CheddahBot/cheddahbot/tools/web.py

65 lines
2.3 KiB
Python

"""Web tools: search, fetch URL, scrape."""
from __future__ import annotations
import httpx
from bs4 import BeautifulSoup
from . import tool
@tool("web_search", "Search the web using DuckDuckGo", category="web")
def web_search(query: str, max_results: int = 5) -> str:
try:
# Use DuckDuckGo HTML search (no API key needed)
r = httpx.get(
"https://html.duckduckgo.com/html/",
params={"q": query},
headers={"User-Agent": "Mozilla/5.0 (compatible; CheddahBot/1.0)"},
timeout=15,
follow_redirects=True,
)
soup = BeautifulSoup(r.text, "html.parser")
results = []
for item in soup.select(".result")[:max_results]:
title_el = item.select_one(".result__title a")
snippet_el = item.select_one(".result__snippet")
if title_el:
title = title_el.get_text(strip=True)
url = title_el.get("href", "")
snippet = snippet_el.get_text(strip=True) if snippet_el else ""
results.append(f"**{title}**\n{url}\n{snippet}")
return "\n\n".join(results) if results else "No results found."
except Exception as e:
return f"Search error: {e}"
@tool("fetch_url", "Fetch and extract text content from a URL", category="web")
def fetch_url(url: str) -> str:
try:
r = httpx.get(
url,
headers={"User-Agent": "Mozilla/5.0 (compatible; CheddahBot/1.0)"},
timeout=20,
follow_redirects=True,
)
content_type = r.headers.get("content-type", "")
if "html" in content_type:
soup = BeautifulSoup(r.text, "html.parser")
# Remove script/style elements
for tag in soup(["script", "style", "nav", "footer", "header"]):
tag.decompose()
text = soup.get_text(separator="\n", strip=True)
# Collapse whitespace
lines = [line.strip() for line in text.split("\n") if line.strip()]
text = "\n".join(lines)
if len(text) > 15000:
text = text[:15000] + "\n... (truncated)"
return text
elif "json" in content_type:
return r.text[:15000]
else:
return r.text[:5000]
except Exception as e:
return f"Fetch error: {e}"