html-to-markdown 2.4.1__cp310-abi3-win_amd64.whl → 2.4.2__cp310-abi3-win_amd64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of html-to-markdown might be problematic. Click here for more details.
- html_to_markdown/__init__.py +1 -1
- html_to_markdown/_html_to_markdown.pyd +0 -0
- html_to_markdown/bin/html-to-markdown.exe +0 -0
- html_to_markdown/options.py +2 -2
- {html_to_markdown-2.4.1.data → html_to_markdown-2.4.2.data}/scripts/html-to-markdown.exe +0 -0
- {html_to_markdown-2.4.1.dist-info → html_to_markdown-2.4.2.dist-info}/METADATA +7 -4
- html_to_markdown-2.4.2.dist-info/RECORD +17 -0
- html_to_markdown-2.4.1.dist-info/RECORD +0 -17
- {html_to_markdown-2.4.1.dist-info → html_to_markdown-2.4.2.dist-info}/WHEEL +0 -0
- {html_to_markdown-2.4.1.dist-info → html_to_markdown-2.4.2.dist-info}/licenses/LICENSE +0 -0
html_to_markdown/__init__.py
CHANGED
|
Binary file
|
|
Binary file
|
html_to_markdown/options.py
CHANGED
|
@@ -128,8 +128,8 @@ class PreprocessingOptions:
|
|
|
128
128
|
... )
|
|
129
129
|
"""
|
|
130
130
|
|
|
131
|
-
enabled: bool =
|
|
132
|
-
"""Whether to enable HTML preprocessing (
|
|
131
|
+
enabled: bool = True
|
|
132
|
+
"""Whether to enable HTML preprocessing (enabled by default for robust handling of malformed HTML)."""
|
|
133
133
|
|
|
134
134
|
preset: Literal["minimal", "standard", "aggressive"] = "standard"
|
|
135
135
|
"""Preprocessing aggressiveness level."""
|
|
Binary file
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: html-to-markdown
|
|
3
|
-
Version: 2.4.
|
|
3
|
+
Version: 2.4.2
|
|
4
4
|
Classifier: Development Status :: 5 - Production/Stable
|
|
5
5
|
Classifier: Environment :: Console
|
|
6
6
|
Classifier: Intended Audience :: Developers
|
|
@@ -162,9 +162,12 @@ Key fields (see docstring for full matrix):
|
|
|
162
162
|
|
|
163
163
|
### `PreprocessingOptions`
|
|
164
164
|
|
|
165
|
-
- `enabled`: enable HTML sanitisation
|
|
166
|
-
- `preset`: `"minimal" | "standard" | "aggressive"`
|
|
167
|
-
- `remove_navigation
|
|
165
|
+
- `enabled`: enable HTML sanitisation (default: `True` since v2.4.2 for robust malformed HTML handling)
|
|
166
|
+
- `preset`: `"minimal" | "standard" | "aggressive"` (default: `"standard"`)
|
|
167
|
+
- `remove_navigation`: remove navigation elements (default: `True`)
|
|
168
|
+
- `remove_forms`: remove form elements (default: `True`)
|
|
169
|
+
|
|
170
|
+
**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.
|
|
168
171
|
|
|
169
172
|
### `InlineImageConfig`
|
|
170
173
|
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
html_to_markdown-2.4.2.data/scripts/html-to-markdown.exe,sha256=QZE0yre_OpAgh30pYOtAnrfcOV4GE9MWaY1b7zEZZHc,4506624
|
|
2
|
+
html_to_markdown-2.4.2.dist-info/METADATA,sha256=0nWVx7GGOHsCRBr-KL-U_n60C3XKJpGNi44MBLXeOsg,9403
|
|
3
|
+
html_to_markdown-2.4.2.dist-info/WHEEL,sha256=4EDp_7DiFfWl1yYv5M4wSosAn5L_xgD1dyrQxQxfCx8,95
|
|
4
|
+
