mirror of
https://github.com/karust/openserp.git
synced 2026-08-05 16:53:54 +08:00
9cc69da758
- Add structured `search [engine] [query]` CLI: --limit/--lang/--region/--site/--file, --format (json|text|markdown|ndjson), --extract N, --search-timeout; Envelope and route logs to stderr with a --quiet default (fixes stdout pollution) - Unify engines behind a single engineSpec registry (CLI + serve share it) - Unify the extract knob to bool-or-int `extract=N` (drop extract_top); CLI and HTTP share core batch extraction, raw/rendered fetch, and clamp helpers - Engines: Ecosia CF captcha detection (raw + browser), Yandex progressive-result wait, Google PAA poll + Has() existence probes, Bing title/desc attribute fallbacks - Proxy: rotate challenged proxies out of the tag pool for one retry (X-Proxy-Attempts); browser health-ping skip window; opt-in WaitStable
32 lines
1.1 KiB
Go
32 lines
1.1 KiB
Go
package ecosia
|
|
|
|
// Selectors is the single source of truth for Ecosia SERP CSS selectors.
|
|
var Selectors = struct {
|
|
Captcha string
|
|
Mainline string
|
|
Result string
|
|
Ad string
|
|
ResultLink string
|
|
Title string
|
|
Desc string
|
|
ImageResult string
|
|
ImageLink string
|
|
ImageSource string
|
|
ImageDims string
|
|
}{
|
|
// Captcha matches Ecosia's Cloudflare Turnstile interstitial. The hidden
|
|
// cf-turnstile-response input is present on every challenge page and never
|
|
// on a real SERP, so it's a precise marker for the raw (browserless) path.
|
|
Captcha: "input[name='cf-turnstile-response']",
|
|
Mainline: "[data-test-id='mainline']",
|
|
Result: "[data-test-id='mainline-result-web']",
|
|
Ad: "[data-test-id='mainline-result-ad']",
|
|
ResultLink: "[data-test-id='result-link']",
|
|
Title: "[data-test-id='result-title']",
|
|
Desc: "[data-test-id='result-description']",
|
|
ImageResult: "[data-test-id='images-result']",
|
|
ImageLink: "[data-test-id='image-result-link']",
|
|
ImageSource: "[data-test-id='image-result-source']",
|
|
ImageDims: "[data-test-id='image-result-dimensions']",
|
|
}
|