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,
+  "EM",      # Exception messages
   "FBT",     # Boolean Args
   "FIX",     # we allow todo and fixme comments
   "ISC001",  # Conflicts with formatter
-  "PLR0913", # Pylint - too many arguments.
+  "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
@@ -92,22 +108,32 @@ lint.pydocstyle.convention = "google"
 [tool.pytest.ini_options]
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "function"
+testpaths = [ "tests" ]
+filterwarnings = [
+  "error",
+  "ignore::pytest.PytestConfigWarning",
+  "ignore::pytest.PytestUnraisableExceptionWarning",
+  "ignore::ResourceWarning",
+]
 
 [tool.coverage.run]
+source = [ "html_to_markdown" ]
 omit = [ "tests/*" ]
 plugins = [ "covdefaults" ]
-source = [ "html_to_markdown" ]
 
 [tool.coverage.report]
-exclude_lines = [ 'if TYPE_CHECKING:' ]
+exclude_lines = [ "if TYPE_CHECKING:" ]
 fail_under = 100
+show_missing = true
 
 [tool.mypy]
 packages = [ "html_to_markdown", "tests" ]
 python_version = "3.9"
+strict = true
 implicit_reexport = false
 show_error_codes = true
-strict = true
+warn_return_any = true
+warn_unused_configs = true
 
 [[tool.mypy.overrides]]
 module = "tests.*"