{"uid":"cap_YDytHBQL-hvbwaGPGpqLQ","slug":"web-scraper-api-metadata-extraction-9e6a5eb7","name":"Web Scraper API – Metadata Extraction","description":"HTML scraping (text, links, metadata, structured) with x402 payments and MCP server.","url":"https://scrape.payapi.market/scrape/metadata?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"Absolute http(s) URL of the page to scrape, e.g. 'https://example.com'."}}},"responseSchema":{"type":"json","example":{"url":"https://example.com","title":"Example Domain","author":null,"favicon":"https://example.com/favicon.ico","twitter":{"card":"summary_large_image","site":"@example","image":"https://example.com/tw.png","title":"Example Domain","creator":"@example","description":"Illustrative example domain."},"keywords":null,"language":"en","modified":"2024-02-01T12:30:00Z","canonical":"https://example.com/","final_url":"https://example.com/","published":"2024-01-15T09:00:00Z","open_graph":{"url":"https://example.com/","type":"website","image":"https://example.com/og.png","title":"Example Domain","site_name":"Example","description":"Illustrative example domain."},"description":"Illustrative example domain reserved for use in documentation."}},"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_ROu8geZ9F0f8tRLFsJhdd","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":"Scrapes a webpage and returns structured metadata including title, description, Open Graph tags, Twitter card data, author, language, canonical URL, and publication dates.","exampleAgentPrompt":"Can you pull the metadata from https://techcrunch.com/2024/03/15/openai-raises-new-funding/ — I need the title, description, Open Graph tags, author, and published date?","exampleUseCases":[{"title":"SEO audit of competitor pages","prompt":"Grab the metadata from https://www.hubspot.com/products/marketing — I want to see their page title, meta description, Open Graph image, and canonical URL so I can compare it against ours."},{"title":"Article enrichment for content pipeline","prompt":"I'm ingesting articles into my content database — can you fetch the structured metadata for https://www.nytimes.com/2024/04/01/technology/ai-regulation.html, especially the author, published date, and description?"},{"title":"Link preview card generation","prompt":"I need to build a link preview for this URL: https://github.com/openai/whisper — can you get me the title, description, favicon, and any Open Graph or Twitter card image from that page?"}],"resultDescription":"Returns a JSON object containing the scraped page's URL, final resolved URL, canonical URL, title, meta description, author, language, published and modified timestamps, keywords, favicon URL, and fully parsed Open Graph and Twitter card objects (including image, site name, card type, creator handle, and per-field content).","failureModes":["URL is unreachable or returns a non-200 HTTP status — metadata fields will be null or the request may error","Page blocks scraping bots via robots.txt or JS challenges — may return empty or partial metadata","Malformed or missing meta tags on the target page — relevant fields will be null","Payment failure via x402 protocol — request will not be processed","Invalid or non-HTTP(S) URL provided — request will be rejected"],"whenToPreferThis":"Choose this endpoint when you need structured page metadata (title, description, Open Graph, Twitter cards, dates, author, language) from a single URL quickly and cheaply at $0.002 per call, especially in agentic pipelines that require link previews, SEO audits, or article enrichment. Prefer this over full HTML scraping endpoints when you only need header-level metadata rather than full page text or link extraction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T08:05:22.896Z","isFirstParty":false,"canonicalSlug":"web-scraper-api-metadata-extraction-9e6a5eb7"}