-
Notifications
You must be signed in to change notification settings - Fork 8
/
Copy pathpyproject.toml
127 lines (119 loc) · 2.95 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
[project]
name = "par_scrape"
dynamic = [
"version",
]
description = "A versatile web scraping tool with options for Selenium or Playwright, featuring OpenAI-powered data extraction and formatting."
url = "https://github.com/paulrobello/par_scrape"
readme = "README.md"
requires-python = ">=3.10"
authors = [
{ name = "Paul Robello", email = "[email protected]" },
]
maintainers = [
{ name = "Paul Robello", email = "[email protected]" },
]
classifiers = [
"License :: OSI Approved :: MIT License",
"Environment :: Console",
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Intended Audience :: End Users/Desktop",
"Intended Audience :: Other Audience",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Operating System :: MacOS",
"Operating System :: Microsoft :: Windows :: Windows 10",
"Operating System :: Microsoft :: Windows :: Windows 11",
"Operating System :: POSIX :: Linux",
"Topic :: Internet :: WWW/HTTP :: Browsers",
"Topic :: Software Development :: Libraries :: Python Modules",
"Topic :: Text Processing :: Markup :: HTML",
"Typing :: Typed",
]
keywords = [
"web scraping",
"data extraction",
"selenium",
"playwright",
"openai",
"anthropic",
"xai",
"openrouter",
"groq",
"ollama",
"llamacpp",
]
dependencies = [
"beautifulsoup4>=4.13.3",
"pandas>=2.2.3",
"pydantic>=2.10.6",
"python-dotenv>=1.0.1",
"rich>=13.9.4",
"typer>=0.15.1",
"openpyxl>=3.1.5",
"tabulate>=0.9.0",
"par-ai-core>=0.1.20",
"fastapi>=0.115.8",
"tldextract>=5.1.3",
"strenum>=0.4.15",
]
packages = [
"src/par_scrape",
]
[project.license]
file = "LICENSE"
[project.urls]
Homepage = "https://github.com/paulrobello/par_scrape"
Documentation = "https://github.com/paulrobello/par_scrape/blob/main/README.md"
Repository = "https://github.com/paulrobello/par_scrape"
Issues = "https://github.com/paulrobello/par_scrape/issues"
Discussions = "https://github.com/paulrobello/par_scrape/discussions"
Wiki = "https://github.com/paulrobello/par_scrape/wiki"
[project.scripts]
par_scrape = "par_scrape.__main__:app"
[build-system]
requires = [
"hatchling",
"wheel",
]
build-backend = "hatchling.build"
[dependency-groups]
dev = [
"build>=1.2.1",
"twine>=6.1.0",
"pyright>=1.1.379",
"ruff>=0.9.6",
"pre-commit>=4.1.0",
]
[tool.hatch.version]
path = "src/par_scrape/__init__.py"
[tool.hatch.build.targets.wheel]
packages = [
"src/par_scrape",
]
include = [
"py.typed",
"**/*.py",
"**/*.html",
"**/*.gif",
"**/*.jpg",
"**/*.png",
"**/*.md",
]
[tool.hatch.build.targets.sdist]
include = [
"src/par_scrape",
"LICENSE",
"README.md",
"extraction_prompt.md",
"pyproject.toml",
]
exclude = [
"*.pyc",
"__pycache__",
"*.so",
"*.dylib",
]