pyproject.toml

[project]
name = "scrapegraphai"

version = "1.4.0"

description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
authors = [
    { name = "Marco Vinciguerra", email = "mvincig11@gmail.com" },
    { name = "Marco Perini", email = "perinim.98@gmail.com" },
    { name = "Lorenzo Padoan", email = "lorenzo.padoan977@gmail.com" }
]
dependencies = [
    # python = ">=3.9, <3.12"
    "langchain==0.1.15",
    "langchain-openai==0.1.6",
    "langchain-google-genai==1.0.3",
    "langchain-groq==0.1.3",
    "langchain-aws==0.1.3",
    "langchain-anthropic==0.1.11",
    "html2text==2024.2.26",
    "faiss-cpu==1.8.0",
    "beautifulsoup4==4.12.3",
    "pandas==2.2.2",
    "python-dotenv==1.0.1",
    "tiktoken==0.6.0",
    "tqdm==4.66.4",
    "graphviz==0.20.3",
    "minify-html==0.15.0",
    "free-proxy==1.1.1",
    "playwright==1.43.0",
    "google==3.0.0",
    "yahoo-search-py==0.3",
]

license = "MIT"
readme = "README.md"
homepage = "https://scrapegraph-ai.readthedocs.io/"
repository = "https://github.com/VinciGit00/Scrapegraph-ai"
documentation = "https://scrapegraph-doc.onrender.com/"
keywords = [
    "scrapegraph",
    "scrapegraphai",
    "langchain",
    "ai",
    "artificial intelligence",
    "gpt",
    "machine learning",
    "rag",
    "nlp",
    "natural language processing",
    "openai",
    "scraping",
    "web scraping",
    "web scraping library",
    "web scraping tool",
    "webscraping",
    "graph",
]
classifiers = [
    "Intended Audience :: Developers",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Programming Language :: Python :: 3",
    "Operating System :: OS Independent",
]
requires-python = ">= 3.9"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.rye]
managed = true
dev-dependencies = [
    "pytest==8.0.0",
    "pytest-mock==3.14.0"
]

[tool.rye.group.docs]
optional = true

[tool.rye.group.docs.dependencies]
sphinx = "7.1.2"
sphinx-rtd-theme = "2.0.0"