{"uid":"cap_kAhifZZf0iWP9rqO9HqB1","slug":"dopaminedesk-web-scrape-to-markdown-5df94acc","name":"DopamineDesk Web Scrape to Markdown","description":"Fetch a public HTTP(S) page with private-network blocking, remove boilerplate tags, and return bounded Markdown-like text.","url":"https://ai-data-marketplace-1042299154756.us-central1.run.app/api/v1/scrape_md","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":"The target URL to scrape."},"timeout_ms":{"type":"integer","description":"Request timeout in milliseconds."}},"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","truncated","markdown","marketplace_metadata"],"properties":{"url":{"type":"string"},"title":{"type":"string"},"source":{"type":"string"},"success":{"type":"boolean"},"markdown":{"type":"string"},"truncated":{"type":"boolean"},"fetched_at":{"type":"string"},"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","truncated":false,"fetched_at":"2026-08-07T07:32:38.884Z","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":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_eKoL-7UeFubI-REWFwMDQ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL and returns its main content converted to clean Markdown, including title and content length metadata.","exampleAgentPrompt":"Can you scrape the article at https://example.com/article/tech-news and give me the content as clean markdown? Use a 10000ms timeout.","exampleUseCases":[{"title":"Extract article text for summarization","prompt":"Grab the full text of this news article at https://techcrunch.com/2024/01/15/ai-breakthrough/ as markdown so I can summarize it — use a 15000ms timeout."},{"title":"Read competitor product page","prompt":"Scrape the product page at https://competitor.com/pricing and return the content as markdown so I can analyze what they're offering."},{"title":"Convert documentation page for offline use","prompt":"Fetch the content of https://docs.someproject.org/getting-started and convert it to markdown for me, with a 20000ms timeout."}],"resultDescription":"A JSON object containing the original URL, the extracted page title, a success/failure status string, the full page content converted to clean Markdown, and the content length in characters.","failureModes":["Target URL is unreachable or returns a non-200 status — status field will reflect failure","Timeout exceeded (timeout_ms too low for slow pages) — request aborted","URL is blocked by anti-scraping measures (CAPTCHAs, bot detection) — may return empty or partial markdown","Invalid URL format — likely returns a validation error","JavaScript-heavy single-page apps may return incomplete content if JS is not rendered"],"whenToPreferThis":"Choose this endpoint when you need to extract readable, structured Markdown content from a public web page quickly and cheaply ($0.003/call via USDC x402). It is ideal for agents that need to read articles, documentation, or product pages without dealing with raw HTML. Prefer it over browser-automation alternatives when page content is server-rendered and low-latency conversion to Markdown is sufficient.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:46:58.586Z","isFirstParty":false}