html-to-markdown 1.4.0__py3-none-any.whl → 1.6.0__py3-none-any.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 +19 -2
- html_to_markdown/cli.py +103 -25
- html_to_markdown/constants.py +1 -0
- html_to_markdown/converters.py +1646 -104
- html_to_markdown/exceptions.py +49 -0
- html_to_markdown/processing.py +720 -47
- html_to_markdown-1.6.0.dist-info/METADATA +472 -0
- html_to_markdown-1.6.0.dist-info/RECORD +15 -0
- html_to_markdown-1.4.0.dist-info/METADATA +0 -249
- html_to_markdown-1.4.0.dist-info/RECORD +0 -14
- {html_to_markdown-1.4.0.dist-info → html_to_markdown-1.6.0.dist-info}/WHEEL +0 -0
- {html_to_markdown-1.4.0.dist-info → html_to_markdown-1.6.0.dist-info}/entry_points.txt +0 -0
- {html_to_markdown-1.4.0.dist-info → html_to_markdown-1.6.0.dist-info}/licenses/LICENSE +0 -0
- {html_to_markdown-1.4.0.dist-info → html_to_markdown-1.6.0.dist-info}/top_level.txt +0 -0
|
@@ -1,249 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: html-to-markdown
|
|
3
|
-
Version: 1.4.0
|
|
4
|
-
Summary: A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options
|
|
5
|
-
Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
|
|
6
|
-
License: MIT
|
|
7
|
-
Project-URL: Changelog, https://github.com/Goldziher/html-to-markdown/releases
|
|
8
|
-
Project-URL: Homepage, https://github.com/Goldziher/html-to-markdown
|
|
9
|
-
Project-URL: Issues, https://github.com/Goldziher/html-to-markdown/issues
|
|
10
|
-
Project-URL: Repository, https://github.com/Goldziher/html-to-markdown.git
|
|
11
|
-
Keywords: beautifulsoup,cli-tool,converter,html,html2markdown,markdown,markup,text-extraction,text-processing
|
|
12
|
-
Classifier: Development Status :: 5 - Production/Stable
|
|
13
|
-
Classifier: Environment :: Console
|
|
14
|
-
Classifier: Intended Audience :: Developers
|
|
15
|
-
Classifier: License :: OSI Approved :: MIT License
|
|
16
|
-
Classifier: Operating System :: OS Independent
|
|
17
|
-
Classifier: Programming Language :: Python :: 3 :: Only
|
|
18
|
-
Classifier: Programming Language :: Python :: 3.9
|
|
19
|
-
Classifier: Programming Language :: Python :: 3.10
|
|
20
|
-
Classifier: Programming Language :: Python :: 3.11
|
|
21
|
-
Classifier: Programming Language :: Python :: 3.12
|
|
22
|
-
Classifier: Programming Language :: Python :: 3.13
|
|
23
|
-
Classifier: Topic :: Internet :: WWW/HTTP
|
|
24
|
-
Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
25
|
-
Classifier: Topic :: Text Processing
|
|
26
|
-
Classifier: Topic :: Text Processing :: Markup
|
|
27
|
-
Classifier: Topic :: Text Processing :: Markup :: HTML
|
|
28
|
-
Classifier: Topic :: Text Processing :: Markup :: Markdown
|
|
29
|
-
Classifier: Topic :: Utilities
|
|
30
|
-
Classifier: Typing :: Typed
|
|
31
|
-
Requires-Python: >=3.9
|
|
32
|
-
Description-Content-Type: text/markdown
|
|
33
|
-
License-File: LICENSE
|
|
34
|
-
Requires-Dist: beautifulsoup4>=4.13.4
|
|
35
|
-
Dynamic: license-file
|
|
36
|
-
|
|
37
|
-
# html-to-markdown
|
|
38
|
-
|
|
39
|
-
A modern, fully typed Python library for converting HTML to Markdown. This library is a completely rewritten fork
|
|
40
|
-
of [markdownify](https://pypi.org/project/markdownify/) with a modernized codebase, strict type safety and support for
|
|
41
|
-
Python 3.9+.
