content-core 1.1.0__py3-none-any.whl → 1.1.2__py3-none-any.whl

content_core/mcp/server.py

@@ -30,6 +30,7 @@ def suppress_stdout():
     finally:
         sys.stdout = original_stdout
 
+
 # Add parent directory to path to import content_core
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
 
@@ -38,38 +39,40 @@ import content_core as cc
 # Initialize MCP server
 mcp = FastMCP("Content Core MCP Server")
 
+
 async def _extract_content_impl(
-    url: Optional[str] = None,
-    file_path: Optional[str] = None
+    url: Optional[str] = None, file_path: Optional[str] = None
 ) -> Dict[str, Any]:
     """
-    Extract content from a URL or file using Content Core's auto engine.
-    
+    Extract content from a URL or file using Content Core's auto engine. This is useful for processing Youtube transcripts, website content, PDFs, ePUB, Office files, etc. You can also use it to extract transcripts from audio or video files.
+
     Args:
         url: Optional URL to extract content from
         file_path: Optional file path to extract content from
-        
+
     Returns:
         JSON object containing extracted content and metadata
-        
+
     Raises:
         ValueError: If neither or both url and file_path are provided
     """
     # Validate input - exactly one must be provided
-    if (url is None and file_path is None) or (url is not None and file_path is not None):
+    if (url is None and file_path is None) or (
+        url is not None and file_path is not None
+    ):
         return {
             "success": False,
             "error": "Exactly one of 'url' or 'file_path' must be provided",
             "source_type": None,
             "source": None,
             "content": None,
-            "metadata": None
+            "metadata": None,
         }
-    
+
     # Determine source type and validate
     source_type = "url" if url else "file"
     source = url if url else file_path
-    
+
     # Additional validation for file paths
     if file_path:
         path = Path(file_path)
@@ -80,9 +83,9 @@ async def _extract_content_impl(
                 "source_type": source_type,
                 "source": source,
                 "content": None,
-                "metadata": None
+                "metadata": None,
             }
-        
+
         # Security check - ensure no directory traversal
         try:
             # Resolve to absolute path and ensure it's not trying to access sensitive areas
@@ -95,30 +98,30 @@ async def _extract_content_impl(
                 "source_type": source_type,
                 "source": source,
                 "content": None,
-                "metadata": None
+                "metadata": None,
             }
-    
+
     # Build extraction request
     extraction_request = {}
     if url:
         extraction_request["url"] = url
     else:
         extraction_request["file_path"] = str(Path(file_path).resolve())
-    
+
     # Track start time
     start_time = datetime.utcnow()
-    
+
     try:
         # Use Content Core's extract_content with auto engine
         logger.info(f"Extracting content from {source_type}: {source}")
-        
+
         # Suppress stdout to prevent MoviePy and other libraries from interfering with MCP protocol
         with suppress_stdout():
             result = await cc.extract_content(extraction_request)
-        
+
         # Calculate extraction time
         extraction_time = (datetime.utcnow() - start_time).total_seconds()
-        
+
         # Build response - result is a ProcessSourceOutput object
         response = {
             "success": True,
@@ -132,13 +135,13 @@ async def _extract_content_impl(
                 "content_length": len(result.content or ""),
                 "identified_type": result.identified_type or "unknown",
                 "identified_provider": result.identified_provider or "",
-            }
+            },
         }
-        
+
         # Add metadata from the result
         if result.metadata:
             response["metadata"].update(result.metadata)
-        
+
         # Add specific metadata based on source type
         if source_type == "url":
             if result.title:
@@ -152,10 +155,10 @@ async def _extract_content_impl(
                 response["metadata"]["file_path"] = result.file_path
             response["metadata"]["file_size"] = Path(file_path).stat().st_size
             response["metadata"]["file_extension"] = Path(file_path).suffix
-        
+
         logger.info(f"Successfully extracted content from {source_type}: {source}")
         return response
-        
+
     except Exception as e:
         logger.error(f"Error extracting content from {source_type} {source}: {str(e)}")
         return {
@@ -166,26 +169,25 @@ async def _extract_content_impl(
             "content": None,
             "metadata": {
                 "extraction_timestamp": start_time.isoformat() + "Z",
-                "error_type": type(e).__name__
-            }
+                "error_type": type(e).__name__,
+            },
         }
 
