{"uid":"cap__yGo3JEa8ADQo5Nz9L27X","slug":"web-page-contents-extractor-f3a78b44","name":"Web Page Contents Extractor","description":"Page contents API (urls or ids, text.maxCharacters), pay per request: clean text, title, author and date of up to 5 pages in one call. No account or API key; failed calls are not charged.","url":"https://agent-data-tools.revmesh2074.workers.dev/v1/contents?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["urls"],"properties":{"urls":{"type":"string","examples":["https://example.com,https://www.iana.org/help/example-domains"],"description":"One to five page URLs: comma-separated, one per line, or a JSON array"},"format":{"type":"string","examples":["text"],"description":"text (default) or markdown"},"maxChars":{"type":"string","examples":["3000"],"description":"Characters per page, 500 to 20000 (default 4000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"read":{"type":"number"},"results":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"url":{"type":"string"},"lang":{"type":"string"},"text":{"type":"string"},"title":{"type":"string"},"author":{},"truncated":{"type":"boolean"},"textLength":{"type":"number"},"publishedDate":{}}}},"statuses":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"status":{"type":"string"}}}},"requested":{"type":"number"}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_xpmiXe9npZMJvavhpfkJ3","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches clean text, title, author, and publication date from up to 5 URLs in a single call","exampleAgentPrompt":"Can you fetch the clean readable text from these three pages for me: https://example.com/article1, https://example.com/article2, and https://example.com/article3 — keep each one under 3000 characters and return it as plain text?","exampleUseCases":[{"title":"Research article summarization pipeline","prompt":"Pull the full text from these two news articles and give me the titles, authors, and publish dates along with the content: https://techcrunch.com/some-article and https://wired.com/another-article — limit each to 5000 characters of plain text."},{"title":"Fact-checking a web claim","prompt":"Fetch the readable content from this URL so I can verify what it actually says: https://somesite.com/claim-page — just the clean text, up to 4000 characters, no markdown needed."},{"title":"Competitive intelligence content pull","prompt":"Get me the clean text, title, and author from up to five of our competitor blog posts in one shot: https://competitor1.com/blog/post-a, https://competitor2.com/blog/post-b, https://competitor3.com/blog/post-c — plain text format, 2000 characters max each."}],"resultDescription":"Returns a results array where each entry contains the page URL, extracted clean text (up to the requested character limit), page title, author, language code, published date, and a truncated flag. Also returns counts of how many pages were requested and successfully read, plus a statuses array with per-URL success or failure status.","failureModes":["URL is unreachable or returns a non-200 HTTP status — that URL appears in statuses with a failure status and is not charged","Page has no extractable text (e.g. pure JavaScript SPA with no server-rendered content) — returns empty or minimal text","Invalid or malformed URL in the urls parameter — rejected at input validation","More than 5 URLs provided — request likely rejected or only first 5 processed","maxChars outside allowed range (500–20000) — may be clamped or rejected"],"whenToPreferThis":"Choose this endpoint when you need clean, reader-friendly text extracted from one to five web pages without dealing with HTML parsing or a browser. It's ideal for article ingestion, summarization pipelines, fact-checking, or any workflow that needs the main textual body of a page plus metadata (title, author, date) without building your own scraper. No API key is required, costs only $0.01 per call for up to 5 URLs, and failed fetches are not charged.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T00:16:59.281Z","isFirstParty":false,"canonicalSlug":"web-page-contents-extractor-f3a78b44"}