|
|
42
|
-
|
|
43
|
-
## Features
|
|
44
|
-
|
|
45
|
-
- Full type safety with strict MyPy adherence
|
|
46
|
-
- Functional API design
|
|
47
|
-
- Extensive test coverage
|
|
48
|
-
- Configurable conversion options
|
|
49
|
-
- CLI tool for easy conversions
|
|
50
|
-
- Support for pre-configured BeautifulSoup instances
|
|
51
|
-
- Strict semver versioning
|
|
52
|
-
|
|
53
|
-
## Installation
|
|
54
|
-
|
|
55
|
-
```shell
|
|
56
|
-
pip install html-to-markdown
|
|
57
|
-
```
|
|
58
|
-
|
|
59
|
-
## Quick Start
|
|
60
|
-
|
|
61
|
-
Convert HTML to Markdown with a single function call:
|
|
62
|
-
|
|
63
|
-
```python
|
|
64
|
-
from html_to_markdown import convert_to_markdown
|
|
65
|
-
|
|
66
|
-
html = """
|
|
67
|
-
<article>
|
|
68
|
-
<h1>Welcome</h1>
|
|
69
|
-
<p>This is a <strong>sample</strong> with a <a href="https://example.com">link</a>.</p>
|
|
70
|
-
<ul>
|
|
71
|
-
<li>Item 1</li>
|
|
72
|
-
<li>Item 2</li>
|
|
73
|
-
</ul>
|
|
74
|
-
</article>
|
|
75
|
-
"""
|
|
76
|
-
|
|
77
|
-
markdown = convert_to_markdown(html)
|
|
78
|
-
print(markdown)
|
|
79
|
-
```
|
|
80
|
-
|
|
81
|
-
Output:
|
|
82
|
-
|
|
83
|
-
```markdown
|
|
84
|
-
# Welcome
|
|
85
|
-
|
|
86
|
-
This is a **sample** with a [link](https://example.com).
|
|
87
|
-
|
|
88
|
-
* Item 1
|
|
89
|
-
* Item 2
|
|
90
|
-
```
|
|
91
|
-
|
|
92
|
-
### Working with BeautifulSoup
|
|
93
|
-
|
|
94
|
-
If you need more control over HTML parsing, you can pass a pre-configured BeautifulSoup instance:
|
|
95
|
-
|
|
96
|
-
```python
|
|
97
|
-
from bs4 import BeautifulSoup
|
|
98
|
-
from html_to_markdown import convert_to_markdown
|
|
99
|
-
|
|
100
|
-
# Configure BeautifulSoup with your preferred parser
|
|
101
|
-
soup = BeautifulSoup(html, "lxml") # Note: lxml requires additional installation
|
|
102
|
-
markdown = convert_to_markdown(soup)
|
|
103
|
-
```
|
|
104
|
-
|
|
105
|
-
## Advanced Usage
|
|
106
|
-
|
|
107
|
-
### Customizing Conversion Options
|
|
108
|
-
|
|
109
|
-
The library offers extensive customization through various options:
|
|
110
|
-
|
|
111
|
-
```python
|
|
112
|
-
from html_to_markdown import convert_to_markdown
|
|
113
|
-
|
|
114
|
-
html = "<div>Your content here...</div>"
|
|
115
|
-
markdown = convert_to_markdown(
|
|
116
|
-
html,
|
|
117
|
-
heading_style="atx", # Use # style headers
|
|
118
|
-
strong_em_symbol="*", # Use * for bold/italic
|
|
119
|
-
bullets="*+-", # Define bullet point characters
|
|
120
|
-
wrap=True, # Enable text wrapping
|
|
121
|
-
wrap_width=100, # Set wrap width
|
|
122
|
-
escape_asterisks=True, # Escape * characters
|
|
123
|
-
code_language="python", # Default code block language
|
|
124
|
-
)
|
|
125
|
-
```
|
|
126
|
-
|
|
127
|
-
### Custom Converters
|
|
128
|
-
|
|
129
|
-
You can provide your own conversion functions for specific HTML tags:
|
|
130
|
-
|
|
131
|
-
```python
|
|
132
|
-
from bs4.element import Tag
|
|
133
|
-
from html_to_markdown import convert_to_markdown
|
|
134
|
-
|
|
135
|
-
# Define a custom converter for the <b> tag
|
|
136
|
-
def custom_bold_converter(*, tag: Tag, text: str, **kwargs) -> str:
|
|
137
|
-
return f"IMPORTANT: {text}"
|
|
138
|
-
|
|
139
|
-
html = "<p>This is a <b>bold statement</b>.</p>"
|
|
140
|
-
markdown = convert_to_markdown(html, custom_converters={"b": custom_bold_converter})
|
|
141
|
-
print(markdown)
|
|
142
|
-
# Output: This is a IMPORTANT: bold statement.
|
|
143
|
-
```
|
|
144
|
-
|
|
145
|
-
Custom converters take precedence over the built-in converters and can be used alongside other configuration options.
