{"uid":"cap_sxyatHRDiy4NntFryBJE5","slug":"eudata402-structured-field-extraction-from-text-html-f8e1b01c","name":"eudata402 Structured Field Extraction from Text/HTML","description":"Structured JSON extraction from messy text/HTML. POST {text, fields[]}. Returns {data}.","url":"https://x402-seller-202595743428.europe-west1.run.app/extract","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","description":"Source text or HTML (max 24k chars)"},"fields":{"type":"array","items":{"type":"string"},"description":"Field names to extract (max 30)"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bn-EcQkQdKN1G-QylvCu6","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts specified named fields as structured JSON from unstructured text or HTML input","exampleAgentPrompt":"Extract the fields 'company_name', 'address', 'phone', and 'founding_year' from this HTML snippet I'm pasting — return them as a clean JSON object.","exampleUseCases":[{"title":"Parse job listing into structured record","prompt":"Take this raw HTML from a job posting and extract the fields 'job_title', 'salary_range', 'location', 'company', and 'required_skills' into a structured JSON object."},{"title":"Extract invoice data from email body","prompt":"Here's the text body of an invoice email — can you pull out 'invoice_number', 'due_date', 'total_amount', 'vendor_name', and 'line_items' as structured JSON?"},{"title":"Structure product info from scraped page","prompt":"I scraped this messy HTML from a product page — extract 'product_name', 'price', 'availability', 'sku', and 'description' from it and give me clean JSON."}],"resultDescription":"Returns a JSON object with a 'data' key containing the extracted values mapped to each requested field name. Values are drawn directly from the input text/HTML using semantic understanding of field names.","failureModes":["Input text exceeds 24,000 character limit — request will be rejected or truncated","More than 30 fields requested — may return error or partial results","Field names are ambiguous and cannot be matched to content — fields may return null or empty","Malformed HTML that cannot be parsed — extraction quality degrades","Payment not included or insufficient — 402 Payment Required response","Field genuinely not present in source text — returns null or absent key"],"whenToPreferThis":"Choose this endpoint when you need to pull multiple named fields from a single block of unstructured or semi-structured text or HTML in one call, especially when the source is messy or inconsistent. It is well-suited for agentic pipelines doing web scraping, document ingestion, or email parsing where you know the schema you want but the source lacks it. Prefer it over regex or manual parsing when field positions vary, and over a full summarization endpoint when you need specific discrete values rather than a narrative summary.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:33:26.583Z","isFirstParty":false}