html_to_markdown-2.4.2.dist-info/licenses/LICENSE,sha256=QhKFMkQLa4mSUlOsyG9VElzC7GYbAKtiS_EwOCyH-b4,1107
|
|
5
|
+
html_to_markdown/__init__.py,sha256=lUaiep0SHCyeU74Qedl423s10ZfKru2VxQsOSMLCSJQ,1410
|
|
6
|
+
html_to_markdown/__main__.py,sha256=5objj9lB7hhpSpZsDok5tv9o9yztVR63Ccww-pXsAyY,343
|
|
7
|
+
html_to_markdown/_html_to_markdown.pyd,sha256=peYlzkWU0gDJ0UrRJM778-p5XmA_lVvon7He9yfAhDA,4225536
|
|
8
|
+
html_to_markdown/_rust.pyi,sha256=JP8tvcjYDfFJeJkbLpQ4qeK-5jl0hzIVT3Sa0daTkyo,2171
|
|
9
|
+
html_to_markdown/api.py,sha256=jDb8PT1cS3KqipT4m_rKBE0R20UKOU85rH-7M6P6Owk,5003
|
|
10
|
+
html_to_markdown/bin/html-to-markdown.exe,sha256=QZE0yre_OpAgh30pYOtAnrfcOV4GE9MWaY1b7zEZZHc,4506624
|
|
11
|
+
html_to_markdown/cli.py,sha256=z59l8sF8wIRRzJtUd-tXgqiC0WTqkTjzl-df8Ey_oQ0,67
|
|
12
|
+
html_to_markdown/cli_proxy.py,sha256=JGOuINBI8OMYLxojXGz8DdzMHo8eqgdINstOZWrdw-8,3816
|
|
13
|
+
html_to_markdown/exceptions.py,sha256=31VqpPi4JLGv7lI2481Z4f2s5ejYmq97c3s-WFFkXVU,2443
|
|
14
|
+
html_to_markdown/options.py,sha256=yW0OJ0PZvsPXHT0bpWMDYIcvjjiI9YT_BT6Ax5R0ESs,5063
|
|
15
|
+
html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
16
|
+
html_to_markdown/v1_compat.py,sha256=aVt9cVTBfYcrS8EfBsrC6HQwWc3Kz9-65-LB9foN6Jk,8227
|
|
17
|
+
html_to_markdown-2.4.2.dist-info/RECORD,,
|
|
@@ -1,17 +0,0 @@
|
|
|
1
|
-
html_to_markdown-2.4.1.data/scripts/html-to-markdown.exe,sha256=C7lSkItGKC-rxUTJ1-s_lLM4mgsNYKAF1aA1ctQjTJE,4476928
|
|
2
|
-
html_to_markdown-2.4.1.dist-info/METADATA,sha256=ONL8X8T_EPsCf6LmWEnNozk5IFmfkWdp-IYjMD_u2K8,9012
|
|
3
|
-
html_to_markdown-2.4.1.dist-info/WHEEL,sha256=4EDp_7DiFfWl1yYv5M4wSosAn5L_xgD1dyrQxQxfCx8,95
|
|
4
|
-
html_to_markdown-2.4.1.dist-info/licenses/LICENSE,sha256=QhKFMkQLa4mSUlOsyG9VElzC7GYbAKtiS_EwOCyH-b4,1107
|
|
5
|
-
html_to_markdown/__init__.py,sha256=RMyWY2awLrpssSrYn0eh-BnlGgDxcK8dhSXAj5_Upbc,1410
|
|
6
|
-
html_to_markdown/__main__.py,sha256=5objj9lB7hhpSpZsDok5tv9o9yztVR63Ccww-pXsAyY,343
|
|
7
|
-
html_to_markdown/_html_to_markdown.pyd,sha256=0OYBHg29UeEQ3tHzdUL0CyinV1T3V5ed1L5Nto7oI50,4223488
|
|
8
|
-
html_to_markdown/_rust.pyi,sha256=JP8tvcjYDfFJeJkbLpQ4qeK-5jl0hzIVT3Sa0daTkyo,2171
|
|
9
|
-
html_to_markdown/api.py,sha256=jDb8PT1cS3KqipT4m_rKBE0R20UKOU85rH-7M6P6Owk,5003
|
|
10
|
-
html_to_markdown/bin/html-to-markdown.exe,sha256=C7lSkItGKC-rxUTJ1-s_lLM4mgsNYKAF1aA1ctQjTJE,4476928
|
|
11
|
-
html_to_markdown/cli.py,sha256=z59l8sF8wIRRzJtUd-tXgqiC0WTqkTjzl-df8Ey_oQ0,67
|
|
12
|
-
html_to_markdown/cli_proxy.py,sha256=JGOuINBI8OMYLxojXGz8DdzMHo8eqgdINstOZWrdw-8,3816
|
|
13
|
-
html_to_markdown/exceptions.py,sha256=31VqpPi4JLGv7lI2481Z4f2s5ejYmq97c3s-WFFkXVU,2443
|
|
14
|
-
html_to_markdown/options.py,sha256=jna7fx9bHhx8N7u5IYtMXganFFzdJSVVgLZW0tYk3GA,5054
|
|
15
|
-
html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
16
|
-
html_to_markdown/v1_compat.py,sha256=aVt9cVTBfYcrS8EfBsrC6HQwWc3Kz9-65-LB9foN6Jk,8227
|
|
17
|
-
html_to_markdown-2.4.1.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|