|
|
146
|
-
|
|
147
|
-
### Configuration Options
|
|
148
|
-
|
|
149
|
-
| Option | Type | Default | Description |
|
|
150
|
-
| -------------------- | ---- | -------------- | ------------------------------------------------------ |
|
|
151
|
-
| `autolinks` | bool | `True` | Auto-convert URLs to Markdown links |
|
|
152
|
-
| `bullets` | str | `'*+-'` | Characters to use for bullet points |
|
|
153
|
-
| `code_language` | str | `''` | Default language for code blocks |
|
|
154
|
-
| `heading_style` | str | `'underlined'` | Header style (`'underlined'`, `'atx'`, `'atx_closed'`) |
|
|
155
|
-
| `escape_asterisks` | bool | `True` | Escape * characters |
|
|
156
|
-
| `escape_underscores` | bool | `True` | Escape _ characters |
|
|
157
|
-
| `wrap` | bool | `False` | Enable text wrapping |
|
|
158
|
-
| `wrap_width` | int | `80` | Text wrap width |
|
|
159
|
-
|
|
160
|
-
For a complete list of options, see the [Configuration](#configuration) section below.
|
|
161
|
-
|
|
162
|
-
## CLI Usage
|
|
163
|
-
|
|
164
|
-
Convert HTML files directly from the command line:
|
|
165
|
-
|
|
166
|
-
```shell
|
|
167
|
-
# Convert a file
|
|
168
|
-
html_to_markdown input.html > output.md
|
|
169
|
-
|
|
170
|
-
# Process stdin
|
|
171
|
-
cat input.html | html_to_markdown > output.md
|
|
172
|
-
|
|
173
|
-
# Use custom options
|
|
174
|
-
html_to_markdown --heading-style atx --wrap --wrap-width 100 input.html > output.md
|
|
175
|
-
```
|
|
176
|
-
|
|
177
|
-
View all available options:
|
|
178
|
-
|
|
179
|
-
```shell
|
|
180
|
-
html_to_markdown --help
|
|
181
|
-
```
|
|
182
|
-
|
|
183
|
-
## Migration from Markdownify
|
|
184
|
-
|
|
185
|
-
For existing projects using Markdownify, a compatibility layer is provided:
|
|
186
|
-
|
|
187
|
-
```python
|
|
188
|
-
# Old code
|
|
189
|
-
from markdownify import markdownify as md
|
|
190
|
-
|
|
191
|
-
# New code - works the same way
|
|
192
|
-
from html_to_markdown import markdownify as md
|
|
193
|
-
```
|
|
194
|
-
|
|
195
|
-
The `markdownify` function is an alias for `convert_to_markdown` and provides identical functionality.
|
|
196
|
-
|
|
197
|
-
## Configuration
|
|
198
|
-
|
|
199
|
-
Full list of configuration options:
|
|
200
|
-
|
|
201
|
-
- `autolinks`: Convert valid URLs to Markdown links automatically
|
|
202
|
-
- `bullets`: Characters to use for bullet points in lists
|
|
203
|
-
- `code_language`: Default language for fenced code blocks
|
|
204
|
-
- `code_language_callback`: Function to determine code block language
|
|
205
|
-
- `convert`: List of HTML tags to convert (None = all supported tags)
|
|
206
|
-
- `default_title`: Use default titles for elements like links
|
|
207
|
-
- `escape_asterisks`: Escape * characters
|
|
208
|
-
- `escape_misc`: Escape miscellaneous Markdown characters
|
|
209
|
-
- `escape_underscores`: Escape _ characters
|
|
210
|
-
- `heading_style`: Header style (underlined/atx/atx_closed)
|
|
211
|
-
- `keep_inline_images_in`: Tags where inline images should be kept
|
|
212
|
-
- `newline_style`: Style for handling newlines (spaces/backslash)
|
|
213
|
-
- `strip`: Tags to remove from output
|
|
214
|
-
- `strong_em_symbol`: Symbol for strong/emphasized text (\* or \_)
|
|
215
|
-
- `sub_symbol`: Symbol for subscript text
|
|
216
|
-
- `sup_symbol`: Symbol for superscript text
|
|
217
|
-
- `wrap`: Enable text wrapping
|
|
218
|
-
- `wrap_width`: Width for text wrapping
|
|
219
|
-
- `convert_as_inline`: Treat content as inline elements
|
|
220
|
-
- `custom_converters`: A mapping of HTML tag names to custom converter functions
|
|
221
|
-
|
|
222
|
-
## Contribution
|
|
223
|
-
|
|
224
|
-
This library is open to contribution. Feel free to open issues or submit PRs. Its better to discuss issues before
|
|
225
|
-
submitting PRs to avoid disappointment.
