app.py

import gradio as gr
import requests
from tenacity import retry, wait_exponential, stop_after_attempt, retry_if_exception_type
import json

# Define custom exceptions for clarity
class RateLimitException(Exception):
    pass

# Retry configuration: Retry up to 5 times with exponential backoff
@retry(
    wait=wait_exponential(multiplier=1, min=4, max=10),
    stop=stop_after_attempt(5),
    retry=retry_if_exception_type(RateLimitException)
)
def search_searx(query, instance_url='https://searx.org', categories='general'):
    """
    Perform a search using the Searx API with retry logic.

    :param query: The search query string.
    :param instance_url: The URL of the Searx instance.
    :param categories: Categories to search in (e.g., 'general', 'images', 'videos').
    :return: A list of formatted search results or an error message.
    """
    search_endpoint = f"{instance_url}/search"
    params = {
        'q': query,
        'format': 'json',
        'categories': categories,
        'pageno': 1,          # Page number
        'time_range': '',     # Time range filter
        'engines': '',        # Specify search engines, comma-separated
        'safesearch': '0'     # Safe search (0: off, 1: moderate, 2: strict)
    }
    
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' +
                      'AppleWebKit/537.36 (KHTML, like Gecko) ' +
                      'Chrome/58.0.3029.110 Safari/537.3'
    }

    try:
        response = requests.get(search_endpoint, params=params, headers=headers, timeout=10)
        if response.status_code == 429:
            raise RateLimitException("Rate limit exceeded. Retrying...")
        response.raise_for_status()  # Raise an error for bad status codes
        data = response.json()
        
        if 'results' not in data or not data['results']:
            return "No results found."

        formatted_results = ""
        for idx, result in enumerate(data['results'], start=1):
            title = result.get('title', 'No Title')
            url = result.get('url', 'No URL')
            snippet = result.get('content', 'No Description')
            # Using Markdown link formatting
            formatted_results += f"**{idx}. [{title}]({url})**\n{snippet}\n\n"

        return formatted_results

    except RateLimitException as e:
        # After retries, if still failing due to rate limits
        return f"Rate limit exceeded. Please try again later.\nError: {e}"
    except requests.exceptions.RequestException as e:
        return f"An error occurred while searching: {e}"
    except json.JSONDecodeError:
        return "Failed to parse the response from the Searx instance."

def create_gradio_interface():
    """
    Creates and returns the Gradio interface.
    """
    with gr.Blocks() as demo:
        gr.Markdown("# 🕵️‍♂️ Private Search with Searx and Gradio")
        gr.Markdown(
            "This application allows you to perform private searches using the [Searx](https://searx.org/) metasearch engine."
        )

        with gr.Row():
            with gr.Column():
                query = gr.Textbox(
                    label="Search Query",
                    placeholder="Enter your search query here...",
                    lines=1
                )
                instance_url = gr.Textbox(
                    label="Searx Instance URL",
                    value="https://searx.org",
                    placeholder="https://searx.instance.url",
                    lines=1
                )
                categories = gr.Textbox(
                    label="Categories",
                    value="general",
                    placeholder="e.g., general, images, videos",
                    lines=1
                )
                search_button = gr.Button("Search")

            with gr.Column():
                results = gr.Markdown("### Search Results will appear here...")

        def perform_search(q, url, cats):
            return search_searx(q, instance_url=url, categories=cats)

        search_button.click(
            perform_search,
            inputs=[query, instance_url, categories],
            outputs=results
        )

        gr.Markdown(
            """
            ---
            **Note:** This application uses the Searx metasearch engine to fetch results from multiple sources while preserving your privacy.
            """
        )

    return demo

iface = create_gradio_interface()

if __name__ == "__main__":
    iface.launch()