Spaces:
Sleeping
Sleeping
Create tools.py
Browse files
tools.py
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
import requests
|
| 3 |
+
from markdownify import markdownify
|
| 4 |
+
from requests.exceptions import RequestException
|
| 5 |
+
from smolagents import tool
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
@tool
|
| 9 |
+
def visit_webpage(url: str) -> str:
|
| 10 |
+
"""Visits a webpage at the given URL and returns its content as a markdown string.
|
| 11 |
+
|
| 12 |
+
Args:
|
| 13 |
+
url: The URL of the webpage to visit.
|
| 14 |
+
|
| 15 |
+
Returns:
|
| 16 |
+
The content of the webpage converted to Markdown, or an error message if the request fails.
|
| 17 |
+
"""
|
| 18 |
+
try:
|
| 19 |
+
# Send a GET request to the URL
|
| 20 |
+
response = requests.get(url)
|
| 21 |
+
response.raise_for_status() # Raise an exception for bad status codes
|
| 22 |
+
|
| 23 |
+
# Convert the HTML content to Markdown
|
| 24 |
+
markdown_content = markdownify(response.text).strip()
|
| 25 |
+
|
| 26 |
+
# Remove multiple line breaks
|
| 27 |
+
markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
|
| 28 |
+
|
| 29 |
+
return markdown_content
|
| 30 |
+
|
| 31 |
+
except RequestException as e:
|
| 32 |
+
return f"Error fetching the webpage: {str(e)}"
|
| 33 |
+
except Exception as e:
|
| 34 |
+
return f"An unexpected error occurred: {str(e)}"
|