scrapit/pyproject.toml at main · harryautomazione/scrapit · GitHub

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
133
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "scrapit-scraper"
version = "0.3.0"
description = "YAML-driven web scraper framework with AI agent integrations"
readme = "README.md"
license = { file = "LICENSE" }
requires-python = ">=3.10"
authors = [
  { name = "João Benedet Machado", email = "joaobenedetmachado@gmail.com" },
]
keywords = [
  "web-scraping", "scraper", "yaml", "beautifulsoup", "playwright",
  "langchain", "llm", "ai-agents", "mcp",
]
classifiers = [
  "Development Status :: 3 - Alpha",
  "Intended Audience :: Developers",
  "License :: OSI Approved :: MIT License",
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.10",
  "Programming Language :: Python :: 3.11",
  "Programming Language :: Python :: 3.12",
  "Topic :: Internet :: WWW/HTTP :: Indexing/Search",
  "Topic :: Software Development :: Libraries :: Python Modules",
]

# Core dependencies — always installed
dependencies = [
  "requests>=2.28",
  "beautifulsoup4>=4.12",
  "pyyaml>=6.0",
  "python-dotenv>=1.0",
]

[project.optional-dependencies]
# pip install scrapit[mongo]
mongo = ["pymongo>=4.0"]

# pip install scrapit[rabbitmq]
rabbitmq = ["pika>=1.3"]

# pip install scrapit[playwright]
playwright = ["playwright>=1.40"]

# pip install scrapit[httpx]
httpx = ["httpx>=0.27"]

# pip install scrapit[parquet]
parquet = ["pyarrow>=15.0"]

# pip install scrapit[ui]
ui = ["fastapi>=0.110", "uvicorn>=0.29"]

# pip install scrapit[excel]
excel = ["openpyxl>=3.1"]

# pip install scrapit[sheets]
sheets = [
  "google-api-python-client>=2.0",
  "google-auth>=2.0",
]

# pip install scrapit[langchain]
langchain = ["langchain-core>=0.1"]

# pip install scrapit[llamaindex]
llamaindex = ["llama-index-core>=0.10"]

# pip install scrapit[anthropic]
anthropic = ["anthropic>=0.25"]

# pip install scrapit[openai]
openai = ["openai>=1.0"]

# pip install scrapit[mcp]
mcp = ["mcp>=1.0"]

# pip install scrapit[all]  — everything
all = [
  "pymongo>=4.0",
  "pika>=1.3",
  "playwright>=1.40",
  "httpx>=0.27",
  "openpyxl>=3.1",
  "google-api-python-client>=2.0",
  "google-auth>=2.0",
  "langchain-core>=0.1",
  "llama-index-core>=0.10",
  "anthropic>=0.25",
  "openai>=1.0",
  "mcp>=1.0",
]

# pip install scrapit[dev]
dev = [
  "ruff",
  "pytest",
  "pytest-asyncio",
  "hatch",
  "build",
  "twine",
]

[project.urls]
Homepage = "https://joaobenedetmachado.github.io/scrapit"
Repository = "https://github.com/joaobenedetmachado/scrapit"
Issues = "https://github.com/joaobenedetmachado/scrapit/issues"
Changelog = "https://github.com/joaobenedetmachado/scrapit/releases"

[project.scripts]
scrapit = "scraper.main:main"

[tool.hatch.build.targets.wheel]
packages = ["scraper"]

[tool.hatch.build.targets.sdist]
include = [
  "scraper/",
  "README.md",
  "LICENSE",
  "pyproject.toml",
]

[tool.ruff]
line-length = 120
target-version = "py310"

[tool.ruff.lint]
ignore = ["E501", "F401"]