This repository has been archived on 2026-04-03. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
core/server/tools/search/duckduckgo.go
2026-02-25 23:56:27 +00:00

153 lines
3.5 KiB
Go

package search
import (
"context"
"fmt"
"io"
"net/http"
"net/url"
"strings"
"time"
"golang.org/x/net/html"
)
func init() {
RegisterProvider(&DuckDuckGo{})
// Default active provider — no API key needed
_ = SetActive("duckduckgo")
}
// DuckDuckGo implements Provider using DDG's HTML lite endpoint.
// No API key required. Returns organic web results.
type DuckDuckGo struct{}
func (d *DuckDuckGo) Name() string { return "duckduckgo" }
func (d *DuckDuckGo) Search(ctx context.Context, query string, maxResults int) ([]SearchResult, error) {
if maxResults <= 0 {
maxResults = 5
}
if maxResults > 10 {
maxResults = 10
}
endpoint := "https://html.duckduckgo.com/html/?q=" + url.QueryEscape(query)
req, err := http.NewRequestWithContext(ctx, "GET", endpoint, nil)
if err != nil {
return nil, fmt.Errorf("build request: %w", err)
}
req.Header.Set("User-Agent", "ChatSwitchboard/1.0 (Web Search Tool)")
client := &http.Client{Timeout: 10 * time.Second}
resp, err := client.Do(req)
if err != nil {
return nil, fmt.Errorf("search request failed: %w", err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
return nil, fmt.Errorf("search returned HTTP %d", resp.StatusCode)
}
// Limit body read to 512KB
body, err := io.ReadAll(io.LimitReader(resp.Body, 512*1024))
if err != nil {
return nil, fmt.Errorf("read response: %w", err)
}
return parseDDGHTML(string(body), maxResults), nil
}
// parseDDGHTML extracts search results from DuckDuckGo's HTML lite page.
// Results are in <a class="result__a"> tags with snippets in <a class="result__snippet">.
func parseDDGHTML(htmlContent string, maxResults int) []SearchResult {
doc, err := html.Parse(strings.NewReader(htmlContent))
if err != nil {
return nil
}
var results []SearchResult
// Walk the DOM looking for result blocks
var walk func(*html.Node)
walk = func(n *html.Node) {
if len(results) >= maxResults {
return
}
if n.Type == html.ElementNode && n.Data == "a" {
class := getAttr(n, "class")
if strings.Contains(class, "result__a") {
href := getAttr(n, "href")
title := textContent(n)
// DDG wraps URLs through a redirect; extract the actual URL
actualURL := extractDDGURL(href)
if actualURL != "" && title != "" {
results = append(results, SearchResult{
Title: strings.TrimSpace(title),
URL: actualURL,
})
}
}
if strings.Contains(class, "result__snippet") {
snippet := strings.TrimSpace(textContent(n))
// Attach snippet to the most recent result
if len(results) > 0 && results[len(results)-1].Snippet == "" {
results[len(results)-1].Snippet = snippet
}
}
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
walk(c)
}
}
walk(doc)
return results
}
// extractDDGURL extracts the actual URL from DDG's redirect wrapper.
// DDG links look like: //duckduckgo.com/l/?uddg=https%3A%2F%2Fexample.com&rut=...
func extractDDGURL(href string) string {
if strings.Contains(href, "uddg=") {
u, err := url.Parse(href)
if err != nil {
return href
}
uddg := u.Query().Get("uddg")
if uddg != "" {
return uddg
}
}
// Direct URL
if strings.HasPrefix(href, "http") {
return href
}
return ""
}
func getAttr(n *html.Node, key string) string {
for _, a := range n.Attr {
if a.Key == key {
return a.Val
}
}
return ""
}
func textContent(n *html.Node) string {
if n.Type == html.TextNode {
return n.Data
}
var sb strings.Builder
for c := n.FirstChild; c != nil; c = c.NextSibling {
sb.WriteString(textContent(c))
}
return sb.String()
}