 
 @mcp.tool
 async def extract_content(
-    url: Optional[str] = None,
-    file_path: Optional[str] = None
+    url: Optional[str] = None, file_path: Optional[str] = None
 ) -> Dict[str, Any]:
     """
     Extract content from a URL or file using Content Core's auto engine.
-    
+
     Args:
         url: Optional URL to extract content from
         file_path: Optional file path to extract content from
-        
+
     Returns:
         JSON object containing extracted content and metadata
-        
+
     Raises:
         ValueError: If neither or both url and file_path are provided
     """
@@ -197,15 +199,16 @@ def main():
     # Additional MoviePy configuration to suppress all output
     try:
         import moviepy.config as mp_config
+
         mp_config.check_and_download_cmd("ffmpeg")  # Pre-download to avoid logs later
     except Exception:
         pass  # Ignore if MoviePy isn't available or configured
-    
+
     logger.info("Starting Content Core MCP Server")
-    
+
     # Run with STDIO transport for MCP compatibility
     mcp.run()
 
 
 if __name__ == "__main__":
-    main()
+    main()

{content_core-1.1.0.dist-info → content_core-1.1.2.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 1.1.0
-Summary: Extract what matters from any media source
+Version: 1.1.2
+Summary: Extract what matters from any media source. Available as Python Library, macOS Service, CLI and MCP Server
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
 Requires-Python: >=3.10
@@ -60,6 +60,7 @@ The primary goal of Content Core is to simplify the process of ingesting content
     * You can override this by specifying an engine, but `'auto'` is recommended for most users.
 *   **Content Cleaning (Optional):** Likely integrates with LLMs (via `prompter.py` and Jinja templates) to refine and clean the extracted content.
 *   **MCP Server:** Includes a Model Context Protocol (MCP) server for seamless integration with Claude Desktop and other MCP-compatible applications.
+*   **macOS Services:** Right-click context menu integration for Finder (extract and summarize files directly).
 *   **Asynchronous:** Built with `asyncio` for efficient I/O operations.
 
 ## Getting Started
@@ -92,6 +93,18 @@ uv sync
 Content Core provides three CLI commands for extracting, cleaning, and summarizing content: 
 ccore, cclean, and csum. These commands support input from text, URLs, files, or piped data (e.g., via cat file | command).
 
+**Zero-install usage with uvx:**
+```bash
+# Extract content
+uvx --from "content-core" ccore https://example.com
+
+# Clean content  
+uvx --from "content-core" cclean "messy content"
+
+# Summarize content
+uvx --from "content-core" csum "long text" --context "bullet points"
+```
+
 #### ccore - Extract Content
 
 Extracts content from text, URLs, or files, with optional formatting.
@@ -232,6 +245,49 @@ Add to your `claude_desktop_config.json`:
 
 For detailed setup instructions, configuration options, and usage examples, see our [MCP Documentation](docs/mcp.md).
 
