mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-28 21:01:55 +08:00
eddcb79486
## [1.19.0-beta.1](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.18.1...v1.19.0-beta.1) (2024-09-08) ### Features * **AbstractGraph:** add adjustable rate limit ([2859fb7](2859fb72d6)) * add scrape_do_integration ([94e69a0](94e69a0515)) * add togheterai ([8f615ad](8f615adef3)) * ConcatNode.py added for heavy merge operations ([bd4b26d](bd4b26d7d7)) * fetch_node improved ([167f970](167f97040f)) ### Bug Fixes * **AbstractGraph:** Bedrock init issues ([63a5d18](63a5d18486)), closes [#633](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/633) * correctly parsing output when using structured_output ([8e74ac5](8e74ac55a1)) * **ScreenshotScraper:** impose dynamic imports ([b8ef937](b8ef93738e)) * **Ollama:** instance model from correct package ([398b2c5](398b2c556f)) * Parse Node scraping link and img urls allowing OmniScraper to work ([66a3b6d](66a3b6d6a3)) * **SmartScraper:** pass llm_model to ParseNode ([5242166](5242166575)) * **DeepSeek:** proper model initialization ([74dfc69](74dfc693f6)) * Removed link_urls and img_ulrs from FetchNode output ([57337a0](57337a0a8c)) * screenshot scraper ([388630c](388630c0ff)) * screenshot_scraper ([ef7a589](ef7a5891dc)) * **ScreenShotScraper:** static import of optional dependencies ([52fe441](52fe441c5a)) * update generate answernode ([c348f67](c348f674ad)) ### chore * **examples:** create Together AI examples ([34942de](34942deca5)) ### CI * **release:** 1.16.0-beta.1 [skip ci] ([d7f6036](d7f6036f90)) * **release:** 1.16.0-beta.2 [skip ci] ([1c37d5d](1c37d5db1c)) * **release:** 1.16.0-beta.3 [skip ci] ([886c987](886c987172)) * **release:** 1.16.0-beta.4 [skip ci] ([ba5c7ad](ba5c7adcea)) * **release:** 1.17.0-beta.1 [skip ci] ([13efd4e](13efd4e3a4)) * **release:** 1.17.0-beta.10 [skip ci] ([af28885](af2888539e)) * **release:** 1.17.0-beta.11 [skip ci] ([a73fec5](a73fec5a98)) * **release:** 1.17.0-beta.2 [skip ci] ([08afc92](08afc9292e)) * **release:** 1.17.0-beta.3 [skip ci] ([fc55418](fc55418a45)) * **release:** 1.17.0-beta.4 [skip ci] ([5e99071](5e990719cf)) * **release:** 1.17.0-beta.5 [skip ci] ([16ab1bf](16ab1bf3d9)) * **release:** 1.17.0-beta.6 [skip ci] ([50c9c6b](50c9c6bd8c)) * **release:** 1.17.0-beta.7 [skip ci] ([4347afb](4347afb8d4)), closes [#633](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/633) * **release:** 1.17.0-beta.8 [skip ci] ([85c374e](85c374e4b3)) * **release:** 1.17.0-beta.9 [skip ci] ([77d0fd3](77d0fd3dba))
119 lines
3.0 KiB
TOML
119 lines
3.0 KiB
TOML
[project]
|
|
name = "scrapegraphai"
|
|
|
|
version = "1.19.0b1"
|
|
|
|
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>=0.2.14",
|
|
"langchain-google-genai>=1.0.7",
|
|
"langchain-openai>=0.1.22",
|
|
"langchain-mistralai>=0.1.12",
|
|
"langchain_community>=0.2.9",
|
|
"langchain-aws>=0.1.3",
|
|
"html2text>=2024.2.26",
|
|
"faiss-cpu>=1.8.0",
|
|
"beautifulsoup4>=4.12.3",
|
|
"pandas>=2.2.2",
|
|
"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",
|
|
"google>=3.0.0",
|
|
"semchunk>=1.0.1",
|
|
"langchain-ollama>=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"]
|
|
|
|
# Group 1: Other Language Models
|
|
other-language-models = [
|
|
"langchain-google-vertexai>=1.0.7",
|
|
"langchain-fireworks>=0.1.3",
|
|
"langchain-groq>=0.1.3",
|
|
"langchain-anthropic>=0.1.11",
|
|
"langchain-huggingface>=0.0.3",
|
|
"langchain-nvidia-ai-endpoints>=0.1.6",
|
|
"langchain_together>=1.2.9"
|
|
]
|
|
|
|
# Group 2: More Semantic Options
|
|
more-semantic-options = [
|
|
"graphviz>=0.20.3",
|
|
]
|
|
|
|
# Group 3: More Browser Options
|
|
more-browser-options = [
|
|
"browserbase>=0.3.0",
|
|
]
|
|
|
|
# Group 4: Surya Library
|
|
screenshot_scraper = [
|
|
"surya-ocr>=0.5.0; python_version >= '3.10'",
|
|
"matplotlib>=3.7.2; python_version >= '3.10'",
|
|
"ipywidgets>=8.1.0; python_version >= '3.10'",
|
|
"pillow>=10.4.0",
|
|
]
|
|
|
|
[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"
|
|
update-requirements = "python 'manual deployment/autorequirements.py'"
|