|
|
226
|
-
|
|
227
|
-
### Local Development
|
|
228
|
-
|
|
229
|
-
1. Clone the repo
|
|
230
|
-
|
|
231
|
-
1. Install the system dependencies
|
|
232
|
-
|
|
233
|
-
1. Install the full dependencies with `uv sync`
|
|
234
|
-
|
|
235
|
-
1. Install the pre-commit hooks with:
|
|
236
|
-
|
|
237
|
-
```shell
|
|
238
|
-
pre-commit install && pre-commit install --hook-type commit-msg
|
|
239
|
-
```
|
|
240
|
-
|
|
241
|
-
1. Make your changes and submit a PR
|
|
242
|
-
|
|
243
|
-
## License
|
|
244
|
-
|
|
245
|
-
This library uses the MIT license.
|
|
246
|
-
|
|
247
|
-
## Acknowledgments
|
|
248
|
-
|
|
249
|
-
Special thanks to the original [markdownify](https://pypi.org/project/markdownify/) project creators and contributors.
|
|
@@ -1,14 +0,0 @@
|
|
|
1
|
-
html_to_markdown/__init__.py,sha256=95S7_7mR_g88uTnFI0FaRNykrtAaSKb6sJbwSea2zjk,145
|
|
2
|
-
html_to_markdown/__main__.py,sha256=DJyJX7NIK0BVPNS2r3BYJ0Ci_lKHhgVOpw7ZEqACH3c,323
|
|
3
|
-
html_to_markdown/cli.py,sha256=Kfh2sF_ySE_fQ0qdwvUZ5Rqx-P4Y12uTpG8xF60gAq0,4789
|
|
4
|
-
html_to_markdown/constants.py,sha256=Usk67k18tuRovJpKDsiEXdgH20KgqI9KOnK4Fbx-M5c,547
|
|
5
|
-
html_to_markdown/converters.py,sha256=SHRAV1qIFQQdXSD_TToR_F_t8hw3-amz8rIs2Q84YbQ,12276
|
|
6
|
-
html_to_markdown/processing.py,sha256=mzF6YNqhj2VoRN6_TafnZ4ZndOyFglsZXTNnOl4uvWM,10564
|
|
7
|
-
html_to_markdown/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
8
|
-
html_to_markdown/utils.py,sha256=HJUDej5HSpXRtYv-OkCyD0hwnPnVfQCwY6rBRlIOt9s,1989
|
|
9
|
-
html_to_markdown-1.4.0.dist-info/licenses/LICENSE,sha256=3J_HR5BWvUM1mlIrlkF32-uC1FM64gy8JfG17LBuheQ,1122
|
|
10
|
-
html_to_markdown-1.4.0.dist-info/METADATA,sha256=LmjDer-QQkH6kSlkua1NBhnaKpIu4sVvyJZPPX5PgLk,8229
|
|
11
|
-
html_to_markdown-1.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
12
|
-
html_to_markdown-1.4.0.dist-info/entry_points.txt,sha256=xmFijrTfgYW7lOrZxZGRPciicQHa5KiXKkUhBCmICtQ,116
|
|
13
|
-
html_to_markdown-1.4.0.dist-info/top_level.txt,sha256=Ev6djb1c4dSKr_-n4K-FpEGDkzBigXY6LuZ5onqS7AE,17
|
|
14
|
-
html_to_markdown-1.4.0.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|