PyPI page
Home page
Author:
Ali Zahid Raja
Summary:
Web scraper and crawler that converts websites to clean Markdown with byte-level provenance for LLM/RAG knowledge bases
Latest version:
2.4.3
Required dependencies:
beautifulsoup4
|
click
|
defusedxml
|
httpcore
|
httpx
|
lxml
|
pyyaml
|
rich
|
warcio
Optional dependencies:
cryptography
|
langchain-core
|
llama-index-core
|
markitdown
|
mcp
|
pyarrow
|
pytest
|
python-frontmatter
|
torch
|
transformers
Downloads last day:
1
Downloads last week:
203
Downloads last month:
1,171
7-day smoothing