tools/http_request_tool.py

#!/usr/bin/env python3
"""
Custom HTTP Request Tool for Hugging Face Spaces

Replaces strands-tools http_request to avoid npm permission issues
"""

import requests
from bs4 import BeautifulSoup
import html2text
from strands import tool
from typing import Optional

@tool
def http_request(url: str, method: str = "GET", headers: Optional[dict] = None, 
                data: Optional[dict] = None, timeout: int = 30) -> str:
    """
    Make HTTP requests and return content as markdown
    
    Args:
        url: The URL to fetch
        method: HTTP method (GET, POST, etc.)
        headers: Optional headers dictionary
        data: Optional data for POST requests
        timeout: Request timeout in seconds
        
    Returns:
        Content converted to markdown format
    """
    print(f"🌐 Making {method} request to: {url}")
    
    try:
        # Set default headers
        if headers is None:
            headers = {
                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
            }
        
        # Make the HTTP request
        if method.upper() == "POST":
            response = requests.post(url, headers=headers, json=data, timeout=timeout)
        elif method.upper() == "PUT":
            response = requests.put(url, headers=headers, json=data, timeout=timeout)
        elif method.upper() == "DELETE":
            response = requests.delete(url, headers=headers, timeout=timeout)
        else:
            response = requests.get(url, headers=headers, timeout=timeout)
        
        # Check if request was successful
        response.raise_for_status()
        
        # Get content type
        content_type = response.headers.get('content-type', '').lower()
        
        # Handle different content types
        if 'application/json' in content_type:
            # Return JSON as formatted text
            import json
            return json.dumps(response.json(), indent=2)
            
        elif 'text/html' in content_type:
            # Convert HTML to markdown
            soup = BeautifulSoup(response.text, 'html.parser')
            
            # Remove script and style tags
            for tag in soup(["script", "style", "nav", "footer", "header"]):
                tag.decompose()
            
            # Convert to markdown
            h = html2text.HTML2Text()
            h.ignore_links = False
            h.ignore_images = False
            h.body_width = 0  # No line wrapping
            
            markdown_content = h.handle(str(soup))
            
            # Add metadata
            result = f"# Content from {url}\n\n"
            result += f"**Status Code:** {response.status_code}\n"
            result += f"**Content Type:** {content_type}\n\n"
            result += markdown_content
            
            print(f"✅ Successfully fetched and converted HTML content ({len(result)} chars)")
            return result
            
        else:
            # Return plain text
            result = f"# Content from {url}\n\n"
            result += f"**Status Code:** {response.status_code}\n"
            result += f"**Content Type:** {content_type}\n\n"
            result += response.text
            
            print(f"✅ Successfully fetched text content ({len(result)} chars)")
            return result
            
    except requests.exceptions.Timeout:
        error_msg = f"Request to {url} timed out after {timeout} seconds"
        print(f"❌ {error_msg}")
        return error_msg
        
    except requests.exceptions.RequestException as e:
        error_msg = f"HTTP request failed for {url}: {str(e)}"
        print(f"❌ {error_msg}")
        return error_msg
        
    except Exception as e:
        error_msg = f"Error processing HTTP request for {url}: {str(e)}"
        print(f"❌ {error_msg}")
        return error_msg