Scrapegraph-ai/pyproject.toml
semantic-release-bot 3933d64601 ci(release): 1.27.0 [skip ci]
## [1.27.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.26.7...v1.27.0) (2024-10-26)

### Features

* add conditional node structure to the smart_scraper_graph and implemented a structured way to check condition ([cacd9cd](cacd9cde00))
* add integration with scrape.do ([ae275ec](ae275ec5e8))
* add model integration gpt4 ([51c55eb](51c55eb3a2))
* implement ScrapeGraph class for only web scraping automation ([612c644](612c644623))
* Implement SmartScraperMultiParseMergeFirstGraph class that scrapes a list of URLs and merge the content first and finally generates answers to a given prompt. ([3e3e1b2](3e3e1b2f3a))
* refactoring of export functions ([0ea00c0](0ea00c078f))
* refactoring of get_probable_tags node ([f658092](f658092dff))
* refactoring of ScrapeGraph to SmartScraperLiteGraph ([52b6bf5](52b6bf5fb8))

### Bug Fixes

* fix export function ([c8a000f](c8a000f1d9))
* fix the example variable name ([69ff649](69ff649556))
* remove variable "max_result" not being used in the code ([e76a68a](e76a68a782))

### chore

* fix example ([9cd9a87](9cd9a874f9))

### Test

* Add scrape_graph test ([cdb3c11](cdb3c1100e))
* Add smart_scraper_multi_parse_merge_first_graph test ([464b8b0](464b8b04ea))

### CI

* **release:** 1.26.6-beta.1 [skip ci] ([e0fc457](e0fc457d1a))
* **release:** 1.27.0-beta.1 [skip ci] ([9266a36](9266a36b2e))
* **release:** 1.27.0-beta.10 [skip ci] ([eee131e](eee131e959))
* **release:** 1.27.0-beta.2 [skip ci] ([d84d295](d84d295389))
* **release:** 1.27.0-beta.3 [skip ci] ([f576afa](f576afaf0c))
* **release:** 1.27.0-beta.4 [skip ci] ([3d6bbcd](3d6bbcdaa3))
* **release:** 1.27.0-beta.5 [skip ci] ([5002c71](5002c713d5))
* **release:** 1.27.0-beta.6 [skip ci] ([94b9836](94b9836ef6))
* **release:** 1.27.0-beta.7 [skip ci] ([407f1ce](407f1ce4eb))
* **release:** 1.27.0-beta.8 [skip ci] ([4f1ed93](4f1ed939e6))
* **release:** 1.27.0-beta.9 [skip ci] ([fd57cc7](fd57cc7c12))
2024-10-26 08:06:36 +00:00

131 lines
3.2 KiB
TOML

[project]
name = "scrapegraphai"
version = "1.27.0"
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",
"transformers>=4.44.2",
"googlesearch-python>=1.2.5",
"async-timeout>=4.0.3",
"transformers>=4.44.2",
"googlesearch-python>=1.2.5",
"simpleeval>=1.0.0",
"async_timeout>=4.0.3"
]
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'"