html-to-markdown 2.4.1__cp310-abi3-macosx_11_0_arm64.whl → 2.5.0__cp310-abi3-macosx_11_0_arm64.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.dist-info/RECORD,,
+html_to_markdown-2.5.0.dist-info/WHEEL,sha256=HtAbUhtjhH1WdiDuIy2CapdoAiKCwe6bij_Tlxr1lEg,131
+html_to_markdown-2.5.0.dist-info/METADATA,sha256=-cJomvtoyyYuKadCinA5UZEO4Oc-0SFP4gozQZMW0bc,9199
+html_to_markdown-2.5.0.dist-info/licenses/LICENSE,sha256=oQvPC-0UWvfg0WaeUBe11OJMtX60An-TW1ev_oaAA0k,1086
+html_to_markdown-2.5.0.data/scripts/html-to-markdown,sha256=mTrDOF6GXv69CkGoDj8kfAZYxtxUraCrJn098XF9eWA,3884336
+html_to_markdown/options.py,sha256=vImRfeHAeyAy0Lnt6cTPHGbj7mTdw8AEUgo19u7MAA0,5080
+html_to_markdown/_html_to_markdown.abi3.so,sha256=uMIpbLa7N1jXzb2iYHWkD0-FMfxVP5oOwXvV-huAq0E,3701616
+html_to_markdown/__init__.py,sha256=dyDrtQxQvh8ReI-5LVHgeR1cflevhIW838jFo5KRdpI,1358
+html_to_markdown/api.py,sha256=uiNoieNXrcXTJI2_vV7ruDv9HKD7XFuosCAeqZL-C_Q,4944
+html_to_markdown/_rust.pyi,sha256=pi6C_qAdB81qUlC89Dy1ZKC1JrpdnqVce-caJx3ekPA,2098
+html_to_markdown/v1_compat.py,sha256=5DZA-fPMqZ5hYiA43rFaOAqshLS8MScbBnivDXuvQII,8034
+html_to_markdown/cli.py,sha256=Rn-s3FZPea1jgCJtDzH_TFvOEiA_uZFVfgjhr6xyL_g,64
+html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+html_to_markdown/exceptions.py,sha256=aTASOzbywgfqOYjlw18ZkOWSxKff4EbUbmMua_73TGA,2370
+html_to_markdown/cli_proxy.py,sha256=8Byrnok5-WkDWToaUeMcKi1xVr62PhZKygHymdrSfFE,3682
+html_to_markdown/__main__.py,sha256=3Ic_EbOt2h6W88q084pkz5IKU6iY5z_woBygH6u9aw0,327
+html_to_markdown/bin/html-to-markdown,sha256=mTrDOF6GXv69CkGoDj8kfAZYxtxUraCrJn098XF9eWA,3884336

html_to_markdown-2.4.1.dist-info/RECORD

@@ -1,17 +0,0 @@
-html_to_markdown-2.4.1.dist-info/RECORD,,
-html_to_markdown-2.4.1.dist-info/WHEEL,sha256=HtAbUhtjhH1WdiDuIy2CapdoAiKCwe6bij_Tlxr1lEg,131
-html_to_markdown-2.4.1.dist-info/METADATA,sha256=4x7lilhuSBe0BYBt8adF-sWSDyc3ltqeozbuq2WliGQ,8811
-html_to_markdown-2.4.1.dist-info/licenses/LICENSE,sha256=oQvPC-0UWvfg0WaeUBe11OJMtX60An-TW1ev_oaAA0k,1086
-html_to_markdown-2.4.1.data/scripts/html-to-markdown,sha256=emkAIvTTFXT2bSBY6gbJ6MMNvI7zGnJJ-U74JPmhL1M,3834416
-html_to_markdown/options.py,sha256=N1orEtzXiqgV88Y7eqRjw3ilxDi7N97FBkBa79hdfzo,4913
-html_to_markdown/_html_to_markdown.abi3.so,sha256=NP1TwcmacpejjFFEF6ivrqj1ja1lWolha2UtcPrd0Ac,3668544
-html_to_markdown/__init__.py,sha256=dE3LTqvmvxA0QzXwC-36wah17rJtmzWXKFAvraStEkQ,1358
-html_to_markdown/api.py,sha256=sXezV2iZb42s-za0hWWHFhihKjaMo6j_tx7e-0EyQPg,4860
-html_to_markdown/_rust.pyi,sha256=pi6C_qAdB81qUlC89Dy1ZKC1JrpdnqVce-caJx3ekPA,2098
-html_to_markdown/v1_compat.py,sha256=5DZA-fPMqZ5hYiA43rFaOAqshLS8MScbBnivDXuvQII,8034
-html_to_markdown/cli.py,sha256=Rn-s3FZPea1jgCJtDzH_TFvOEiA_uZFVfgjhr6xyL_g,64
-html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-html_to_markdown/exceptions.py,sha256=aTASOzbywgfqOYjlw18ZkOWSxKff4EbUbmMua_73TGA,2370
-html_to_markdown/cli_proxy.py,sha256=8Byrnok5-WkDWToaUeMcKi1xVr62PhZKygHymdrSfFE,3682
-html_to_markdown/__main__.py,sha256=3Ic_EbOt2h6W88q084pkz5IKU6iY5z_woBygH6u9aw0,327
-html_to_markdown/bin/html-to-markdown,sha256=emkAIvTTFXT2bSBY6gbJ6MMNvI7zGnJJ-U74JPmhL1M,3834416