# Virtual environment
venv/
.venv/

# Python cache
__pycache__/
*.py[cod]
*.egg-info/

# Pipeline outputs (large, regenerated each run)
output/
uploads/

# Input newspaper PDFs (large binary data)
*.pdf

# Scratch / diagnostic preview images
_*.png
pg-*.jpg
q-*.jpg
gp-*.jpg
gq-*.jpg

# Generated HTML guides
Extractor_Guide.html
HOW_IT_WORKS.html

# Secrets / API keys (never commit)
.keyenv
.env
.env.*

# OS / editor cruft
~$*
.DS_Store
*.swp
.idea/
.vscode/

# Data directories and temp files
input/
processed/
NewsPapers/
_tess_tmp/
scratch_py/
*.log
_*.txt
