Files
go-extractor/sites/duckduckgo/duckduckgo.go
T
steve 841f1ec2bf
CI / build (push) Successful in 1m0s
CI / test (push) Successful in 1m8s
CI / vet (push) Successful in 1m12s
feat(duckduckgo): detect anti-bot challenge and surface ErrBlocked
DuckDuckGo intermittently serves a CAPTCHA modal ("Unfortunately, bots
use DuckDuckGo too...") instead of search results. The result selector
matches zero elements on that page, so callers used to get
([]Result{}, nil) — silent empty results that look like "no matches."

Detect the challenge via the BEM class .anomaly-modal__title and return
a typed ErrBlocked so callers can distinguish blocked from no-results
and react (retry, fallback to another engine, surface to user).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-27 23:25:28 +00:00

105 lines
2.2 KiB
Go

package duckduckgo
import (
"context"
"errors"
"fmt"
"log/slog"
"net/url"
"gitea.stevedudenhoeffer.com/steve/go-extractor"
)
// ErrBlocked is returned when DuckDuckGo serves an anti-bot challenge
// page instead of search results.
var ErrBlocked = errors.New("duckduckgo: blocked by anti-bot challenge")
type SafeSearch int
const (
SafeSearchOn SafeSearch = 1
SafeSearchModerate SafeSearch = -1
SafeSearchOff SafeSearch = -2
)
type Config struct {
// SafeSearch is the safe-search level to use. If empty, SafeSearchOff will be used.
SafeSearch SafeSearch
// Region is the region to use for the search engine.
// See: https://duckduckgo.com/duckduckgo-help-pages/settings/params/ for more values
Region string
}
func (c Config) validate() Config {
if c.SafeSearch == 0 {
c.SafeSearch = SafeSearchOff
}
return c
}
func (c Config) ToSearchURL(query string) *url.URL {
c = c.validate()
res, _ := url.Parse("https://duckduckgo.com/")
var vals = res.Query()
switch c.SafeSearch {
case SafeSearchOn:
vals.Set("kp", "1")
case SafeSearchModerate:
vals.Set("kp", "-1")
case SafeSearchOff:
vals.Set("kp", "-2")
}
if c.Region != "" {
vals.Set("kl", c.Region)
}
vals.Set("q", query)
res.RawQuery = vals.Encode()
return res
}
var DefaultConfig = Config{
SafeSearch: SafeSearchOff,
}
type Result struct {
URL string
Title string
Description string
}
func (c Config) OpenSearch(ctx context.Context, b extractor.Browser, query string) (SearchPage, error) {
u := c.ToSearchURL(query)
slog.Info("searching", "url", u, "query", query, "config", c, "browser", b)
doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{})
if err != nil {
if doc != nil {
_ = doc.Close()
}
return nil, fmt.Errorf("failed to open url: %w", err)
}
return searchPage{doc}, nil
}
func (c Config) Search(ctx context.Context, b extractor.Browser, query string) ([]Result, error) {
u := c.ToSearchURL(query)
slog.Info("searching", "url", u, "query", query, "config", c, "browser", b)
doc, err := b.Open(ctx, u.String(), extractor.OpenPageOptions{})
if err != nil {
return nil, fmt.Errorf("failed to open url: %w", err)
}
defer extractor.DeferClose(doc)
return extractResults(doc)
}