mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-09 21:19:20 +08:00
70a883fa32
## [1.26.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.25.2...v1.26.0) (2024-10-13) ### Features * add deep scraper implementation ([4b371f4](4b371f4d94)) * add google proxy support ([a986523](a986523884)) * add html_mode to smart_scraper ([bdcffd6](bdcffd6360)) * add reasoning integration ([b2822f6](b2822f620a)) * async invocation ([257f393](257f393761)) * conditional_node ([f837dc1](f837dc16ce)) * finished basic version of deep scraper ([85cb957](85cb957297)) * prompt refactoring ([5a2f6d9](5a2f6d9a77)) * refactoring fetch_node ([39a029e](39a029ed9a)) * refactoring of mdscraper ([3b7b701](3b7b701a89)) * refactoring of research web ([26f89d8](26f89d895d)) * refactoring of the conditional node ([420c71b](420c71ba2c)) * undected_chromedriver support ([80ece21](80ece2179a)) * update chromium loader ([4f816f3](4f816f3b04)) ### Bug Fixes * bugs ([026a70b](026a70bd3a)) * import error ([37b6ba0](37b6ba08ae)) * integration with html_mode ([f87ffa1](f87ffa1d8d)) * nodes prompt ([8753537](8753537ecd)) * pyproject.toml ([3b27c5e](3b27c5e88c)) * refactoring prompts ([c655642](c655642577)) * removed pdf_scraper graph and created document scraper ([a57da96](a57da96175)) * search_on_web paremter ([7f03ec1](7f03ec15de)) * typo ([e285127](e28512720c)) ### Perf * Proxy integration in googlesearch ([e828c70](e828c7010a)) ### CI * **release:** 1.22.0-beta.4 [skip ci] ([4330179](4330179cb6)) * **release:** 1.22.0-beta.5 [skip ci] ([6d8f543](6d8f5435d1)) * **release:** 1.22.0-beta.6 [skip ci] ([39f7815](39f78154a6)) * **release:** 1.26.0-beta.1 [skip ci] ([ac31d7f](ac31d7f710)) * **release:** 1.26.0-beta.10 [skip ci] ([0c7ebe2](0c7ebe28ac)) * **release:** 1.26.0-beta.11 [skip ci] ([6d8828a](6d8828aa62)) * **release:** 1.26.0-beta.12 [skip ci] ([44d10aa](44d10aa1c0)) * **release:** 1.26.0-beta.13 [skip ci] ([12f2b99](12f2b9946b)) * **release:** 1.26.0-beta.14 [skip ci] ([eb25725](eb257259f8)) * **release:** 1.26.0-beta.15 [skip ci] ([528a974](528a9746fe)) * **release:** 1.26.0-beta.16 [skip ci] ([04bd2a8](04bd2a87fb)) * **release:** 1.26.0-beta.17 [skip ci] ([f17089c](f17089c123)) * **release:** 1.26.0-beta.2 [skip ci] ([5cedeb8](5cedeb8486)) * **release:** 1.26.0-beta.3 [skip ci] ([4f65be4](4f65be44b5)) * **release:** 1.26.0-beta.4 [skip ci] ([84d7937](84d7937472)) * **release:** 1.26.0-beta.5 [skip ci] ([ea9ed1a](ea9ed1a981)) * **release:** 1.26.0-beta.6 [skip ci] ([4cd21f5](4cd21f500d)) * **release:** 1.26.0-beta.7 [skip ci] ([482f060](482f060c9a)) * **release:** 1.26.0-beta.8 [skip ci] ([38b795e](38b795e48a)) * **release:** 1.26.0-beta.9 [skip ci] ([4dc0699](4dc0699483))
123 lines
3.0 KiB
TOML
123 lines
3.0 KiB
TOML
[project]
|
|
name = "scrapegraphai"
|
|
|
|
version = "1.26.0"
|
|
|
|
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 = [
|
|
"langchain>=0.3.0",
|
|
"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",
|
|
"mistral-common>=1.4.0",
|
|
"html2text>=2024.2.26",
|
|
"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",
|
|
"langchain-ollama>=0.1.3",
|
|
"qdrant-client>=1.11.3",
|
|
"fastembed>=0.3.6",
|
|
"semchunk>=2.2.0",
|
|
"transformers>=4.44.2",
|
|
"googlesearch-python>=1.2.5"
|
|
]
|
|
|
|
license = "MIT"
|
|
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"]
|
|
|
|
# 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",
|
|
"matplotlib>=3.7.2",
|
|
"ipywidgets>=8.1.0",
|
|
"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'"
|