Agent0.py

from duckduckgo_search import DDGS
import datetime
import requests
from bs4 import BeautifulSoup

class Agent:
    """
    An enhanced agent that gathers comprehensive context from various sources,
    excluding weather.
    """

    def __init__(self):
        """
        Initializes the Agent with a DDGS search object.
        """
        self.ddgs = DDGS()

    def search(self, query, num_results=3):
        """
        Performs a web search using DuckDuckGo.

        Args:
            query (str): The search query.
            num_results (int): The maximum number of results to return.

        Returns:
            str: A formatted string of search results.
        """
        results = ""
        try:
            search_results = list(self.ddgs.text(query, max_results=num_results))
            if not search_results:
                return "No search results found.\n"
            for r in search_results:
                results += f"Title: {r.get('title', 'N/A')}\n"
                results += f"Link: {r.get('href', 'N/A')}\n"
                results += f"Snippet: {r.get('body', 'N/A')}\n\n"
        except Exception as e:
            results = f"An error occurred during search: {e}\n"
        return results

    def get_news(self, query="top stories", num_results=5):
        """
        Fetches the latest news headlines.

        Args:
            query (str): The news query (e.g., "technology", "business").
            num_results (int): The maximum number of news articles to return.

        Returns:
            str: A formatted string of news headlines.
        """
        results = ""
        try:
            news_results = list(self.ddgs.news(query, max_results=num_results))
            if not news_results:
                return "No news found.\n"
            for r in news_results:
                results += f"Title: {r.get('title', 'N/A')}\n"
                results += f"Source: {r.get('source', 'N/A')}\n"
                results += f"URL: {r.get('url', 'N/A')}\n"
                results += f"Date: {r.get('date', 'N/A')}\n"
                results += f"Snippet: {r.get('body', 'N/A')}\n\n"
        except Exception as e:
            results = f"An error occurred while fetching news: {e}\n"
        return results

    def get_website_content(self, url):
        """
        Fetches and summarizes the content of a given URL.

        Args:
            url (str): The URL of the website to scrape.

        Returns:
            str: The plain text content of the website.
        """
        try:
            response = requests.get(url, timeout=10)
            response.raise_for_status()  # Raise an exception for bad status codes
            soup = BeautifulSoup(response.text, 'html.parser')
            # Remove script and style elements
            for script_or_style in soup(["script", "style"]):
                script_or_style.decompose()
            text = ' '.join(soup.stripped_strings)
            return f"Content of {url}:\n{text[:2000]}...\n"  # Return a snippet of the content
        except requests.exceptions.RequestException as e:
            return f"Error fetching website content: {e}\n"

    def search_images(self, query, num_results=3):
        """
        Performs an image search using DuckDuckGo.

        Args:
            query (str): The search query for images.
            num_results (int): The maximum number of image results to return.

        Returns:
            str: A formatted string of image results.
        """
        results = ""
        try:
            image_results = list(self.ddgs.images(query, max_results=num_results))
            if not image_results:
                return "No image results found.\n"
            for i in image_results:
                results += f"Title: {i.get('title', 'N/A')}\n"
                results += f"Image URL: {i.get('image', 'N/A')}\n"
                results += f"Source URL: {i.get('url', 'N/A')}\n\n"
        except Exception as e:
            results = f"An error occurred during image search: {e}\n"
        return results

    def GatherContext(self, query="today's news", num_results=3, target_url=None):
        """
        Gathers a comprehensive context from various sources.

        Args:
            query (str): The primary search query.
            num_results (int): The number of results for searches.
            target_url (str, optional): A specific URL to fetch content from.

        Returns:
            str: A single multiline string containing all the gathered context.
        """
        todaydate = datetime.datetime.now().strftime("%Y-%m-%d")
        current_time = datetime.datetime.now().strftime("%H:%M:%S")

        context = f"--- Context Gathered at {current_time} on {todaydate} ---\n\n"

        context += "--- System Time ---\n"
        context += f"Date: {todaydate}\n"
        context += f"Time: {current_time}\n\n"

        context += "--- Latest News ---\n"
        context += self.get_news(query, num_results) + "\n"

        context += "--- Web Search Results ---\n"
        context += self.search(query, num_results) + "\n"

        context += "--- Image Search Results ---\n"
        context += self.search_images(query, num_results) + "\n"

        if target_url:
            context += "--- Website Content ---\n"
            context += self.get_website_content(target_url) + "\n"

        context += "--- End of Context ---"

        return context

if __name__ == "__main__":
    agent = Agent()
    context1 = agent.GatherContext(query="latest advancements in AI", num_results=3)
    print("--- Example 1: General Query ---")
    print(context1)