spiderforce4ai 2.3.1__tar.gz → 2.4__tar.gz

{spiderforce4ai-2.3.1 → spiderforce4ai-2.4}/PKG-INFO

@@ -1,16 +1,24 @@
 Metadata-Version: 2.2
 Name: spiderforce4ai
-Version: 2.3.1
-Summary: Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service
+Version: 2.4
+Summary: Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing
 Home-page: https://petertam.pro
 Author: Piotr Tamulewicz
 Author-email: Piotr Tamulewicz <pt@petertam.pro>
-License: MIT
+Project-URL: Homepage, https://petertam.pro
+Project-URL: Documentation, https://petertam.pro/docs/spiderforce4ai
+Project-URL: Repository, https://github.com/yourusername/spiderforce4ai
+Project-URL: Bug Tracker, https://github.com/yourusername/spiderforce4ai/issues
+Keywords: web-scraping,markdown,html-to-markdown,llm,ai,content-extraction,async,parallel-processing
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 Requires-Dist: aiohttp>=3.8.0
@@ -18,6 +26,36 @@ Requires-Dist: asyncio>=3.4.3
 Requires-Dist: rich>=10.0.0
 Requires-Dist: aiofiles>=0.8.0
 Requires-Dist: httpx>=0.24.0
+Requires-Dist: litellm>=1.26.0
+Requires-Dist: pydantic>=2.6.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: aiofiles>=23.2.1
+Requires-Dist: et-xmlfile>=1.1.0
+Requires-Dist: multidict>=6.0.4
+Requires-Dist: openai>=1.12.0
+Requires-Dist: pandas>=2.2.0
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: yarl>=1.9.4
+Requires-Dist: typing_extensions>=4.9.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.1; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: black>=23.7.0; extra == "dev"
+Requires-Dist: isort>=5.12.0; extra == "dev"
+Requires-Dist: mypy>=1.4.1; extra == "dev"
+Requires-Dist: ruff>=0.1.8; extra == "dev"
+Requires-Dist: pre-commit>=3.5.0; extra == "dev"
+Provides-Extra: test
+Requires-Dist: pytest>=7.4.0; extra == "test"
+Requires-Dist: pytest-asyncio>=0.21.1; extra == "test"
+Requires-Dist: pytest-cov>=4.1.0; extra == "test"
+Requires-Dist: pytest-mock>=3.12.0; extra == "test"
+Requires-Dist: coverage>=7.4.0; extra == "test"
+Provides-Extra: docs
+Requires-Dist: sphinx>=7.1.0; extra == "docs"
+Requires-Dist: sphinx-rtd-theme>=1.3.0; extra == "docs"
+Requires-Dist: myst-parser>=2.0.0; extra == "docs"
 Dynamic: author
 Dynamic: home-page
 Dynamic: requires-python

