Parse PDF files containing Japan travel recommendations - extracts text, links, and structure. Use when asked to process or parse PDF files.
Ensure the virtual environment is active and dependencies are installed:
source .venv/bin/activate 2>/dev/null || (python3 -m venv .venv && source .venv/bin/activate)
pip install -q -r requirements.txt
Parse the following PDF file(s): $ARGUMENTS
Run the parser:
source .venv/bin/activate && python scripts/parse_pdf.py $ARGUMENTS
This will:
data/raw/pdfs/<filename>.json/process-reel)!find notes/ -name "*.pdf" 2>/dev/null || echo "No PDFs in notes/ yet"
!ls data/raw/pdfs/*.json 2>/dev/null || echo "No PDFs parsed yet"