html-to-markdown 2.4.1__cp310-abi3-win_amd64.whl → 2.5.0__cp310-abi3-win_amd64.whl

html_to_markdown/__init__.py

@@ -49,4 +49,4 @@ __all__ = [
     "markdownify",
 ]
 
-__version__ = "2.4.1"
+__version__ = "2.5.0"

html_to_markdown/api.py

@@ -82,6 +82,7 @@ def _to_rust_options(
         encoding=options.encoding,
         debug=options.debug,
         strip_tags=list(options.strip_tags) if options.strip_tags else [],
+        preserve_tags=list(options.preserve_tags) if options.preserve_tags else [],
     )
 
 

html_to_markdown/options.py

@@ -95,6 +95,9 @@ class ConversionOptions:
     strip_tags: set[str] | None = None
     """HTML tags to strip from output (output only text content, no markdown conversion)."""
 
+    preserve_tags: set[str] | None = None
+    """HTML tags to preserve as-is in the output (keep original HTML). Useful for complex elements like tables."""
+
     convert_as_inline: bool = False
     """Treat block elements as inline during conversion."""
 
@@ -128,8 +131,8 @@ class PreprocessingOptions:
         ... )
     """
 
-    enabled: bool = False
-    """Whether to enable HTML preprocessing (disabled by default for minimal transformation)."""
+    enabled: bool = True
+    """Whether to enable HTML preprocessing (enabled by default for robust handling of malformed HTML)."""
 
     preset: Literal["minimal", "standard", "aggressive"] = "standard"
     """Preprocessing aggressiveness level."""

{html_to_markdown-2.4.1.dist-info → html_to_markdown-2.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 2.4.1
+Version: 2.5.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -162,9 +162,12 @@ Key fields (see docstring for full matrix):
 
 ### `PreprocessingOptions`
 
-- `enabled`: enable HTML sanitisation
-- `preset`: `"minimal" | "standard" | "aggressive"`
-- `remove_navigation`, `remove_forms`
+- `enabled`: enable HTML sanitisation (default: `True` since v2.4.2 for robust malformed HTML handling)
+- `preset`: `"minimal" | "standard" | "aggressive"` (default: `"standard"`)
+- `remove_navigation`: remove navigation elements (default: `True`)
+- `remove_forms`: remove form elements (default: `True`)
+
+**Note:** As of v2.4.2, preprocessing is enabled by default to ensure robust handling of malformed HTML (e.g., bare angle brackets like `1<2` in content). Set `enabled=False` if you need minimal preprocessing.
 
 ### `InlineImageConfig`
 

html_to_markdown-2.5.0.dist-info/RECORD

@@ -0,0 +1,17 @@
+html_to_markdown-2.5.0.data/scripts/html-to-markdown.exe,sha256=QBIiheprZwfuz5EhSqttEteTPn-w7LeqQNoGx7kO9PE,4531200
+html_to_markdown-2.5.0.dist-info/METADATA,sha256=vsDigqwoGBTZ5L31L7GCePFzhQcuV2WLg2Tn5JlxbR4,9403
+html_to_markdown-2.5.0.dist-info/WHEEL,sha256=4EDp_7DiFfWl1yYv5M4wSosAn5L_xgD1dyrQxQxfCx8,95
+html_to_markdown-2.5.0.dist-info/licenses/LICENSE,sha256=QhKFMkQLa4mSUlOsyG9VElzC7GYbAKtiS_EwOCyH-b4,1107
+html_to_markdown/__init__.py,sha256=w4c2ZeJNTRWE4kGKQEEEE0HabgfxNNpNOyXkBJmGAQ8,1410
+html_to_markdown/__main__.py,sha256=5objj9lB7hhpSpZsDok5tv9o9yztVR63Ccww-pXsAyY,343
+html_to_markdown/_html_to_markdown.pyd,sha256=tIxDvRmWyhcR9_PekDwYtRO0bhXww0GQ8vF-ZAttYgw,4254720
+html_to_markdown/_rust.pyi,sha256=JP8tvcjYDfFJeJkbLpQ4qeK-5jl0hzIVT3Sa0daTkyo,2171
+html_to_markdown/api.py,sha256=fghTHTmWkl9K0ap67uZAhiwxDGYYkknGX8le6prhz34,5088
+html_to_markdown/bin/html-to-markdown.exe,sha256=QBIiheprZwfuz5EhSqttEteTPn-w7LeqQNoGx7kO9PE,4531200
+html_to_markdown/cli.py,sha256=z59l8sF8wIRRzJtUd-tXgqiC0WTqkTjzl-df8Ey_oQ0,67
+html_to_markdown/cli_proxy.py,sha256=JGOuINBI8OMYLxojXGz8DdzMHo8eqgdINstOZWrdw-8,3816
+html_to_markdown/exceptions.py,sha256=31VqpPi4JLGv7lI2481Z4f2s5ejYmq97c3s-WFFkXVU,2443
+html_to_markdown/options.py,sha256=iDEIfxxZlSHDM3V-Sr-XVxYLC1mzvuic56jSycYvQvY,5224
+html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+html_to_markdown/v1_compat.py,sha256=aVt9cVTBfYcrS8EfBsrC6HQwWc3Kz9-65-LB9foN6Jk,8227
+html_to_markdown-2.5.0.dist-info/RECORD,,

