21 lines
763 B
Python
21 lines
763 B
Python
import httpx
|
|
from typing import Dict, Any
|
|
|
|
class WebCrawlerTool:
|
|
def __init__(self, timeout: int = 10):
|
|
self.timeout = timeout
|
|
|
|
async def crawl(self, url: str) -> Dict[str, Any]:
|
|
try:
|
|
async with httpx.AsyncClient(timeout=self.timeout) as client:
|
|
response = await client.get(url)
|
|
response.raise_for_status()
|
|
# Basic text extraction can happen here (e.g., stripping HTML tags manually or with a library later)
|
|
return {
|
|
"url": url,
|
|
"status_code": response.status_code,
|
|
"content_preview": response.text[:500]
|
|
}
|
|
except Exception as e:
|
|
return {"url": url, "error": str(e)}
|