+## macOS Services Integration
+
+Content Core provides powerful right-click integration with macOS Finder, allowing you to extract and summarize content from any file without installation. Choose between clipboard or TextEdit output for maximum flexibility.
+
+### Available Services
+
+Create **4 convenient services** for different workflows:
+
+- **Extract Content → Clipboard** - Quick copy for immediate pasting
+- **Extract Content → TextEdit** - Review before using  
+- **Summarize Content → Clipboard** - Quick summary copying
+- **Summarize Content → TextEdit** - Formatted summary with headers
+
+### Quick Setup
+
+1. **Install uv** (if not already installed):
+   ```bash
+   curl -LsSf https://astral.sh/uv/install.sh | sh
+   ```
+
+2. **Create services manually** using Automator (5 minutes setup)
+
+### Usage
+
+**Right-click any supported file** in Finder → **Services** → Choose your option:
+
+- **PDFs, Word docs** - Instant text extraction
+- **Videos, audio files** - Automatic transcription  
+- **Images** - OCR text recognition
+- **Web content** - Clean text extraction
+- **Multiple files** - Batch processing support
+
+### Features
+
+- **Zero-install processing**: Uses `uvx` for isolated execution
+- **Multiple output options**: Clipboard or TextEdit display
+- **System notifications**: Visual feedback on completion
+- **Wide format support**: 20+ file types supported
+- **Batch processing**: Handle multiple files at once
+- **Keyboard shortcuts**: Assignable hotkeys for power users
+
+For complete setup instructions with copy-paste scripts, see [macOS Services Documentation](docs/macos.md).
+
 ## Using with Langchain
 
 For users integrating with the [Langchain](https://python.langchain.com/) framework, `content-core` exposes a set of compatible tools. These tools, located in the `src/content_core/tools` directory, allow you to leverage `content-core` extraction, cleaning, and summarization capabilities directly within your Langchain agents and chains.

{content_core-1.1.0.dist-info → content_core-1.1.2.dist-info}/RECORD

@@ -20,7 +20,7 @@ content_core/content/identification/__init__.py,sha256=x4n8JIjDwmPvAopEEEcmZjloz
 content_core/content/summary/__init__.py,sha256=ReKCZWKfDtqlInKeh87Y1DEfiNzVWabGybEz3hS2FrI,114
 content_core/content/summary/core.py,sha256=kEabpETljzUb-yf0NcVWTOuCtayESo74gGBVDX7YTFs,550
 content_core/mcp/__init__.py,sha256=KNZYH4F9AoW1Orw1BtO3n92Cn-127hI7iF9gnGadueU,95
-content_core/mcp/server.py,sha256=m2A63Qle3nJ_Lw46uWkwVvYERtEw84hd7NHAn1rwdAQ,6968
+content_core/mcp/server.py,sha256=ql0uXHkIbZlHQUhUQ4CaRnj19xT6t8ErydWntFgmtUg,7021
 content_core/notebooks/run.ipynb,sha256=WPBNcQUNXR5MldNMghVcU4vE4ibrVmlANa80baQn8TA,371078
 content_core/processors/audio.py,sha256=Mie20g_2Akhw6BHBVo3sHMpDRYUkqBI72lEDakscx3s,5729
 content_core/processors/docling.py,sha256=dkXehsQdfyWXfrK1K_6Pye50ABM7DxMk6TMguabM9Pc,2151
@@ -34,8 +34,8 @@ content_core/tools/__init__.py,sha256=DuJmd7fE-NpDvLP8IW1XY5MUkAQcdks52rn2jk4N8j
 content_core/tools/cleanup.py,sha256=5IdKedsFyRQMdYzgFSKtsfyxJldbroXQXHesHICNENI,523
 content_core/tools/extract.py,sha256=-r2_jsuMMXyXxGVqWhh1ilNPo_UMYAbw3Pkp1FzPy5g,577
 content_core/tools/summarize.py,sha256=DPfeglLWB08q8SvHrsKpOKZ35XjduUDs2J02ISwjdj0,596
-content_core-1.1.0.dist-info/METADATA,sha256=9-ppXQ7o-s8BCb2lH5xBiaiYBHmOFmXFrWntHuo9G_o,13017
-content_core-1.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-content_core-1.1.0.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
-content_core-1.1.0.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
-content_core-1.1.0.dist-info/RECORD,,
+content_core-1.1.2.dist-info/METADATA,sha256=_0Rg4yeU-05hDB_91dvcMXYKMaKcMcU5C8SpkYhtiRs,15072
+content_core-1.1.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+content_core-1.1.2.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
+content_core-1.1.2.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
+content_core-1.1.2.dist-info/RECORD,,