# clean_html_for_llm
This library provides a method to clean HTML content by removing specified tags and attributes while keeping specified attributes. It is particularly useful for preprocessing HTML data to remove noisy tags, making it easier for language models (LLMs) to understand the HTML and generate accurate responses.
This is helpful if you are querying LLMs with your HTML data.
## Installation
You can install the `clean_html_for_llm` library using pip:
```bash
pip install clean-html-for-llm
```
## Usage
```python
from clean_html_for_llm import clean_html
html_content = '<div id="main" style="color:red">Hello <script>alert("World")</script></div>'
cleaned_html = clean_html(html_content, tags_to_remove=['script'], attributes_to_keep=['id'])
print(cleaned_html)
# Output: '<div id="main">Hello </div>'
```
The `clean_html` function takes the following arguments:
- `html_to_clean` (str): The HTML content to clean.
- `tags_to_remove` (List[str]): List of tags to remove from the HTML content. Default is `['style', 'svg', 'script']`.
- `attributes_to_keep` (List[str]): List of attributes to keep in the HTML tags. Default is `['id', 'href']`.
You can customize the tags and attributes to remove or keep based on your requirements.
## Examples
### Example 1:
```python
html_content = '<div id="content" class="main">This is a <span style="font-size: 18px;">paragraph</span>.</div>'
cleaned_html = clean_html(html_content)
print(cleaned_html)
# Output: '<div id="content">This is a <span>paragraph</span>.</div>'
```
### Example 2:
```python
html_content = '<p class="content">Click <a href="https://example.com">here</a> for more information.</p>'
cleaned_html = clean_html(html_content, tags_to_remove=['a'], attributes_to_keep=['class'])
print(cleaned_html)
# Output: '<p class="content">Click </p>'
```
## License
This library is released under the MIT License. See [LICENSE](LICENSE) for details.
Raw data
{
"_id": null,
"home_page": "https://github.com/shubhamofbce/clean-html-for-llm.git",
"name": "clean-html-for-llm",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "html cleaning, html cleaning for llm, html denoise for llm, html denoising for llm, html cleaning for language model, html denoise for language model, html denoising for language model, html cleaning for nlp, html denoise for nlp, html denoising for nlp",
"author": "Shubham Raj",
"author_email": "sraj13169@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/f0/ef/bdaccf53409f54dae633ca584ce420d4f8868745d17e2d534192c0615fe2/clean_html_for_llm-1.3.2.tar.gz",
"platform": null,
"description": "# clean_html_for_llm\n\nThis library provides a method to clean HTML content by removing specified tags and attributes while keeping specified attributes. It is particularly useful for preprocessing HTML data to remove noisy tags, making it easier for language models (LLMs) to understand the HTML and generate accurate responses.\nThis is helpful if you are querying LLMs with your HTML data.\n\n\n\n\n\n## Installation\n\nYou can install the `clean_html_for_llm` library using pip:\n\n```bash\npip install clean-html-for-llm\n```\n\n## Usage\n\n```python\nfrom clean_html_for_llm import clean_html\n\nhtml_content = '<div id=\"main\" style=\"color:red\">Hello <script>alert(\"World\")</script></div>'\ncleaned_html = clean_html(html_content, tags_to_remove=['script'], attributes_to_keep=['id'])\nprint(cleaned_html)\n# Output: '<div id=\"main\">Hello </div>'\n```\n\nThe `clean_html` function takes the following arguments:\n\n- `html_to_clean` (str): The HTML content to clean.\n- `tags_to_remove` (List[str]): List of tags to remove from the HTML content. Default is `['style', 'svg', 'script']`.\n- `attributes_to_keep` (List[str]): List of attributes to keep in the HTML tags. Default is `['id', 'href']`.\n\nYou can customize the tags and attributes to remove or keep based on your requirements.\n\n## Examples\n\n### Example 1:\n\n```python\nhtml_content = '<div id=\"content\" class=\"main\">This is a <span style=\"font-size: 18px;\">paragraph</span>.</div>'\ncleaned_html = clean_html(html_content)\nprint(cleaned_html)\n# Output: '<div id=\"content\">This is a <span>paragraph</span>.</div>'\n```\n\n### Example 2:\n\n```python\nhtml_content = '<p class=\"content\">Click <a href=\"https://example.com\">here</a> for more information.</p>'\ncleaned_html = clean_html(html_content, tags_to_remove=['a'], attributes_to_keep=['class'])\nprint(cleaned_html)\n# Output: '<p class=\"content\">Click </p>'\n```\n\n## License\n\nThis library is released under the MIT License. See [LICENSE](LICENSE) for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A library for cleaning HTML content by removing specified tags and attributes.",
"version": "1.3.2",
"project_urls": {
"Homepage": "https://github.com/shubhamofbce/clean-html-for-llm.git"
},
"split_keywords": [
"html cleaning",
" html cleaning for llm",
" html denoise for llm",
" html denoising for llm",
" html cleaning for language model",
" html denoise for language model",
" html denoising for language model",
" html cleaning for nlp",
" html denoise for nlp",
" html denoising for nlp"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f90f32dab024ae329c19da55a69defecfbd6e658ef00ed6ea440f8aa1e8991eb",
"md5": "e12a002f63f24c7b0430c0b16e537c30",
"sha256": "0d33c726627be03b63bcc9880ef9f7cab9863969443de31fe4d26d84e7733545"
},
"downloads": -1,
"filename": "clean_html_for_llm-1.3.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e12a002f63f24c7b0430c0b16e537c30",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 4014,
"upload_time": "2024-04-10T12:24:53",
"upload_time_iso_8601": "2024-04-10T12:24:53.094491Z",
"url": "https://files.pythonhosted.org/packages/f9/0f/32dab024ae329c19da55a69defecfbd6e658ef00ed6ea440f8aa1e8991eb/clean_html_for_llm-1.3.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "f0efbdaccf53409f54dae633ca584ce420d4f8868745d17e2d534192c0615fe2",
"md5": "ef3064246c004f8e99bec6036a82e247",
"sha256": "d39f1fe6761ff84f1917ced1c04985aa2411100f8ea3169475d55c78024971ae"
},
"downloads": -1,
"filename": "clean_html_for_llm-1.3.2.tar.gz",
"has_sig": false,
"md5_digest": "ef3064246c004f8e99bec6036a82e247",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 3339,
"upload_time": "2024-04-10T12:24:54",
"upload_time_iso_8601": "2024-04-10T12:24:54.772542Z",
"url": "https://files.pythonhosted.org/packages/f0/ef/bdaccf53409f54dae633ca584ce420d4f8868745d17e2d534192c0615fe2/clean_html_for_llm-1.3.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-10 12:24:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "shubhamofbce",
"github_project": "clean-html-for-llm",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "clean-html-for-llm"
}
JSON
