{"uid":"cap_R-UP1sII0KEY0UB-So1vp","slug":"diffbot-article-extraction-via-locus-x402-37320737","name":"Diffbot Article Extraction via Locus x402","description":"Web data extraction — articles, products, discussions, images, videos, and auto-detect.","url":"https://diffbot.x402.paywithlocus.com/diffbot/article?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string"},"fields":{"type":"string"},"paging":{"type":"boolean"},"maxTags":{"type":"number"},"timeout":{"type":"number"},"discussion":{"type":"boolean"},"naturalLanguage":{"type":"string"}}},"responseSchema":{"type":"json","example":{"data":{},"payment":{"scheme":"exact","settledUsdc":"0.001000","authorizedMaxUsdc":"0.001000"},"request":{"id":"00000000-0000-4000-8000-000000000000","statusUrl":"/requests/00000000-0000-4000-8000-000000000000"},"success":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0042","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":"$0.0042/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0042","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0042","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_dmU56zTLYC2ycHIRPVRlJ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0042","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured article data (title, author, text, tags, comments, NLP features) from any article URL using Diffbot's AI-powered parser, paid per-call via x402/USDC.","exampleAgentPrompt":"Can you extract the full text, author, publish date, and up to 15 tags from this article — https://www.nytimes.com/2024/05/01/technology/ai-regulation.html — and also run sentiment and entity NLP on it?","exampleUseCases":[{"title":"News article structured data extraction","prompt":"Pull the full article text, author name, and publication date from https://www.bbc.com/news/world-us-canada-68942817, and return up to 20 tags with sentiment and a summary."},{"title":"Blog post comment thread mining","prompt":"Extract the article body and all the reader comments from https://techcrunch.com/2024/04/22/openai-gpt-5-preview/ — I want to see what people are saying in the discussion section."},{"title":"Multi-page investigative article ingestion","prompt":"Grab the full text of this multi-page article — https://www.propublica.org/article/supreme-court-clarence-thomas-harlan-crow — combining all pages into one document, and run entity and facts NLP on it."}],"resultDescription":"Returns a JSON object with structured article fields including title, author, date, full text, tags, linked images, and optionally discussion/comments threads and NLP-derived fields such as named entities, sentiment score, summary, facts, and categories. Also includes payment settlement details (USDC amount settled) and a request ID for status tracking.","failureModes":["URL is paywalled or requires login — Diffbot may return partial or empty content","URL is not an article page — parser may misclassify or return sparse data","Timeout exceeded (default 30000ms) for slow or large pages — returns timeout error","Invalid or malformed URL — returns error with no data","NLP naturalLanguage parameter contains unsupported feature names — ignored or error returned","Payment failure via x402 — request not processed if USDC authorization fails"],"whenToPreferThis":"Choose this endpoint when you need clean, structured article data (author, date, body text, tags, NLP features) from a specific article URL without building your own scraper. It is ideal for agents that process news, research, or blog content at scale and need per-call micropayment billing via USDC x402 rather than a subscription. Prefer it over generic HTML fetchers when you need Diffbot's AI layout detection, multi-page concatenation, or built-in NLP (entities, sentiment, summary).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T00:30:58.311Z","isFirstParty":false,"canonicalSlug":"diffbot-article-extraction-via-locus-x402-37320737"}