# Iran Chemical Database — Python dependencies
# HTTrack-powered live crawling architecture (see SKILL.md / docs/)

# ---- API / web ----
fastapi>=0.115
uvicorn[standard]>=0.30
pydantic>=2.8
pydantic-settings>=2.4
python-multipart>=0.0.9

# ---- Database ----
sqlalchemy>=2.0
psycopg2-binary>=2.9
alembic>=1.13
redis>=5.0

# ---- Task queue ----
celery>=5.4

# ---- Crawling / mirroring ----
# httrack is a SYSTEM package:  sudo apt install httrack libhttrack-dev

# ---- HTML parsing (local mirror files only) ----
beautifulsoup4>=4.12
lxml>=5.2
parsel>=1.9

# ---- PDF / Excel parsing ----
pdfplumber>=0.11
PyMuPDF>=1.24
openpyxl>=3.1
pandas>=2.2
# camelot-py[cv]>=0.11   # optional: heavy PDF table extraction (needs ghostscript+opencv)

# ---- JS fallback ----
playwright>=1.45          # run: playwright install chromium

# ---- Chemistry ----
rdkit>=2024.03
pubchempy>=1.0.4

# ---- Persian NLP ----
hazm>=0.9
parsivar>=0.2
langdetect>=1.0.9

# ---- Dashboard ----
streamlit>=1.36
dash>=2.17
plotly>=5.22

# ---- Config / misc ----
PyYAML>=6.0
python-dotenv>=1.0
requests>=2.32
httpx>=0.27
