{"uid":"cap_YHfjgQ7mNYFISwZ2KlZX5","slug":"crawlspur-x-robots-tag-checker-for-news-documents-f11f4a47","name":"Crawlspur X-Robots-Tag Checker for News Documents","description":"Prüft am Objekt news-dokument den Befund Wert des X-Robots-Tags.","url":"https://crawlspur.halowerk.com/v1/pruef/crawlspur/x-robots/news-dokument","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"ziel":{"oneOf":[{"type":"string","maxLength":2048,"minLength":1,"description":"Öffentliche HTTP(S)-Adresse; bei DNS-Befunden Domain oder öffentliche IP."},{"type":"object","required":["adresse"],"properties":{"adresse":{"type":"string","maxLength":2048,"minLength":1},"selektor":{"type":"string","maxLength":240,"minLength":1,"description":"CSS-Selektor: genau ein Objekt, sonst erster Treffer des Objektfilters."},"vergleich":{"type":"string","maxLength":2048,"description":"Öffentliche Vergleichsadresse für Link-, Sitemap- oder Sprachbefunde."},"user_agent":{"type":"string","pattern":"^[A-Za-z0-9_-]{1,80}$"},"dkim_selektor":{"type":"string","pattern":"^[A-Za-z0-9_-]{1,63}$"}},"additionalProperties":false}]}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm__IFVcxw5hjE0UMAcvO52J","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Checks the X-Robots-Tag HTTP header value on a news document URL and returns the crawl/indexing directive found.","exampleAgentPrompt":"Check the X-Robots-Tag HTTP header on this news article and tell me what crawl directive it returns: https://www.example-news.com/2024/01/breaking-story.html","exampleUseCases":[{"title":"News article indexability audit","prompt":"I need to check whether our latest news article at https://news.mysite.com/2024/05/article.html is being blocked from Google News by the X-Robots-Tag — can you inspect the header and tell me what value it returns?"},{"title":"Diagnosing missing news from Google News","prompt":"Our news story at https://publisher.example.com/politics/story-123.html isn't showing up in Google News. Can you check whether the X-Robots-Tag header on that page has a noindex or unavailable_after directive?"},{"title":"Pre-publish SEO header validation","prompt":"Before we push this article live at https://beta.newsroom.example.com/preview/story-456.html, can you verify that the X-Robots-Tag header isn't accidentally set to noindex or noodp?"}],"resultDescription":"Returns the value of the X-Robots-Tag HTTP response header found on the specified news document, indicating any crawl or indexing directives (e.g. noindex, nofollow, none, unavailable_after) that search engine bots would receive when visiting the page.","failureModes":["Target URL is not publicly accessible or returns a non-200 HTTP status","URL does not point to a news document, returning unexpected content type","X-Robots-Tag header is absent on the response (may return empty or null result)","URL exceeds maximum length of 2048 characters","Network timeout or DNS resolution failure for the target address","Invalid input schema (missing required 'ziel' field)"],"whenToPreferThis":"Use this endpoint when you specifically need to inspect the X-Robots-Tag HTTP header on a news document — distinct from meta robots tags or robots.txt directives. Prefer this over generic HTTP header tools when the target is a news page and you need a structured, SEO-focused interpretation of the X-Robots-Tag value. Choose this over the sibling 'bild' (image) or 'robots-datei' endpoints when the object type is specifically a news article or news document URL.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:59:29.779Z","isFirstParty":false}