html-to-markdown 1.3.3__py3-none-any.whl → 1.4.0__py3-none-any.whl

html_to_markdown/__main__.py

@@ -1,8 +1,10 @@
 import sys
 
-def cli():
-    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
@@ -10,5 +12,6 @@ def cli():
         print(str(e), file=sys.stderr)  # noqa: T201
         sys.exit(1)
 
+
 if __name__ == "__main__":
     cli()

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/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/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-1.3.3.dist-info → html_to_markdown-1.4.0.dist-info}/METADATA

@@ -1,11 +1,16 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.3.3
-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-1.4.0.dist-info/RECORD

@@ -0,0 +1,14 @@
+html_to_markdown/__init__.py,sha256=95S7_7mR_g88uTnFI0FaRNykrtAaSKb6sJbwSea2zjk,145
+html_to_markdown/__main__.py,sha256=DJyJX7NIK0BVPNS2r3BYJ0Ci_lKHhgVOpw7ZEqACH3c,323
+html_to_markdown/cli.py,sha256=Kfh2sF_ySE_fQ0qdwvUZ5Rqx-P4Y12uTpG8xF60gAq0,4789
+html_to_markdown/constants.py,sha256=Usk67k18tuRovJpKDsiEXdgH20KgqI9KOnK4Fbx-M5c,547
+html_to_markdown/converters.py,sha256=SHRAV1qIFQQdXSD_TToR_F_t8hw3-amz8rIs2Q84YbQ,12276
+html_to_markdown/processing.py,sha256=mzF6YNqhj2VoRN6_TafnZ4ZndOyFglsZXTNnOl4uvWM,10564
+html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+html_to_markdown/utils.py,sha256=HJUDej5HSpXRtYv-OkCyD0hwnPnVfQCwY6rBRlIOt9s,1989
+html_to_markdown-1.4.0.dist-info/licenses/LICENSE,sha256=3J_HR5BWvUM1mlIrlkF32-uC1FM64gy8JfG17LBuheQ,1122
+html_to_markdown-1.4.0.dist-info/METADATA,sha256=LmjDer-QQkH6kSlkua1NBhnaKpIu4sVvyJZPPX5PgLk,8229
+html_to_markdown-1.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+html_to_markdown-1.4.0.dist-info/entry_points.txt,sha256=xmFijrTfgYW7lOrZxZGRPciicQHa5KiXKkUhBCmICtQ,116
+html_to_markdown-1.4.0.dist-info/top_level.txt,sha256=Ev6djb1c4dSKr_-n4K-FpEGDkzBigXY6LuZ5onqS7AE,17
+html_to_markdown-1.4.0.dist-info/RECORD,,

{html_to_markdown-1.3.3.dist-info → html_to_markdown-1.4.0.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
+html-to-markdown = html_to_markdown.__main__:cli
 html_to_markdown = html_to_markdown.__main__:cli

html_to_markdown-1.3.3.dist-info/RECORD

@@ -1,14 +0,0 @@
-html_to_markdown/__init__.py,sha256=95S7_7mR_g88uTnFI0FaRNykrtAaSKb6sJbwSea2zjk,145
-html_to_markdown/__main__.py,sha256=_EeKI8veMWZO7xsl-mBHBE-OmH1vnkVyXuExsOfduFI,286
-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=p8arBdejEeuAp9_wIYvp5PuWNBB0M699CgLSEkW3v88,11910
-html_to_markdown/processing.py,sha256=JNCjDgbfuW3YI7mfsj9aHlk2-KriQXJHU8Eo5D9Qj1E,10280
-html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-html_to_markdown/utils.py,sha256=HJUDej5HSpXRtYv-OkCyD0hwnPnVfQCwY6rBRlIOt9s,1989
-html_to_markdown-1.3.3.dist-info/licenses/LICENSE,sha256=3J_HR5BWvUM1mlIrlkF32-uC1FM64gy8JfG17LBuheQ,1122
-html_to_markdown-1.3.3.dist-info/METADATA,sha256=BcfsHs0cSG8Y1BScMsGFOGfN5mrxiu-HA_fJC6DrtFg,7653
-html_to_markdown-1.3.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-html_to_markdown-1.3.3.dist-info/entry_points.txt,sha256=jhMqXDYvIyzQDLKjCn4xCyzCCbAMl94tzQx_HiG5Qi0,67
-html_to_markdown-1.3.3.dist-info/top_level.txt,sha256=Ev6djb1c4dSKr_-n4K-FpEGDkzBigXY6LuZ5onqS7AE,17
-html_to_markdown-1.3.3.dist-info/RECORD,,