requirements.txt•489 B
httpx>=0.20.0,<1.0.0
beautifulsoup4>=4.9.0,<5.0.0
pydantic>=1.8.0,<3.0.0
tzdata>=2022.1 # For timezone support
trafilatura>=1.8.0,<2.0.0 # For main content extraction
python-dateutil>=2.8.0,<3.0.0 # For robust date parsing
cachetools>=5.0.0,<6.0.0 # For caching get_website results
filetype>=1.1.0,<2.0.0 # For detecting file types when processing get_website results
pymupdf>=1.20.0,<2.0.0 # For converting PDFs to plaintext
pymupdf4llm>=0.0.20,<0.1 # For MD formatting of converted PDFs