{"uid":"cap_OkIknZqK2JcWBZp7VlCKN","slug":"dopaminedesk-deep-scrape-http-page-fetcher-83ed7eb4","name":"DopamineDesk Deep Scrape – HTTP Page Fetcher","description":"Fetch a public HTTP(S) page with private-network blocking and return bounded Markdown-like content plus title, description, Open Graph image, status, and URL metadata.","url":"https://ai-data-marketplace-1042299154756.us-central1.run.app/api/v1/deep_scrape","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":["url"],"properties":{"url":{"type":"string","description":"Public HTTP(S) URL to fetch. The page is fetched directly, not rendered in a browser, so JavaScript-generated content is not captured."}},"additionalProperties":true}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["success","source","fetched_at","url","status_code","title","description","og_image","truncated","markdown","marketplace_metadata"],"properties":{"url":{"type":"string"},"title":{"type":"string"},"source":{"type":"string"},"success":{"type":"boolean"},"markdown":{"type":"string"},"og_image":{"type":"null"},"truncated":{"type":"boolean"},"fetched_at":{"type":"string"},"description":{"type":"null"},"status_code":{"type":"integer"},"marketplace_metadata":{"type":"object","required":["data_mode","billable","availability","source"],"properties":{"source":{"type":"string"},"billable":{"type":"boolean"},"data_mode":{"type":"string"},"availability":{"type":"string"}},"additionalProperties":true}},"additionalProperties":true}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","title":"Example Domain","source":"live public web fetch","success":true,"markdown":"Example Domain\n# Example Domain\nThis domain is for use in documentation examples without needing permission. Avoid use in operations.\nLearn more","og_image":null,"truncated":false,"fetched_at":"2026-08-07T07:32:39.175Z","description":null,"status_code":200,"marketplace_metadata":{"source":"live public web fetch","billable":true,"data_mode":"live_source","availability":"operational"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Buki8ZMnXgtUQECwbrWJe","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches the raw HTML and extracted text of any public HTTP(S) URL, returning page content, load time, and cleaned text — without JavaScript rendering.","exampleAgentPrompt":"Fetch the content of https://example-saas.com/pricing and pull out all the visible text — I need to see what plans and prices they list.","exampleUseCases":[{"title":"Competitor pricing intelligence","prompt":"Go to https://competitor.com/pricing and scrape the page — I want the full extracted text so I can see all their plan names and prices."},{"title":"News article text extraction","prompt":"Fetch the article at https://techcrunch.com/2024/05/01/some-article and give me the cleaned text so I can summarize it."},{"title":"Job listing content pull","prompt":"Scrape https://careers.company.com/jobs/12345 and return the visible text from the page — I need the full job description."}],"resultDescription":"Returns a JSON object containing the original URL, the full raw HTML of the fetched page, load time in milliseconds, and the extracted visible text content stripped of HTML markup.","failureModes":["URL is not publicly accessible or requires authentication — returns an error or empty content","URL points to a JavaScript-heavy single-page app — JS-rendered content will be missing since no browser is used","Page returns a non-200 HTTP status (404, 500, etc.) — error reflected in response","Network timeout if the target server is slow or unreachable","URL is malformed or missing scheme — schema validation error"],"whenToPreferThis":"Use this endpoint when you need raw HTML or extracted text from a static or server-rendered public web page and do not require JavaScript execution. It is ideal for scraping pricing pages, documentation, news articles, job listings, or any content delivered in the initial HTML response. Prefer this over browser-based scraping when speed matters and the page content does not depend on client-side JavaScript rendering.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:47:27.894Z","isFirstParty":false}