First_agent_template / tools /visit_webpage.py
juanmaguitar's picture
more reliable way of getting images
e27aff8
import re
from typing import Any, Optional
from smolagents.tools import Tool
import requests
import markdownify
import smolagents
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:
# Add headers to mimic a browser
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
# Send a GET request to the URL with a 20-second timeout
response = requests.get(url, timeout=20, headers=headers)
response.raise_for_status()
# Convert the HTML content to Markdown
markdown_content = markdownify.markdownify(response.text).strip()
# Remove multiple line breaks
markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
return markdown_content[:10000] # Limit content length
except requests.exceptions.Timeout:
return "The request timed out. Please try again later or check the URL."
except requests.exceptions.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