# Virtual environment
venv/
.venv/
.venv*/

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

# Pipeline inputs and outputs (large, regenerated each run)
input/
output/
processed/
uploads/
NewsPapers/

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

# Scratch / diagnostic files and directories
_*.png
pg-*.jpg
q-*.jpg
gp-*.jpg
gq-*.jpg
_*.log
_*.py
_*.txt
_tess_tmp/
scratch_py/
test_*.py
fix_pdf.py
app_py_utf8.txt
original_app_py.txt

# Generated guides
Extractor_Guide.html
HOW_IT_WORKS.html

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

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