DE

Web Search Rerank

Search the web from a natural-language request and return relevance-ranked webpage results with content and source metadata

Entwickler
Preise
0,008 $ / 50 Datensätze
Zuletzt aktualisiert
2026-09-14

Übersicht

Web research often starts with a question rather than a known page. This Data App turns a natural-language request into a relevance-ranked set of webpages, preserving the page text, concise summaries, source identity, and publication context needed for analysis.

It is useful for quickly building a research set around a company, product, topic, or event. Freshness and domain filters help focus the search, while account, organization, and search-role filters can narrow the results when those source attributes are available.

Data notes

Each row represents one webpage returned for the submitted search question. Page URL is used to identify a result and remove duplicates. The result set covers webpage records only; a separate image collection returned by the source is not included here.

Page content may be empty even when a title, snippet, or summary is available. Account name, organization name, site icon, cached URL, language, and family-friendly or navigational flags may also be unavailable for individual pages. Publication and crawl timestamps are preserved as source text without inferring a timezone.

What the results look like

Each row is one relevance-ranked webpage result.

Page URLPage titleSite namePublished atSnippet
https://www.example.com/article/123Xiaomi car delivery momentum continues to riseExample Site2026-08-05 14:23:10Xiaomi car deliveries have continued to grow.

Additional values include the full page content, summary, display and cached URLs, account and organization names, language, source identifiers, and crawl time.

Use cases

  • Build a research set for a company, product, market, or event by combining Page title, Page content, Snippet, and Summary.
  • Monitor recent coverage by pairing a Freshness filter with Published at and Last crawled at.
  • Compare source visibility by grouping results by Site name, Account name, or Organization name.
  • Preserve traceable source links by using Page URL and Display URL when reviewing or exporting results.

Anwendungsbereich & Grenzen

Each run accepts one natural-language search request and returns up to 200 relevance-ranked webpage records in one response. Separate image results are not included.

  • Geeignet für
  • When you need relevance-ranked webpage results for a natural-language research question
  • When you need webpage titles, summaries, content, source metadata, and publication timestamps in a structured result set
  • When you want to narrow web search by freshness, domains, account, organization, or search role
  • Nicht verwenden für
  • When you need image-only results or a dedicated image search dataset
  • When you need private, login-only, or non-public webpage content

Fehlerbehandlung

Vom Entwickler deklariertes Fehler- und Wiederholungsverhalten. Wir empfehlen, es bei der Integration in Ihren System-Prompt aufzunehmen.

  1. 1If no useful webpages are returned, broaden the query or remove restrictive domain and freshness filters
  2. 2Retry later after rate limiting, temporary service unavailability, or a timeout
  3. 3If authentication fails, verify the API Key configured for the execution environment

Eingabe

Parameter, die zum Aufruf dieser App erforderlich sind, generiert aus dem input.schema in der manifest.json.

  • Search questionqueryErforderlichstring
    The natural-language topic or question to search. Provide at least one character; clearer wording produces more focused results.
    BeispielXiaomi car delivery and sales performance
  • Result countcountOptionalinteger
    The number of webpage results to request. The default is 10 and the allowed range is 1 to 200; fewer results may be available for a narrow query.
    Bereich1–200Standard10
  • Freshness filterfreshnessOptionalstring
    Limits results by recency. Use noLimit, oneDay, oneWeek, oneMonth, oneYear, a date such as 2026-08-05, or a date range such as 2026-08-01..2026-08-31. The default is noLimit.
    StandardnoLimit
  • Included domainsincludeOptionalstring
    Search only the listed domains. Separate up to 100 domain values with | or commas, using domain values supplied by the Data Hub domain list.
  • Excluded domainsexcludeOptionalstring
    Exclude the listed domains from the search. Separate up to 100 domain values with | or commas, using domain values supplied by the Data Hub domain list.
  • Account nameaccount_nameOptionalstring
    Filters results to an exact account name when the source identifies one. Leave empty to search without an account filter.
  • Organization nameoffice_nameOptionalstring
    Filters results to an exact organization name when the source identifies one. Leave empty to search without an organization filter.
  • Search rolerole_codeOptionalstring
    Uses a configured Data Hub search role, such as WEB_SEARCH. Leave empty to use the system default role.

