cryptorugmunch
0200bf3e16
Per CONVENTIONS.md Part 2 ("Never bare except") and CONVENTIONS.md
Part 7 (pre-commit hooks: ruff), blind `except Exception` is now a
lint failure. Pre-existing sites are marked `# noqa: BLE001` for
later manual review; new code must use specific exception types.
Changes:
- pyproject.toml: added "BLE" to ruff lint select. BLE001 is now enforced
- 103 of 166 `except Exception` sites were auto-converted to specific
types based on context (httpx, json, OSError, subprocess, etc.)
- 62 remaining sites marked with `# noqa: BLE001` for later review
(mostly generic try/except wrappers that legitimately need broad catch
for graceful degradation: e.g. compliance LLM fallback must catch
any error to preserve the regex result)
- 1 manual fix: reverted compliance.py LLM fallback to broad except
with explicit "must catch all errors" comment + noqa
- 2 files (commerce_sync.py, crm_sync.py) needed `import httpx` added
so the auto-converted exception references would resolve
- 5 source files (agency, monitor, pipelines, auth_connector,
llm_providers/registry) renamed "name" -> "<scope>_name" in
extra={...} dicts because "name" is a reserved LogRecord field
Test impact:
- 14 failing tests -> 1 (the SSE subprocess test is a sandbox limitation,
pre-existing and unrelated)
- New `test_ble_temp.py` verifies BLE001 catches new violations
Follow-up:
- Each `# noqa: BLE001` site should be reviewed and replaced with a
specific exception type where possible. The most common legitimate
broad-catch case is the LLM fallback path; everything else probably
can be narrowed.
127 lines
3 KiB
TOML
127 lines
3 KiB
TOML
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
[build-system]
|
|
requires = ["setuptools>=69.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "pry"
|
|
version = "3.0.0"
|
|
description = "Free web scraping + browser automation API — self-hosted, no API keys needed"
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
license = { text = "MIT AND BSL-1.1" }
|
|
authors = [{ name = "Rug Munch Media LLC" }]
|
|
keywords = ["scraping", "crawler", "browser-automation", "mcp", "x402", "ai-agents"]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"License :: OSI Approved :: MIT License",
|
|
"License :: Other/Proprietary License",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Internet :: WWW/HTTP :: Browsers",
|
|
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
"Typing :: Typed",
|
|
]
|
|
[project.license-files]
|
|
paths = ["LICENSE", "LICENSE-BSL-STEALTH"]
|
|
dependencies = [
|
|
"fastapi>=0.115.0",
|
|
"uvicorn[standard]>=0.32.0",
|
|
"trafilatura>=2.0.0",
|
|
"readability-lxml>=0.8.1",
|
|
"lxml>=5.3.0",
|
|
"httpx>=0.28.0",
|
|
"markdownify>=0.14.0",
|
|
"pydantic>=2.0.0",
|
|
"pydantic-settings>=2.0.0",
|
|
"playwright>=1.50.0",
|
|
"redis>=5.0.0",
|
|
"pypdf>=5.0.0",
|
|
"python-docx>=1.1.0",
|
|
"tiktoken>=0.8.0",
|
|
"pillow>=10.0.0",
|
|
"click>=8.0.0",
|
|
"pyyaml>=6.0",
|
|
"pandas>=2.0.0",
|
|
"anyio>=4.0.0",
|
|
"croniter>=2.0.0",
|
|
"structlog>=24.0.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8.0",
|
|
"pytest-asyncio>=0.24.0",
|
|
"pytest-cov>=5.0.0",
|
|
"ruff>=0.7.0",
|
|
"mypy>=1.12.0",
|
|
"pre-commit>=4.0.0",
|
|
]
|
|
|
|
[project.scripts]
|
|
pry = "cli:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
include = ["pry*"]
|
|
|
|
[tool.ruff]
|
|
target-version = "py311"
|
|
line-length = 100
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "N", "W", "B", "A", "C4", "SIM", "UP", "RUF", "BLE"]
|
|
ignore = ["E501", "N815", "B008", "A002", "RUF006"]
|
|
|
|
# BLE001 (blind except Exception) is enforced. Pre-existing sites are
|
|
# marked with `# noqa: BLE001`; new code must use specific exception
|
|
# types (e.g. httpx.HTTPError, json.JSONDecodeError, OSError).
|
|
|
|
[tool.ruff.format]
|
|
quote-style = "double"
|
|
indent-style = "space"
|
|
|
|
[tool.mypy]
|
|
python_version = "3.11"
|
|
strict = true
|
|
ignore_missing_imports = true
|
|
exclude = [
|
|
"build/",
|
|
"dist/",
|
|
".git/",
|
|
"__pycache__/",
|
|
]
|
|
warn_unused_ignores = false
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"trafilatura",
|
|
"trafilatura.*",
|
|
"readability",
|
|
"readability.*",
|
|
"playwright",
|
|
"playwright.*",
|
|
"pypdf",
|
|
"pypdf.*",
|
|
"docx",
|
|
"docx.*",
|
|
"PIL",
|
|
"PIL.*",
|
|
"markdownify",
|
|
"markdownify.*",
|
|
"pandas",
|
|
"pandas.*",
|
|
"yaml",
|
|
"yaml.*",
|
|
"numpy",
|
|
"numpy.*",
|
|
]
|
|
ignore_missing_imports = true
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|