|
|
from typing import Any, Optional |
|
|
from smolagents.tools import Tool |
|
|
import re |
|
|
import requests |
|
|
import markdownify |
|
|
|
|
|
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, max_output_length: int = 40000): |
|
|
super().__init__() |
|
|
self.max_output_length = max_output_length |
|
|
|
|
|
def _truncate_content(self, content: str, max_length: int) -> str: |
|
|
if len(content) <= max_length: |
|
|
return content |
|
|
return ( |
|
|
content[:max_length] + f"\n..._This content has been truncated to stay below {max_length} characters_...\n" |
|
|
) |
|
|
|
|
|
def forward(self, url: str) -> str: |
|
|
try: |
|
|
import re |
|
|
|
|
|
import requests |
|
|
from markdownify import markdownify |
|
|
from requests.exceptions import RequestException |
|
|
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: |
|
|
|
|
|
response = requests.get(url, timeout=20) |
|
|
response.raise_for_status() |
|
|
|
|
|
|
|
|
markdown_content = markdownify(response.text).strip() |
|
|
|
|
|
|
|
|
markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content) |
|
|
|
|
|
return self._truncate_content(markdown_content, self.max_output_length) |
|
|
|
|
|
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)}" |
|
|
|