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 __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.is_initialized = True

    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:
            # Add User-Agent header to mimic a browser
            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'}
            response = requests.get(url, headers=headers, timeout=20)
            response.raise_for_status()

            markdown_content = markdownify(response.text).strip()
            markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)

            return truncate_content(markdown_content, 10000)

        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)}"