Add webscraper MCP server (7 tools, httpx+bs4, 15+ tests)

2026-04-03 13:40:50 +02:00
parent 6623fe0337
commit 38a2b89bd3
9 changed files with 2266 additions and 0 deletions
@@ -0,0 +1,43 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "webscraper"
+dynamic = ["version"]
+description = "MCP server for web scraping: fetch pages, extract links/tables, sitemap parsing"
+readme = "README.md"
+requires-python = ">=3.11"
+license = "MIT"
+authors = [{name = "Patrick Plate", email = "patrickplate@gmx.de"}]
+dependencies = [
+  "fastmcp>=0.1.0",
+  "httpx>=0.28.0",
+  "beautifulsoup4>=4.14.0",
+  "lxml>=6.0.0",
+  "html2text>=2025.4.15",
+]
+
+[project.optional-dependencies]
+test = [
+  "pytest>=7.0",
+  "pytest-mock>=3.0",
+  "pytest-cov>=4.0",
+]
+
+[tool.hatch.version]
+path = "src/__init__.py"
+
+[tool.hatch.build.targets.sdist]
+include = ["/src", "/tests"]
+
+[tool.hatch.build.targets.wheel]
+include = ["/src", "/tests"]
+packages = ["src/webscraper"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = "test_*.py"
+python_classes = "Test*"
+python_functions = "test_*"
+addopts = "--cov=src --cov-report=term-missing --cov-report=xml"