tools/visit_webpage.py

from typing import Any, Optional
from smolagents.tools import Tool
import requests
import markdownify
import smolagents
import re

class VisitWebpageTool(Tool):
    name = "visit_webpage"
    description = "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages."
    inputs = {'url': {'type': 'string', 'description': 'The url of the webpage to visit.'}}
    output_type = "string"

    def forward(self, url: str) -> str:
        try:
            import requests
            from markdownify import markdownify
            from requests.exceptions import RequestException

            from smolagents.utils import truncate_content
        except ImportError as e:
            raise ImportError(
                "You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
            ) from e
        try:
            headers = {
                "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.1 Safari/605.1.15",
                "referer": "https://duckduckgo.com/",
                "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
                'accept-language': 'en-US,en;q=0.9',
                'accept-Encoding': 'gzip, deflate, br',
                'priority': 'u=0, i',
                'referer': 'https://duckduckgo.com/',
                'sec-fetch-dest': 'document',
                'sec-fetch-mode': 'navigate',
                'sec-fetch-site': 'cross-site',
            }
            
            # Send a GET request to the URL with a 20-second timeout
            response = requests.get(url, timeout=20, allow_redirects=True, headers=headers)
            response.raise_for_status()  # Raise an exception for bad status codes

            # Convert the HTML content to Markdown
            markdown_content = markdownify(response.text).strip()

            # Remove multiple line breaks
            markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)

            return truncate_content(markdown_content, 50000)

        except requests.exceptions.Timeout:
            return "The request timed out. Please try again later or check the URL."
        except RequestException as e:
            return f"Error fetching the webpage: {str(e)}"
        except Exception as e:
            return f"An unexpected error occurred: {str(e)}"

    def __init__(self, *args, **kwargs):
        self.is_initialized = False