{"uid":"cap_HtqS8yr7gCG3kx7VvshKi","slug":"diffbot-article-6a01bd1d","name":"Diffbot Article Extraction","description":"Extract clean article text, author, date, images, tags, and sentiment from news/blog pages.","url":"https://diffbot.mpp.paywithlocus.com/diffbot/article?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"URL of the article page"},"fields":{"type":"string","description":"Comma-separated extra fields to return (e.g. links, meta, breadcrumb)"},"paging":{"type":"boolean","description":"Concatenate multi-page articles"},"maxTags":{"type":"number","description":"Max tags to return (default 10)"},"timeout":{"type":"number","description":"Request timeout in ms (default 30000)"},"discussion":{"type":"boolean","description":"Extract comments/discussion threads (default true for article)"},"naturalLanguage":{"type":"string","description":"NLP features to apply (e.g. entities, sentiment, summary, facts, categories)"}},"additionalProperties":true},"responseSchema":null,"example":{"request":{"url":"https://www.bbc.com/news/world","fields":"links,meta,breadcrumb","paging":true,"maxTags":10,"timeout":30000,"discussion":true,"naturalLanguage":"entities,sentiment"},"response":{"data":{"objects":[{"icon":"https://static.files.bbci.co.uk/bbcdotcom/web/20260527-122213-f92e6ec078-web-3.7.0-4/apple-touch-icon.png","meta":{"og":{"og:title":"World | Latest News & Updates | BBC News","og:description":"Get all the latest news, live updates and content about the World from across the BBC."},"title":"World | Latest News & Updates | BBC News","robots":"NOODP, NOYDIR","twitter":{"twitter:title":"World | Latest News & Updates | BBC News","twitter:description":"Get all the latest news, live updates and content about the World from across the BBC."},"version":"web-3.7.0-4","viewport":"width=device-width","microdata":{"items":[],"json-ld":[{"url":"https://www.bbc.com/news/world","name":"World | Latest News & Updates | BBC News","@type":"WebPage","@context":"https://schema.org","publisher":{"logo":"https://m.files.bbci.co.uk/modules/bbc-morph-news-waf-page-meta/5.3.0/bbc_news_logo.png","name":"BBC News","@type":"NewsMediaOrganization","sameAs":["https://www.facebook.com/BBCGlobalFB/","https://twitter.com/bbc","https://www.instagram.com/bbcglobal/","https://www.youtube.com/@BBC_Global"],"publishingPrinciples":"https://www.bbc.co.uk/news/help-41670342"},"description":"Get all the latest news, live updates and content about the World from across the BBC.","mainEntityOfPage":"https://www.bbc.com/news/world"}]},"al:ios:url":"bbcx://news/world","al:web:url":"https://bbc.com/news/world","description":"Get all the latest news, live updates and content about the World from across the BBC.","theme-color":"#ffffff","page.section":"News","canonical-url":"https://www.bbc.com/news/world","al:android:url":"bbcx://news/world","al:ios:app_name":"BBC: World News & Stories","page.subsection":"World","apple-itunes-app":"app-id=364147881, app-argument=https://www.bbc.com/news/world","al:android:package":"bbc.mobile.news.ww","al:android:app_name":"BBC: World News & Stories","al:ios:app_store_id":"364147881","cXenseParse:pageclass":"frontpage","msapplication-TileColor":"#da532c"},"text":"","type":"article","links":["https://www.bbc.com/watch-live-news/","https://www.bbc.com/","https://session.bbc.com/session?userOrigin=BBCS_BBC&ptrt=https%3A%2F%2Fwww.bbc.com%2Fnews%2Fworld","https://www.bbc.com/news","https://www.bbc.com/sport","https://www.bbc.com/business","https://www.bbc.com/technology","https://www.bbc.com/health","https://www.bbc.com/culture","https://www.bbc.com/arts","https://www.bbc.com/travel","https://www.bbc.com/future-planet","https://www.bbc.com/audio","https://www.bbc.com/video","https://www.bbc.com/live","https://www.bbc.com/video/docs","https://www.bbc.com/home","https://www.bbc.com/news/us-canada","https://www.bbc.com/news/uk","https://www.bbc.com/news/politics","https://www.bbc.com/news/england","https://www.bbc.com/news/northern_ireland","https://www.bbc.com/news/northern_ireland/northern_ireland_politics","https://www.bbc.com/news/scotland","https://www.bbc.com/news/scotland/scotland_politics","https://www.bbc.com/news/wales","https://www.bbc.com/news/wales/wales_politics","https://www.bbc.com/news/world/africa","https://www.bbc.com/news/world/asia","https://www.bbc.com/news/world/asia/china","https://www.bbc.com/news/world/asia/india","https://www.bbc.com/news/world/australia","https://www.bbc.com/news/world/europe","https://www.bbc.com/news/world/latin_america","https://www.bbc.com/news/world/middle_east","https://www.bbc.com/news/in_pictures","https://www.bbc.com/news/bbcindepth","https://www.bbc.com/news/bbcverify","https://www.bbc.com/business/world-of-business","https://www.bbc.com/business/technology-of-business","https://www.bbc.com/business/opening-bell","https://www.bbc.com/video/docs/category/technology","https://www.bbc.com/technology/artificial-intelligence","https://www.bbc.com/technology/intelligence-revolution","https://www.bbc.com/technology/ai-v-the-mind","https://www.bbc.com/technology/tech-now","https://www