substack-archive-scraper/pyproject.toml at main · xuio/substack-archive-scraper · 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
[build-system]
requires = ["setuptools>=80"]
build-backend = "setuptools.build_meta"

[project]
name = "substack-archive-scraper"
version = "0.1.0"
description = "Substack archive scraper for exporting articles, comments, PDFs, and transcripts to Markdown."
readme = "README.md"
license = "Unlicense"
requires-python = ">=3.12"
keywords = ["substack", "scraper", "archive", "markdown", "downloader", "wiki", "ingestion", "playwright"]
classifiers = [
  "Development Status :: 3 - Alpha",
  "Environment :: Console",
  "Intended Audience :: Developers",
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.12",
  "Programming Language :: Python :: 3.13",
  "Programming Language :: Python :: 3.14",
  "Topic :: Text Processing :: Markup :: Markdown",
]
dependencies = [
  "beautifulsoup4>=4.14",
  "httpx>=0.28",
  "jsonschema>=4.26",
  "playwright>=1.59",
  "PyYAML>=6",
  "pypdf>=6",
]

[project.urls]
Homepage = "https://github.com/xuio/substack-archive-scraper"
Repository = "https://github.com/xuio/substack-archive-scraper"
Issues = "https://github.com/xuio/substack-archive-scraper/issues"

[project.optional-dependencies]
dev = [
  "pytest>=9",
  "ruff>=0.15",
]

[dependency-groups]
dev = [
  "pytest>=9",
  "ruff>=0.15",
]

[project.scripts]
substack-archive-scraper = "substack_ingest.cli:main"
substack-ingest = "substack_ingest.cli:main"

[tool.setuptools.packages.find]
where = ["src"]

[tool.setuptools.package-data]
substack_ingest = ["schemas/*.json"]

[tool.pytest.ini_options]
pythonpath = ["src"]
testpaths = ["tests"]

[tool.ruff]
line-length = 100
target-version = "py312"

[tool.ruff.lint]
select = ["E", "F", "I", "UP", "B"]
ignore = ["E501"]