requirements.txt

requests==2.34.2
beautifulsoup4==4.14.3
lxml==6.1.1
pandas==3.0.3
tqdm==4.67.3
networkx==3.6.1
setuptools>=75.0.0
python-Wappalyzer==0.3.1

# HTML → Markdown extraction (page_markdown package)
markdownify>=0.13,<1

# Local content analysis (duplicates, language)
rapidfuzz==3.14.5
langdetect==1.0.9

# Google Search Console + GA4 integration (optional; required for `python -m src google`)
google-auth==2.53.0
google-auth-oauthlib==1.4.0
google-api-python-client==2.197.0
google-analytics-data==0.23.0
google-analytics-admin==0.30.0
# Google Ads API for Keyword Planner (optional; required for enable_google_keyword_planner)
google-ads==31.0.0

# Keywords Explorer — Google Suggest + Wikipedia + Datamuse (all free, no auth needed)
# requests already listed above
# pytrends is OPTIONAL and frequently rate-limited — uncomment only if you need trend direction
# pytrends>=4.9,<5

# PostgreSQL
psycopg[binary,pool]==3.3.4
sqlalchemy==2.0.50


# Tabular audit exports (CSV/JSON) — PDF and workbook via FileService (.NET)
# JavaScript rendering crawl (headless Chromium via Playwright)
playwright==1.60.0

# LLM providers for AI enrichment (configure via web UI AI tab)
httpx==0.28.1
openai==2.41.0
anthropic==0.107.0
groq==1.4.0

# Spell-check / HTML validation extras
pyspellchecker==0.9.0
html5lib==1.1

# Token counting for agent readiness checks (approximate, cl100k_base encoder)
tiktoken==0.13.0

# MCP server for Cursor / Claude Desktop (stdio + remote Streamable HTTP)
mcp>=1.19,<2
uvicorn>=0.30
starlette>=0.38
fastapi>=0.115

# SQL query validation (read-only chat tool)
sqlglot==30.11.0

# Dev / test
pytest==9.0.3
pytest-cov==7.1.0