Ausgabe

Feldstruktur eines einzelnen Datensatzes, generiert aus dem output.schema in der manifest.json.

  • Account nameaccount_namestring
    The account name associated with the webpage when available.
    BeispielChina News Network
  • Cached page URLcached_page_urlstring
    The cached webpage URL when available.
  • Page contentcontentstring
    The webpage body content when available. It is independent from the snippet and summary and may be empty.
    BeispielXiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling.
  • Last crawled atdate_last_crawledstring
    The source timestamp of the latest crawl, preserved as returned without timezone conversion.
    Beispiel2026-08-05 15:00:00

Beispieldaten

Aus output.schema erzeugt. Felder ohne Beispielwert verwenden strukturelle Platzhalter.

output.example
{
  "account_name": "China News Network",
  "cached_page_url": "<cached_page_url>",
  "content": "Xiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling.",
  "date_last_crawled": "2026-08-05 15:00:00",
  "date_published": "2026-08-05 14:23:10",
  "display_url": "https://www.example.com/article/123",
  "id": "0",
  "is_family_friendly": false,
  "is_navigational": false,
  "language": "en",
  "name": "Xiaomi car delivery momentum continues to rise",
  "office_name": "<office_name>",
  "site_icon": "<site_icon>",
  "site_name": "Example Site",
  "snippet": "Xiaomi car deliveries have continued to grow.",
  "summary": "Xiaomi car deliveries have continued to grow, with stronger showroom traffic and steady delivery scheduling.",
  "url": "https://www.example.com/article/123"
}

Integration

Diese App kann über MCP, API, SDK oder Dateiexport integriert werden — alle Kanäle teilen sich dieselben Fähigkeiten und Preise. Jede Anfrage authentifiziert sich über den Authorization: Bearer-Header mit einem API Key (langlebig, in der Data Hub Konsole erstellt); MCP-Clients können sich zusätzlich per OAuth ohne Key anmelden. Weitere Optionen wie CLI und Skill sind in Vorbereitung.

Über das MCP (Model Context Protocol) können Sie diese App direkt aus KI-Clients wie Claude und Cursor aufrufen. Wählen Sie Ihren Client und den Authentifizierungsmodus und kopieren Sie dann die Konfiguration unten.

Client-Konfiguration

Ersetzen Sie den Wert nach Bearer durch Ihren langlebigen API Key. Funktioniert in jedem Client, in CI und in Headless-Umgebungen.

mcpServers config
{
  "mcpServers": {
    "octoparse_datahub": {
      "type": "http",
      "url": "https://mcp-v2.octoparse.com?pin=meme_today/data-hub-web-search-rerank",
      "headers": { "Authorization": "Bearer <YOUR_API_KEY>" }
    }
  }
}

Lassen Sie die KI die Einrichtung übernehmen

Sie möchten Konfigurationen nicht von Hand bearbeiten? Kopieren Sie den Installations-Prompt und fügen Sie ihn in einen beliebigen KI-Client ein — er schließt die Einrichtung auf seine eigene Weise ab. (Standardmäßig führt er Sie durch die Anmeldung und fordert Sie nie auf, Ihren API Key im Chat zu senden.)

detail.access.mcp.composeHint

Preise

50 returned records

Berechnet nach der Anzahl der erfolgreich zurückgegebenen Datensätze. Fehlgeschlagene Läufe werden nicht berechnet. Abgerechnet in Einheiten von 50 Datensätze; jede angefangene Einheit wird auf 50 Datensätze aufgerundet.

0,008 $/ 50 Datensätze

Mehrere Abrechnungsereignisse werden unabhängig voneinander kumuliert. Details siehe jeweilige Position. Fehlgeschlagene Läufe werden nicht berechnet.

Credits ansehen

Jetzt ausprobieren

Füllen Sie die Parameter aus und starten Sie — die Ergebnisse stammen aus einem echten Aufruf.

Beispiel
Parameter werden vor dem Absenden gegen input.schema validiert
0,008 $ / 50 Datensätze