mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-23 21:00:30 +08:00
96 lines
2.4 KiB
TOML
96 lines
2.4 KiB
TOML
[project]
|
|
name = "scrapegraphai"
|
|
|
|
|
|
version = "1.8.1b1"
|
|
|
|
|
|
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 = [
|
|
"langchain==0.1.15",
|
|
"langchain-openai==0.1.6",
|
|
"langchain-google-genai==1.0.3",
|
|
"langchain-google-vertexai==1.0.6",
|
|
"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",
|
|
"undetected-playwright==0.3.0",
|
|
"semchunk==1.0.1",
|
|
"html2text==2024.2.26",
|
|
"trafilatura==1.10.0",
|
|
"langchain-fireworks==0.1.3"
|
|
]
|
|
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
homepage = "https://scrapegraphai.com/"
|
|
repository = "https://github.com/VinciGit00/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",
|
|
]
|
|
classifiers = [
|
|
"Intended Audience :: Developers",
|
|
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
"Programming Language :: Python :: 3",
|
|
"Operating System :: OS Independent",
|
|
]
|
|
requires-python = ">=3.9,<4.0"
|
|
|
|
[project.optional-dependencies]
|
|
burr = ["burr[start]==0.22.1"]
|
|
docs = ["sphinx==6.0", "furo==2024.5.6"]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.rye]
|
|
managed = true
|
|
dev-dependencies = [
|
|
"pytest==8.0.0",
|
|
"pytest-mock==3.14.0",
|
|
"-e file:.[burr]",
|
|
"-e file:.[docs]",
|
|
"pylint>=3.2.5",
|
|
]
|
|
|
|
[tool.rye.scripts]
|
|
pylint-local = "pylint scrapegraphai/**/*.py"
|
|
pylint-ci = "pylint --disable=C0114,C0115,C0116 --exit-zero scrapegraphai/**/*.py"
|
|
pylint-score-ci = "pylint --disable=all --enable=metrics --output-format=text scrapegraphai/**/.py"
|
|
|