mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-28 21:01:55 +08:00
93b3c5d2bf
## [1.64.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.63.1...v1.64.0) (2025-11-06) ### Features * Add configurable timeout to FetchNode ([e81a4ed](e81a4ed745))
123 lines
2.8 KiB
TOML
123 lines
2.8 KiB
TOML
[project]
|
|
name = "scrapegraphai"
|
|
|
|
version = "1.64.0"
|
|
|
|
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 = "Lorenzo Padoan", email = "lorenzo.padoan977@gmail.com" }
|
|
]
|
|
|
|
dependencies = [
|
|
"langchain>=0.3.0",
|
|
"langchain-openai>=0.1.22",
|
|
"langchain-mistralai>=0.1.12",
|
|
"langchain_community>=0.2.9",
|
|
"langchain-aws>=0.1.3",
|
|
"langchain-ollama>=0.1.3",
|
|
"html2text>=2024.2.26",
|
|
"beautifulsoup4>=4.12.3",
|
|
"python-dotenv>=1.0.1",
|
|
"tiktoken>=0.7",
|
|
"tqdm>=4.66.4",
|
|
"minify-html>=0.15.0",
|
|
"free-proxy>=1.1.1",
|
|
"playwright>=1.43.0",
|
|
"undetected-playwright>=0.3.0",
|
|
"semchunk>=2.2.0",
|
|
"async-timeout>=4.0.3",
|
|
"simpleeval>=1.0.0",
|
|
"jsonschema>=4.23.0",
|
|
"duckduckgo-search>=7.2.1",
|
|
"pydantic>=2.10.2",
|
|
"scrapegraph-py>=0.1.0",
|
|
]
|
|
|
|
readme = "README.md"
|
|
homepage = "https://scrapegraphai.com/"
|
|
repository = "https://github.com/ScrapeGraphAI/Scrapegraph-ai"
|
|
documentation = "https://scrapegraph-ai.readthedocs.io/en/latest/"
|
|
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",
|
|
"llm"
|
|
]
|
|
classifiers = [
|
|
"Intended Audience :: Developers",
|
|
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
"Programming Language :: Python :: 3",
|
|
"Operating System :: OS Independent",
|
|
]
|
|
requires-python = ">=3.10,<4.0"
|
|
|
|
[project.optional-dependencies]
|
|
burr = ["burr[start]==0.22.1"]
|
|
docs = ["sphinx==6.0", "furo==2024.5.6"]
|
|
ocr = [
|
|
"surya-ocr>=0.5.0",
|
|
"matplotlib>=3.7.2",
|
|
"ipywidgets>=8.1.0",
|
|
"pillow>=10.4.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling==1.26.3"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.uv]
|
|
dev-dependencies = [
|
|
"pytest>=8.0.0",
|
|
"pytest-mock>=3.14.0",
|
|
"pytest-asyncio>=0.25.0",
|
|
"pytest-sugar>=1.0.0",
|
|
"pytest-cov>=4.1.0",
|
|
"pylint>=3.2.5",
|
|
"poethepoet>=0.32.0",
|
|
"black>=24.2.0",
|
|
"ruff>=0.2.0",
|
|
"isort>=5.13.2",
|
|
"pre-commit>=3.6.0",
|
|
"mypy>=1.8.0",
|
|
"types-setuptools>=75.1.0"
|
|
]
|
|
|
|
[tool.black]
|
|
line-length = 88
|
|
target-version = ["py310"]
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
|
|
[tool.ruff]
|
|
line-length = 88
|
|
|
|
[tool.ruff.lint]
|
|
select = ["F", "E", "W", "C"]
|
|
ignore = ["E203", "E501", "C901"] # Ignore conflicts with Black
|
|
|
|
[tool.mypy]
|
|
python_version = "3.10"
|
|
strict = true
|
|
disallow_untyped_calls = true
|
|
ignore_missing_imports = true
|
|
|
|
[tool.poe.tasks]
|
|
pylint-local = "pylint scraperaphai/**/*.py"
|
|
pylint-ci = "pylint --disable=C0114,C0115,C0116 --exit-zero scrapegraphai/**/*.py"
|