html_to_markdown-2.4.1.dist-info/RECORD

@@ -1,17 +0,0 @@
-html_to_markdown-2.4.1.data/scripts/html-to-markdown.exe,sha256=C7lSkItGKC-rxUTJ1-s_lLM4mgsNYKAF1aA1ctQjTJE,4476928
-html_to_markdown-2.4.1.dist-info/METADATA,sha256=ONL8X8T_EPsCf6LmWEnNozk5IFmfkWdp-IYjMD_u2K8,9012
-html_to_markdown-2.4.1.dist-info/WHEEL,sha256=4EDp_7DiFfWl1yYv5M4wSosAn5L_xgD1dyrQxQxfCx8,95
-html_to_markdown-2.4.1.dist-info/licenses/LICENSE,sha256=QhKFMkQLa4mSUlOsyG9VElzC7GYbAKtiS_EwOCyH-b4,1107
-html_to_markdown/__init__.py,sha256=RMyWY2awLrpssSrYn0eh-BnlGgDxcK8dhSXAj5_Upbc,1410
-html_to_markdown/__main__.py,sha256=5objj9lB7hhpSpZsDok5tv9o9yztVR63Ccww-pXsAyY,343
-html_to_markdown/_html_to_markdown.pyd,sha256=0OYBHg29UeEQ3tHzdUL0CyinV1T3V5ed1L5Nto7oI50,4223488
-html_to_markdown/_rust.pyi,sha256=JP8tvcjYDfFJeJkbLpQ4qeK-5jl0hzIVT3Sa0daTkyo,2171
-html_to_markdown/api.py,sha256=jDb8PT1cS3KqipT4m_rKBE0R20UKOU85rH-7M6P6Owk,5003
-html_to_markdown/bin/html-to-markdown.exe,sha256=C7lSkItGKC-rxUTJ1-s_lLM4mgsNYKAF1aA1ctQjTJE,4476928
-html_to_markdown/cli.py,sha256=z59l8sF8wIRRzJtUd-tXgqiC0WTqkTjzl-df8Ey_oQ0,67
-html_to_markdown/cli_proxy.py,sha256=JGOuINBI8OMYLxojXGz8DdzMHo8eqgdINstOZWrdw-8,3816
-html_to_markdown/exceptions.py,sha256=31VqpPi4JLGv7lI2481Z4f2s5ejYmq97c3s-WFFkXVU,2443
-html_to_markdown/options.py,sha256=jna7fx9bHhx8N7u5IYtMXganFFzdJSVVgLZW0tYk3GA,5054
-html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-html_to_markdown/v1_compat.py,sha256=aVt9cVTBfYcrS8EfBsrC6HQwWc3Kz9-65-LB9foN6Jk,8227
-html_to_markdown-2.4.1.dist-info/RECORD,,