kafka/internal/engines/bing.go

// kafka — a privacy-respecting metasearch engine
// Copyright (C) 2026-present metamorphosis-dev
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <https://www.gnu.org/licenses/>.

package engines

import (
	"context"
	"encoding/json"
	"encoding/xml"
	"errors"
	"fmt"
	"io"
	"net/http"
	"net/url"
	"strconv"
	"strings"

	"github.com/metamorphosis-dev/kafka/internal/contracts"
)

// BingEngine searches Bing via the public Bing API.
// Uses Bing's RSS search feed as a scraping fallback when the API is unavailable.
// Note: Bing's HTML is heavily JS-dependent and blocks non-browser clients,
// so this engine falls back gracefully when results cannot be retrieved.
type BingEngine struct {
	client *http.Client
}

func (e *BingEngine) Name() string { return "bing" }

func (e *BingEngine) Search(ctx context.Context, req contracts.SearchRequest) (contracts.SearchResponse, error) {
	if strings.TrimSpace(req.Query) == "" {
		return contracts.SearchResponse{Query: req.Query}, nil
	}
	if e == nil || e.client == nil {
		return contracts.SearchResponse{}, errors.New("bing engine not initialized")
	}

	endpoint := fmt.Sprintf(
		"https://www.bing.com/search?q=%s&count=10&offset=%d&format=rss",
		url.QueryEscape(req.Query),
		(req.Pageno-1)*10,
	)

	httpReq, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
	if err != nil {
		return contracts.SearchResponse{}, err
	}
	httpReq.Header.Set("User-Agent", "kafka/0.1 (compatible; +https://git.ashisgreat.xyz/penal-colony/gosearch)")

	resp, err := e.client.Do(httpReq)
	if err != nil {
		return contracts.SearchResponse{}, err
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		body, _ := io.ReadAll(io.LimitReader(resp.Body, 4096))
		return contracts.SearchResponse{}, fmt.Errorf("bing upstream error: status=%d body=%q", resp.StatusCode, string(body))
	}

	contentType := resp.Header.Get("Content-Type")
	if strings.Contains(contentType, "json") {
		return parseBingJSON(resp.Body, req.Query)
	}

	if strings.Contains(contentType, "xml") || strings.Contains(contentType, "rss") {
		return parseBingRSS(resp.Body, req.Query)
	}

	// If Bing returned HTML instead of RSS, it likely blocked us.
	return contracts.SearchResponse{
		Query:               req.Query,
		NumberOfResults:    0,
		Results:             []contracts.MainResult{},
		Answers:             []map[string]any{},
		Corrections:         []string{},
		Infoboxes:           []map[string]any{},
		Suggestions:         []string{},
		UnresponsiveEngines: [][2]string{{"bing", "blocked by bot detection"}},
	}, nil
}

// parseBingRSS parses Bing's RSS search results.
func parseBingRSS(r io.Reader, query string) (contracts.SearchResponse, error) {
	type RSS struct {
		XMLName xml.Name `xml:"rss"`
		Channel struct {
			Items []struct {
				Title   string `xml:"title"`
				Link    string `xml:"link"`
				Descrip string `xml:"description"`
			} `xml:"item"`
		} `xml:"channel"`
	}

	var rss RSS
	if err := xml.NewDecoder(r).Decode(&rss); err != nil {
		return contracts.SearchResponse{}, fmt.Errorf("bing RSS parse error: %w", err)
	}

	results := make([]contracts.MainResult, 0, len(rss.Channel.Items))
	for _, item := range rss.Channel.Items {
		if item.Link == "" {
			continue
		}
		linkPtr := item.Link
		results = append(results, contracts.MainResult{
			Template: "default.html",
			Title:    item.Title,
			Content:  stripHTML(item.Descrip),
			URL:      &linkPtr,
			Engine:   "bing",
			Score:    0,
			Category: "general",
			Engines:  []string{"bing"},
		})
	}

	return contracts.SearchResponse{
		Query:               query,
		NumberOfResults:    len(results),
		Results:             results,
		Answers:             []map[string]any{},
		Corrections:         []string{},
		Infoboxes:           []map[string]any{},
		Suggestions:         []string{},
		UnresponsiveEngines: [][2]string{},
	}, nil
}

// parseBingJSON parses Bing's JSON API response.
func parseBingJSON(r io.Reader, query string) (contracts.SearchResponse, error) {
	var data struct {
		WebPages struct {
			TotalEstimatedMatches int `json:"totalEstimatedMatches"`
			Value                 []struct {
				Name        string `json:"name"`
				URL         string `json:"url"`
				Snippet     string `json:"snippet"`
				DateLastCrawled string `json:"dateLastCrawled"`
			} `json:"value"`
		} `json:"webPages"`
	}

	if err := json.NewDecoder(r).Decode(&data); err != nil {
		return contracts.SearchResponse{}, fmt.Errorf("bing JSON parse error: %w", err)
	}

	results := make([]contracts.MainResult, 0, len(data.WebPages.Value))
	for _, item := range data.WebPages.Value {
		linkPtr := item.URL
		results = append(results, contracts.MainResult{
			Template: "default.html",
			Title:    item.Name,
			Content:  item.Snippet,
			URL:      &linkPtr,
			Engine:   "bing",
			Score:    0,
			Category: "general",
			Engines:  []string{"bing"},
		})
	}

	return contracts.SearchResponse{
		Query:               query,
		NumberOfResults:    data.WebPages.TotalEstimatedMatches,
		Results:             results,
		Answers:             []map[string]any{},
		Corrections:         []string{},
		Infoboxes:           []map[string]any{},
		Suggestions:         []string{},
		UnresponsiveEngines: [][2]string{},
	}, nil
}

var _ = strconv.Itoa
var _ = json.Unmarshal