-
-
Notifications
You must be signed in to change notification settings - Fork 1.3k
/
pyproject.toml
132 lines (116 loc) · 3.16 KB
/
pyproject.toml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
[project]
name = "scrapegraphai"
version = "1.30.0"
description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
authors = [
{ name = "Marco Vinciguerra", email = "[email protected]" },
{ name = "Marco Perini", email = "[email protected]" },
{ name = "Lorenzo Padoan", email = "[email protected]" }
]
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'"