swarmauri_tool_webscraping 0.6.0.dev154__tar.gz

swarmauri_tool_webscraping-0.6.0.dev154/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.3
+Name: swarmauri_tool_webscraping
+Version: 0.6.0.dev154
+Summary: Web Scraping Tool for Swarmauri
+License: Apache-2.0
+Author: Jacob Stewart
+Author-email: jacob@swarmauri.com
+Requires-Python: >=3.10,<3.13
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: beautifulsoup4 (>=4.10.0,<5.0.0)
+Requires-Dist: swarmauri_base (>=0.6.0.dev154,<0.7.0)
+Requires-Dist: swarmauri_core (>=0.6.0.dev154,<0.7.0)
+Project-URL: Repository, http://github.com/swarmauri/swarmauri-sdk
+Description-Content-Type: text/markdown
+
+# Swarmauri Example Community Package

swarmauri_tool_webscraping-0.6.0.dev154/README.md

@@ -0,0 +1 @@
+# Swarmauri Example Community Package

swarmauri_tool_webscraping-0.6.0.dev154/pyproject.toml

@@ -0,0 +1,58 @@
+[tool.poetry]
+name = "swarmauri_tool_webscraping"
+version = "0.6.0.dev154"
+description = "Web Scraping Tool for Swarmauri"
+authors = ["Jacob Stewart <jacob@swarmauri.com>"]
+license = "Apache-2.0"
+readme = "README.md"
+repository = "http://github.com/swarmauri/swarmauri-sdk"
+classifiers = [
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
+]
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.13"
+
+# Swarmauri
+swarmauri_core = {version = "^0.6.0.dev154"}
+swarmauri_base = {version = "^0.6.0.dev154"}
+
+# Dependencies
+beautifulsoup4 = "^4.10.0"
+
+
+
+[tool.poetry.group.dev.dependencies]
+flake8 = "^7.0"
+pytest = "^8.0"
+pytest-asyncio = ">=0.24.0"
+pytest-xdist = "^3.6.1"
+pytest-json-report = "^1.5.0"
+python-dotenv = "*"
+requests = "^2.32.3"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+norecursedirs = ["combined", "scripts"]
+
+markers = [
+    "test: standard test",
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "acceptance: Acceptance tests",
+    "experimental: Experimental tests"
+]
+log_cli = true
+log_cli_level = "INFO"
+log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
+log_cli_date_format = "%Y-%m-%d %H:%M:%S"
+asyncio_default_fixture_loop_scope = "function"
+
+[tool.poetry.plugins."swarmauri.tools"]
+WebScrapingTool = "swarmauri_tool_webscraping.WebScrapingTool:WebScrapingTool"

swarmauri_tool_webscraping-0.6.0.dev154/swarmauri_tool_webscraping/WebScrapingTool.py

@@ -0,0 +1,60 @@
+import requests
+from bs4 import BeautifulSoup
+from swarmauri_core.ComponentBase import ComponentBase
+from swarmauri_base.tools.ToolBase import ToolBase
+from swarmauri_standard.tools.Parameter import Parameter
+from typing import List, Literal, Dict
+from pydantic import Field
+
+
+@ComponentBase.register_type(ToolBase, "WebScrapingTool")
+class WebScrapingTool(ToolBase):
+    version: str = "1.0.0"
+    parameters: List[Parameter] = Field(
+        default_factory=lambda: [
+            Parameter(
+                name="url",
+                type="string",
+                description="URL of the link, website, webpage, etc... to scrape",
+                required=True,
+            ),
+            Parameter(
+                name="selector",
+                type="string",
+                description="CSS selector to target specific elements",
+                required=True,
+            ),
+        ]
+    )
+
+    name: str = "WebScrapingTool"
+    description: str = (
+        "This is a web scraping tool that uses python's requests and BeautifulSoup libraries to parse a URL using a CSS selector to target specific elements."
+    )
+    type: Literal["WebScrapingTool"] = "WebScrapingTool"
+
+    def __call__(self, url: str, selector: str) -> Dict[str, str]:
+        """
+        Fetches content from the specified URL and extracts elements based on the provided CSS selector.
+
+        Args:
+            url (str): The URL of the webpage to scrape.
+            selector (str): CSS selector to target specific elements in the webpage.
+
+        Returns:
+            Dict: A dictionary containing the extracted text or an error message.
+        """
+        try:
+            response = requests.get(url)
+            response.raise_for_status()  # Raises HTTPError for bad requests (4xx or 5xx)
+
+            html_content = response.content
+            soup = BeautifulSoup(html_content, "html.parser")
+
+            elements = soup.select(selector)
+            extracted_text = "\n".join([element.text for element in elements])
+            return {"extracted_text": extracted_text}
+        except requests.RequestException as e:
+            return {"error": f"Request error: {str(e)}"}
+        except Exception as e:
+            return {"error": f"An error occurred: {str(e)}"}

swarmauri_tool_webscraping-0.6.0.dev154/swarmauri_tool_webscraping/__init__.py

@@ -0,0 +1,12 @@
+from .WebScrapingTool import WebScrapingTool
+
+__version__ = "0.6.0.dev26"
+__long_desc__ = """
+
+# Swarmauri WebScraping Tool Plugin
+
+Visit us at: https://swarmauri.com
+Follow us at: https://github.com/swarmauri
+Star us at: https://github.com/swarmauri/swarmauri-sdk
+
+"""