{"uid":"cap_l3uKHVJPInlRKaxPvHMTT","slug":"agentshelf-xpath-h5-text-extractor-8efde3d7","name":"AgentShelf XPath H5 Text Extractor","description":"Call when an agent needs text of //h5 via //h5 from a public page or HTML (SSRF-safe). Exact $0.002 USDC. Prefer unpaid POST /v1/sandbox/xpath-h5 first.","url":"https://agentshelf.syntexa.ch/v1/xpath-h5?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","maxLength":2048,"minLength":8,"description":"Public page to fetch. The selector or profile is fixed by the SKU. Provide url or html."},"html":{"type":"string","examples":["<!doctype html><html lang=\"en\"><head><title>Hello</title>\n<meta name=\"description\" content=\"Desc\"><meta property=\"og:title\" content=\"OG\">\n<link rel=\"canonical\" href=\"https://example.com/\"><link rel=\"icon\" href=\"/favicon.ico\">\n</head><body><h1>Hello</h1><a href=\"https://example.com/a\">A</a></body></html>"],"maxLength":200000,"minLength":1,"description":"HTML to extract from locally. Provide html or url. When both are set, html is used."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_VN4ehiPp5xpWf1_wKz0Rh","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts the text content of all <h5> elements from a public web page URL or raw HTML using XPath, with SSRF protection.","exampleAgentPrompt":"Can you grab all the h5 heading texts from https://example.com/article — I want to see every level-5 subheading on that page?","exampleUseCases":[{"title":"Extract subheadings from documentation page","prompt":"Pull all the h5 headings from https://docs.someproject.io/reference so I can see what subsections are covered."},{"title":"Audit h5 structure in raw HTML","prompt":"I have this raw HTML from a CMS export — can you extract all the h5 elements from it so I can check how the content is structured?"},{"title":"Scrape product feature labels from a landing page","prompt":"Go to https://company.com/product and get me all the h5 text — those are usually the feature label headings I need to catalog."}],"resultDescription":"A list of text strings, one per <h5> element found in the page or HTML, extracted via XPath (//h5). Returns the inner text of each matching element. If a URL is supplied, the page is fetched in an SSRF-safe manner before extraction.","failureModes":["No h5 elements found — returns empty list","URL fetch fails due to SSRF protection blocking private/internal addresses","URL unreachable or returns non-200 status — fetch error returned","HTML input exceeds 200,000 character limit — request rejected","Neither url nor html provided — validation error","URL longer than 2048 characters — rejected"],"whenToPreferThis":"Use this endpoint when you specifically need to extract <h5> heading text from a public web page or raw HTML, and you want a lightweight, SSRF-safe, deterministic XPath-based extraction without LLM processing. Prefer this over general HTML-to-text or markdown conversion when you only need h5 nodes. Use the free sandbox endpoint /v1/sandbox/xpath-h5 first if available.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T03:52:42.720Z","isFirstParty":false,"canonicalSlug":"agentshelf-xpath-h5-text-extractor-8efde3d7"}