{"uid":"cap_V1aH739D-T9ZGSCeDtxNd","slug":"extract-dois-from-web-page-d65ad816","name":"Extract DOIs from Web Page","description":"Extract dois from a web page: fetches the URL and returns every dois found in the page text and markup (deduplicated, with counts and up to 300 items), so an agent gets the values without parsing HTML. $0.01 per page.","url":"https://page.intel.rallylive.ca/page/extract/dois?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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","properties":{}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"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_bTTboomhVlexsC1GFOv5i","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 a web page URL and extracts all Digital Object Identifiers (DOIs) found in the page text and markup, returning deduplicated results with counts (up to 300 items).","exampleAgentPrompt":"Pull all the DOIs mentioned on this page — https://www.nature.com/articles/s41586-023-06419-4 — and give me the deduplicated list with counts.","exampleUseCases":[{"title":"Audit citations on a journal article","prompt":"Can you fetch https://www.biorxiv.org/content/10.1101/2023.08.01.551548 and extract every DOI that appears on that page? I want to see all the cited works as a deduplicated list."},{"title":"Build reference list from a review paper","prompt":"Go to https://www.annualreviews.org/doi/10.1146/annurev-biodiversity and extract all the DOIs you find on that page — I'm trying to compile a reference database from this review article."},{"title":"Verify DOI coverage on a preprint","prompt":"Check this preprint page at https://arxiv.org/abs/2309.12345 and tell me how many unique DOIs are referenced — I want to know if all the cited papers have proper DOI identifiers."}],"resultDescription":"A deduplicated list of up to 300 DOIs found in the page text and HTML markup, each with an occurrence count indicating how many times it appeared on the page.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may return an error or empty result","Page uses JavaScript rendering and DOIs are loaded dynamically — static fetch may miss JS-rendered content","Page has no DOIs — returns empty list","More than 300 unique DOIs on page — only first 300 returned","Malformed or non-standard DOI formats may not be captured by the regex patterns used"],"whenToPreferThis":"Choose this endpoint when you need to extract DOIs specifically from a web page without writing custom HTML parsing logic. It is ideal for academic research workflows, citation auditing, and bibliography compilation where the target page is a standard HTML document containing DOI strings or links. Prefer this over general-purpose scrapers when you only care about DOI identifiers and want a clean, deduplicated output at low cost ($0.01 per page).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T18:57:02.759Z","isFirstParty":false,"canonicalSlug":"extract-dois-from-web-page-d65ad816"}