{"uid":"cap_C8weR0-l_aUmNdWrouazV","slug":"johto-data-api-web-crawler-fed8079a","name":"Johto Data API - Web Crawler","description":"Valuable data. Quality leads. Paid per call in USDC on Base via x402. Not charged if the fetch fails or nothing matches. Prices per call (USDC): /v1/jp-invoice-check $0.002; /v1/sec-13f $0.003; /v1/sec-8k $0.003; /v1/sanctions-screen $0.0025; /v1/tenders $0.011; /v1/uk-tenders $0.003; /v1/fr-tenders $0.006; /v1/au-contracts $0.0035; /v1/wallet-risk $0.0025; /v1/kyb $0.0029; /v1/read $0.0019; /v1/crawl $0.0045; /v1/jobs $0.01; /v1/domain-profile $0.003.","url":"https://johto-x402-api.johtodata.workers.dev/v1/crawl?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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","required":["url"],"properties":{"url":{"type":"string","pattern":"^https?://\\S+$","description":"Start URL, http(s). Only pages under it are crawled."},"pages":{"type":"string","pattern":"^([1-9]|1[0-9]|20)$","description":"Max pages, 1-20 (default 20)"},"max_chars":{"type":"string","pattern":"^[0-9]{3,5}$","description":"Max Markdown characters per page, 500-20000 (default 20000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["data","rows"],"properties":{"data":{"type":"array","items":{"type":"object","properties":{"url":{"type":"string"},"depth":{"type":"integer"},"title":{"type":"string"},"status":{"type":"integer"},"loadedAt":{"type":"string"},"markdown":{"type":"string"},"truncated":{"type":"boolean"},"contentHash":{"type":"string"},"description":{},"tokensEstimate":{"type":"integer"}}}},"rows":{"type":"integer"}}}}}}},"responseSchema":{"type":"json","example":{"data":[{"url":"https://crawlee.dev/python/docs/examples/beautifulsoup-crawler.md","depth":1,"title":"BeautifulSoup crawler","status":200,"loadedAt":"2026-10-22T08:54:44Z","markdown":"* [](https://crawlee.dev/python/python)\n* [Examples](https://crawlee.dev/python/ ...","truncated":true,"contentHash":"fc2f086388e350bc","description":null,"tokensEstimate":1504}],"rows":1}},"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_MNY2UBmdjf9OX2m7FxR32","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":"Crawls a website starting from a given URL and returns the content of up to 20 pages as Markdown, with metadata per page","exampleAgentPrompt":"Crawl the site at https://docs.example.com starting from the homepage, grab up to 10 pages, and give me each page's content as Markdown so I can use it for RAG.","exampleUseCases":[{"title":"Documentation ingestion for RAG pipeline","prompt":"Crawl https://crawlee.dev/python/docs up to 15 pages and return the Markdown content of each page so I can feed it into my vector database."},{"title":"Competitor website content analysis","prompt":"Scrape the website at https://www.competitor.com — up to 20 pages — and return all the page text as Markdown so I can analyze what they're saying about their product."},{"title":"Lead research from company site","prompt":"Fetch the content from https://www.acmecorp.com, crawl up to 5 pages, and give me the Markdown text so I can extract contact info and understand what the company does."}],"resultDescription":"A JSON array of page objects, each containing the page URL, crawl depth, title, HTTP status code, load timestamp, full Markdown content (possibly truncated), a content hash, a description field, and an estimated token count. Also includes a top-level 'rows' count indicating how many pages were returned.","failureModes":["URL is unreachable or returns non-200 status — no charge applied","URL pattern does not start with http/https — rejected by schema validation","pages parameter outside 1-20 range — rejected","max_chars outside 500-20000 range — rejected","Site blocks crawlers (robots.txt, bot detection) — may return empty or partial results","Payment failure via x402 — request not fulfilled"],"whenToPreferThis":"Choose this endpoint when you need to crawl multiple pages of a website (up to 20) and receive structured Markdown output per page, especially for LLM ingestion, RAG pipelines, or competitive intelligence. It is pay-per-call with no charge on failure, making it cost-safe for exploratory crawls. Prefer over single-page scrapers when you need to follow links within a site automatically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T06:32:02.832Z","isFirstParty":false,"canonicalSlug":"johto-data-api-web-crawler-fed8079a"}