Convert URL content to markdown for better LLM context.
Project description
site2markdown
A robust Python utility to convert web pages into clean, structured Markdown. Optimized for generating high-quality context for Large Language Models (LLMs).
Installation
pip install site2markdown
Usage
Quick Start
from site2markdown import UrlToMarkdown
converter = UrlToMarkdown()
# Convert URL to Markdown
markdown = converter.convert(
url="https://www.example.com",
inline_title=True, # Include the page title as an H1
ignore_links=False, # Preserve hyper-links
improve_readability=True # Use readability algorithm to filter boilerplate
)
print(markdown)
Converting HTML Content
from site2markdown import UrlToMarkdown
converter = UrlToMarkdown()
html_content = "<html><body><h1>Example</h1><p>Text content.</p></body></html>"
markdown = converter.convert_html(
html=html_content,
url="https://www.example.com", # Optional: base URL for resolving relative paths
inline_title=True,
improve_readability=True
)
print(markdown)
Core Features
- LLM Optimized: Produces clean text with minimal noise, ideal for RAG and LLM context.
- Smart Filtering: Automatic removal of scripts, styles, and non-content elements.
- Specialized Handling: Custom parsing logic for sites like Stack Overflow, Wikipedia, and Medium.
- Readability Engine: Integration with Mozilla's Readability algorithm to extract the main article body and skip navigation/sidebars.
- Structure Preservation: Reliable conversion of code blocks, tables, and nested lists.
- URL Resolution: Automatically converts relative links and image paths to absolute URLs.
Configuration Options
| Option | Type | Description | Default |
|---|---|---|---|
inline_title |
bool |
Includes the page title as an H1 heading at the top. | True |
ignore_links |
bool |
Removes all hyperlinks from the output. | False |
improve_readability |
bool |
Processes the page through a readability filter before conversion. | True |
License
This project is licensed under the MIT License.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
site2markdown-1.0.2.tar.gz
(10.2 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file site2markdown-1.0.2.tar.gz.
File metadata
- Download URL: site2markdown-1.0.2.tar.gz
- Upload date:
- Size: 10.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
58e128bc8fd48428e830330ae776d7e7e29660369ed0740241264f3dd3198653
|
|
| MD5 |
0c2bd649283fc4ebc57c0ccd7f42160a
|
|
| BLAKE2b-256 |
f1c988e78ffd405fe9000f04ad7502f0ee7d0da707b0904ac183463365f6da45
|
File details
Details for the file site2markdown-1.0.2-py3-none-any.whl.
File metadata
- Download URL: site2markdown-1.0.2-py3-none-any.whl
- Upload date:
- Size: 11.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c30729a8dadf94096f69ec41ab0bdeb41350134854ae177487cffa7c6b853314
|
|
| MD5 |
e9e099d7e2ab09bcf7a8b7299b50c33f
|
|
| BLAKE2b-256 |
2fce4efa64595608b6f905c9f668bee6b42269e0efa42f9d18a6418d928437e8
|