.bbc.com/video/docs/category/health","https://www.bbc.com/video/docs/category/culture","https://www.bbc.com/culture/film-tv","https://www.bbc.com/culture/music","https://www.bbc.com/culture/art","https://www.bbc.com/culture/style","https://www.bbc.com/culture/books","https://www.bbc.com/culture/entertainment-news","https://www.bbc.com/video/docs/category/arts","https://www.bbc.com/arts/arts-in-motion","https://www.bbc.com/video/docs/category/travel","https://www.bbc.com/travel/destinations","https://www.bbc.com/travel/destinations/africa","https://www.bbc.com/travel/destinations/antarctica","https://www.bbc.com/travel/destinations/asia","https://www.bbc.com/travel/destinations/australia-and-pacific","https://www.bbc.com/travel/destinations/caribbean","https://www.bbc.com/travel/destinations/central-america","https://www.bbc.com/travel/destinations/europe","https://www.bbc.com/travel/destinations/middle-east","https://www.bbc.com/travel/destinations/north-america","https://www.bbc.com/travel/destinations/south-america","https://www.bbc.com/travel/worlds-table","https://www.bbc.com/travel/cultural-experiences","https://www.bbc.com/travel/adventures","https://www.bbc.com/travel/specialist","https://www.bbc.com/video/docs/category/earth","https://www.bbc.com/innovation/science","https://www.bbc.com/future-planet/natural-wonders","https://www.bbc.com/future-planet/solutions","https://www.bbc.com/future-planet/sustainable-business","https://www.bbc.com/future-planet/green-living","https://www.bbc.com/audio/categories","https://www.bbc.com/audio/stations","https://www.bbc.com/undefined","https://www.bbc.com/video/bbc-maestro","https://www.bbc.com/video/discover-the-world","https://www.bbc.com/live/news","https://www.bbc.com/live/sport"],"title":"World","pageUrl":"https://www.bbc.com/news/world","siteName":"BBC","sentiment":0.51,"diffbotUri":"article|3|83766130","shareLinks":false,"humanLanguage":"en","naturalLanguage":{"entities":[],"sentiment":0.5095801},"publisherRegion":"Northern Europe","publisherCountry":"United Kingdom"}],"request":{"api":"article","fields":"links,meta,breadcrumb","options":["discussion=true","maxTags=10","naturalLanguage=entities,sentiment","paging=true","timeout=30000"],"pageUrl":"https://www.bbc.com/news/world","version":3}},"success":true}},"exampleRequest":{"url":"https://www.bbc.com/news/world","fields":"links,meta,breadcrumb","paging":true,"maxTags":10,"timeout":30000,"discussion":true,"naturalLanguage":"entities,sentiment"},"tags":["web-scraping","extraction","articles","products","web","data"],"displayCostAmount":"0.0042","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"1.00","reviews":0,"stars":null,"state":"rated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.0042/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.0042","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.0042","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ew7F1-MXnsviD0y6V5k-j","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.0042","costPer":"request","priority":0,"asset":"0x20c000000000000000000000b9537d11c60e8b50","unit":"request","depositMicros":null,"planRef":null}],"brandName":"Diffbot","brandSlug":"diffbot","brandBaseUrl":"https://www.diffbot.com","brandDocsUrl":"https://docs.diffbot.com","whatItDoes":"Extracts structured article content (title, text, author, date, tags, comments) from any article URL using Diffbot's AI parsing","exampleAgentPrompt":"Pull the full article from https://www.nytimes.com/2024/01/15/technology/ai-regulation.html — extract the title, author, publish date, body text, and up to 15 tags, and also run NLP to get entities and sentiment.","exampleUseCases":null,"resultDescription":"Returns a structured JSON object containing the parsed article's title, full text content, author name(s), publication date, primary image, tags (up to maxTags), NLP-derived entities/sentiment/summary if requested, and optionally comment threads — all extracted cleanly from the raw HTML of the given URL.","failureModes":["URL is behind a hard paywall or login wall — returns empty or partial content","URL is not an article page — returns low-confidence or mismatched content","Timeout exceeded for slow-loading pages — returns timeout error","Invalid or unreachable URL — returns HTTP error or connection failure","Multi-page article not fully concatenated if paging param not set","NLP features not available for non-English content"],"whenToPreferThis":"Use this endpoint when you need to extract structured data specifically from article or news pages, including NLP enrichment like entities, sentiment, and summaries. Prefer this over the generic Analyze endpoint when you know the page is an article. Choose it over manual HTML parsing when you need clean, normalized fields like author, publish date, and body text without boilerplate.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":1,"lastUsedAt":"2026-05-10T15:29:15.488Z","lastSuccessfullyRanAt":"2026-05-10T15:29:15.488Z","lastHealthCheckAt":"2026-10-11T18:33:29.120Z","isFirstParty":false,"canonicalSlug":"diffbot-article-6a01bd1d"}