spiderforce4ai-2.4/pyproject.toml

@@ -0,0 +1,166 @@
+[build-system]
+requires = ["setuptools>=65.0.0", "wheel>=0.40.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "spiderforce4ai"
+version = "2.4"
+description = "Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing"
+readme = "README.md"
+authors = [
+    { name = "Piotr Tamulewicz", email = "pt@petertam.pro" }
+]
+license = { file = "LICENSE" }
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
+    "Topic :: Text Processing :: Markup :: Markdown",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+keywords = [
+    "web-scraping",
+    "markdown",
+    "html-to-markdown",
+    "llm",
+    "ai",
+    "content-extraction",
+    "async",
+    "parallel-processing"
+]
+requires-python = ">=3.11"
+dependencies = [
+    "aiohttp>=3.8.0",
+    "asyncio>=3.4.3",
+    "rich>=10.0.0",
+    "aiofiles>=0.8.0",
+    "httpx>=0.24.0",
+    "litellm>=1.26.0",
+    "pydantic>=2.6.0",
+    "requests>=2.31.0",
+    "aiofiles>=23.2.1",
+    "et-xmlfile>=1.1.0",
+    "multidict>=6.0.4",
+    "openai>=1.12.0",
+    "pandas>=2.2.0",
+    "numpy>=1.26.0",
+    "yarl>=1.9.4",
+    "typing_extensions>=4.9.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.4.0",
+    "pytest-asyncio>=0.21.1",
+    "pytest-cov>=4.1.0",
+    "black>=23.7.0",
+    "isort>=5.12.0",
+    "mypy>=1.4.1",
+    "ruff>=0.1.8",
+    "pre-commit>=3.5.0",
+]
+
+test = [
+    "pytest>=7.4.0",
+    "pytest-asyncio>=0.21.1",
+    "pytest-cov>=4.1.0",
+    "pytest-mock>=3.12.0",
+    "coverage>=7.4.0",
+]
+
+docs = [
+    "sphinx>=7.1.0",
+    "sphinx-rtd-theme>=1.3.0",
+    "myst-parser>=2.0.0",
+]
+
+[project.urls]
+Homepage = "https://petertam.pro"
+Documentation = "https://petertam.pro/docs/spiderforce4ai"
+Repository = "https://github.com/yourusername/spiderforce4ai"
+"Bug Tracker" = "https://github.com/yourusername/spiderforce4ai/issues"
+
+[project.scripts]
+spiderforce4ai = "spiderforce4ai.cli:main"
+
+[tool.setuptools]
+packages = ["spiderforce4ai"]
+
+[tool.setuptools.package-data]
+spiderforce4ai = ["py.typed"]
+
+[tool.black]
+line-length = 100
+target-version = ["py311"]
+include = '\.pyi?$'
+
+[tool.isort]
+profile = "black"
+line_length = 100
+multi_line_output = 3
+include_trailing_comma = true
+force_grid_wrap = 0
+use_parentheses = true
+ensure_newline_before_comments = true
+
+[tool.mypy]
+python_version = "3.11"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+check_untyped_defs = true
+disallow_untyped_decorators = true
+no_implicit_optional = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_no_return = true
+warn_unreachable = true
+show_error_codes = true
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+addopts = "-ra -q --cov=spiderforce4ai --cov-report=term-missing"
+testpaths = ["tests"]
+asyncio_mode = "auto"
+
+[tool.coverage.run]
+source = ["spiderforce4ai"]
+branch = true
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "pass",
+    "raise ImportError",
+]
+ignore_errors = true
+omit = [
+    "tests/*",
+    "setup.py",
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+select = [
+    "E",    # pycodestyle errors
+    "W",    # pycodestyle warnings
+    "F",    # pyflakes
+    "I",    # isort
+    "C",    # flake8-comprehensions
+    "B",    # flake8-bugbear
+]
+ignore = [
+    "E501",  # line too long
+]
+[tool.ruff.per-file-ignores]
+"__init__.py" = ["F401"]

spiderforce4ai-2.4/setup.py

@@ -0,0 +1,82 @@
+# setup.py
+from setuptools import setup, find_packages
+
+# Read the README.md file
+with open("README.md", encoding="utf-8") as f:
+    long_description = f.read()
+
+setup(
+    name="spiderforce4ai",
+    version="2.4",
+    author="Piotr Tamulewicz",
+    author_email="pt@petertam.pro",
+    description="Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://petertam.pro",
+    packages=find_packages(),
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
+        "Topic :: Text Processing :: Markup :: Markdown",
+        "Topic :: Software Development :: Libraries :: Python Modules",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    ],
+    python_requires=">=3.11",
+    install_requires=[
+        "aiohttp>=3.8.0",
+        "asyncio>=3.4.3",
+        "rich>=10.0.0",
+        "aiofiles>=0.8.0",
+        "httpx>=0.24.0",
+        "litellm>=1.26.0",
+        "pydantic>=2.6.0",
+        "requests>=2.31.0",
+        "aiofiles>=23.2.1",
+        "et-xmlfile>=1.1.0",
+        "multidict>=6.0.4",
+        "openai>=1.12.0",
+        "pandas>=2.2.0",
+        "numpy>=1.26.0",
+        "yarl>=1.9.4",
+        "typing_extensions>=4.9.0"
+    ],
+    extras_require={
+        'dev': [
+            'pytest>=7.4.0',
+            'pytest-asyncio>=0.21.1',
+            'pytest-cov>=4.1.0',
+            'black>=23.7.0',
+            'isort>=5.12.0',
+            'mypy>=1.4.1',
+        ],
+    },
+    project_urls={
+        "Bug Tracker": "https://github.com/yourusername/spiderforce4ai/issues",
+        "Documentation": "https://petertam.pro/docs/spiderforce4ai",
+        "Source Code": "https://github.com/yourusername/spiderforce4ai",
+    },
+    keywords=[
+        "web-scraping",
+        "markdown",
+        "html-to-markdown",
+        "llm",
+        "ai",
+        "content-extraction",
+        "async",
+        "parallel-processing"
+    ],
+    entry_points={
+        'console_scripts': [
+            'spiderforce4ai=spiderforce4ai.cli:main',
+        ],
+    },
+    package_data={
+        'spiderforce4ai': ['py.typed'],
+    },
+    zip_safe=False,
+)