{"id":"b9ddc555-208f-46e1-bf47-9458bae8291d","url":"https://netintel.dev/web/extract?url=https%3A%2F%2Fwww.sitemaps.org%2Fprotocol.html","method":"GET","fingerprint":"de1f4c3099d3fab9477edba3f24c54d2057ba62ff45c1176e71cf1630bb6f029","name":"NetIntel","description":"Extract article / main content from any URL or PDF to clean, LLM-ready Markdown (web scraper / reader / html-to-markdown) — strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade so agents can read articles and documents without a browser or paid scraping service.","category":"other","docs_url":null,"advertised_price_usd":"0.003000","asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","scheme":"exact","networks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"pay_to":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","input_schema":{"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 URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)"}}}},"additionalProperties":false},"output_schema":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"grade":{"type":"string"},"score":{"type":"number"},"title":{"type":"string"},"findings":{"type":"array"},"markdown":{"type":"string"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"char_count":{"type":"number"},"word_count":{"type":"number"},"status_code":{"type":"number"},"content_type":{"type":"string","description":"article | pdf | other (non-HTML/PDF falls back to best-effort plain text)"},"output_bytes":{"type":"number"}}}}},"schema_completeness":0,"status":"live","first_seen_at":"2026-08-23 12:14:01.688228+00","last_seen_at":"2026-08-25 09:13:38.343+00","last_success_at":"2026-10-15 11:29:15.584+00","dead_since":null,"probe_backoff_tier":0,"next_probe_at":"2026-10-15 11:34:15.584+00","search_tsv":"'ad':27 'agent':57 'articl':3,60 'block':37 'blockquot':39 'bodi':48 'boilerpl':29 'browser':65 'clean':12 'code':36 'content':5 'count':51 'document':62 'extract':2,40 'grade':55 'head':32 'html':21 'html-to-markdown':20 'layer':43 'link':33 'list':34 'llm':14 'llm-readi':13 'main':4 'markdown':16,23,47 'nav':26 'netintel':1 'paid':67 'pdf':10 'pdfs':45 'preserv':31 'qualiti':54 'read':59 'reader':19 'readi':15 'return':46 'scrape':68 'scraper':18 'script':25 'servic':69 'strip':24 'tabl':35 'text':42 'titl':49 'url':8 'web':17 'without':63 'word':50","catalog_number":"424","x402_version":2,"resource_url":"https://netintel.dev/web/extract","resource_description":"Extract text from a web page or PDF as clean Markdown — HTML to Markdown for any URL: strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade. Web scraper / reader for article and main content. For JS-rendered or bot-walled pages a plain fetch can't read, use /exa/contents.","bazaar_extension":{"info":{"input":{"type":"http","method":"GET","queryParams":{"url":"https://www.sitemaps.org/protocol.html"}},"output":{"type":"json","example":{"url":"https://www.sitemaps.org/protocol.html","grade":"A","score":100,"title":"sitemaps.org - Protocol","findings":[],"markdown":"## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...","final_url":"https://www.sitemaps.org/protocol.html","truncated":false,"char_count":21619,"word_count":2707,"status_code":200,"content_type":"article","output_bytes":21619}}},"schema":{"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 URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"grade":{"type":"string"},"score":{"type":"number"},"title":{"type":"string"},"findings":{"type":"array"},"markdown":{"type":"string"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"char_count":{"type":"number"},"word_count":{"type":"number"},"status_code":{"type":"number"},"content_type":{"type":"string","description":"article | pdf | other (non-HTML/PDF falls back to best-effort plain text)"},"output_bytes":{"type":"number"}}}}}}}},"accepted_requirements":[{"raw":{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","extra":{"name":"USD Coin","version":"2"},"payTo":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","amount":"3000","scheme":"exact","network":"eip155:8453","maxTimeoutSeconds":300},"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","payTo":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","scheme":"exact","network":"eip155:8453","amountAtomic":"3000"},{"raw":{"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","extra":{"feePayer":"BFK9TLC3edb13K6v4YyH3DwPb5DSUpkWvb7XnqCL9b4F"},"payTo":"8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s","amount":"3000","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":300},"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","payTo":"8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","amountAtomic":"3000"}],"bazaar_compatible":true,"bazaar_validated_at":"2026-10-15 11:29:15.584+00","bazaar_validation_error":null,"window":"24h","probes_n":20,"handshake_uptime":1,"settle_success_rate":0,"valid_result_rate":null,"latency_p50":469,"latency_p90":691,"price_drift_pct":0,"score":0.8496,"computed_at":"2026-10-15 11:29:21.923+00","source_metadata":[{"raw":{"url":"https://netintel.dev/web/extract?url=https%3A%2F%2Fwww.sitemaps.org%2Fprotocol.html","name":"NetIntel","method":"GET","source":"bazaar:api.cdp.coinbase.com","fingerprint":"de1f4c3099d3fab9477edba3f24c54d2057ba62ff45c1176e71cf1630bb6f029","inputSchema":{"type":"http","method":"GET","queryParams":{"url":"https://www.sitemaps.org/protocol.html"}},"resourceUrl":"https://netintel.dev/web/extract","serviceName":"NetIntel","x402Version":2,"outputSchema":{"type":"json","example":{"url":"https://www.sitemaps.org/protocol.html","grade":"A","score":100,"title":"sitemaps.org - Protocol","findings":[],"markdown":"## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...","final_url":"https://www.sitemaps.org/protocol.html","truncated":false,"char_count":21619,"word_count":2707,"status_code":200,"content_type":"article","output_bytes":21619}},"acceptedAssets":["0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v"],"bazaarExtension":{"info":{"input":{"type":"http","method":"GET","queryParams":{"url":"https://www.sitemaps.org/protocol.html"}},"output":{"type":"json","example":{"url":"https://www.sitemaps.org/protocol.html","grade":"A","score":100,"title":"sitemaps.org - Protocol","findings":[],"markdown":"## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...","final_url":"https://www.sitemaps.org/protocol.html","truncated":false,"char_count":21619,"word_count":2707,"status_code":200,"content_type":"article","output_bytes":21619}}},"schema":{"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 URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"grade":{"type":"string"},"score":{"type":"number"},"title":{"type":"string"},"findings":{"type":"array"},"markdown":{"type":"string"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"char_count":{"type":"number"},"word_count":{"type":"number"},"status_code":{"type":"number"},"content_type":{"type":"string","description":"article | pdf | other (non-HTML/PDF falls back to best-effort plain text)"},"output_bytes":{"type":"number"}}}}}}}},"supportedNetworks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"advertisedPriceUsd":0.003,"paymentRequirements":[{"raw":{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","extra":{"name":"USD Coin","version":"2"},"payTo":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","amount":"3000","scheme":"exact","network":"eip155:8453","maxTimeoutSeconds":300},"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","payTo":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","scheme":"exact","network":"eip155:8453","amountAtomic":"3000"},{"raw":{"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","extra":{"feePayer":"BFK9TLC3edb13K6v4YyH3DwPb5DSUpkWvb7XnqCL9b4F"},"payTo":"8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s","amount":"3000","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":300},"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","payTo":"8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","amountAtomic":"3000"}],"resourceDescription":"Extract article / main content from any URL or PDF to clean, LLM-ready Markdown (web scraper / reader / html-to-markdown) — strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade so agents can read articles and documents without a browser or paid scraping service.","acceptedPaymentMethods":["exact"]},"source_id":1,"external_id":null}],"live_endpoint_metadata":{"x402_version":2,"resource_url":"https://netintel.dev/web/extract","resource_description":"Extract text from a web page or PDF as clean Markdown — HTML to Markdown for any URL: strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade. Web scraper / reader for article and main content. For JS-rendered or bot-walled pages a plain fetch can't read, use /exa/contents.","bazaar_extension":{"info":{"input":{"type":"http","method":"GET","queryParams":{"url":"https://www.sitemaps.org/protocol.html"}},"output":{"type":"json","example":{"url":"https://www.sitemaps.org/protocol.html","grade":"A","score":100,"title":"sitemaps.org - Protocol","findings":[],"markdown":"## Sitemaps XML format\n\nThis document describes the XML schema for the Sitemap protocol...","final_url":"https://www.sitemaps.org/protocol.html","truncated":false,"char_count":21619,"word_count":2707,"status_code":200,"content_type":"article","output_bytes":21619}}},"schema":{"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 URL of an HTML page or PDF to extract (e.g. https://www.sitemaps.org/protocol.html)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"grade":{"type":"string"},"score":{"type":"number"},"title":{"type":"string"},"findings":{"type":"array"},"markdown":{"type":"string"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"char_count":{"type":"number"},"word_count":{"type":"number"},"status_code":{"type":"number"},"content_type":{"type":"string","description":"article | pdf | other (non-HTML/PDF falls back to best-effort plain text)"},"output_bytes":{"type":"number"}}}}}}}},"accepted_requirements":[{"raw":{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","extra":{"name":"USD Coin","version":"2"},"payTo":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","amount":"3000","scheme":"exact","network":"eip155:8453","maxTimeoutSeconds":300},"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","payTo":"0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df","scheme":"exact","network":"eip155:8453","amountAtomic":"3000"},{"raw":{"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","extra":{"feePayer":"BFK9TLC3edb13K6v4YyH3DwPb5DSUpkWvb7XnqCL9b4F"},"payTo":"8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s","amount":"3000","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":300},"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","payTo":"8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","amountAtomic":"3000"}],"bazaar_compatible":true,"bazaar_validated_at":"2026-10-15 11:29:15.584+00","bazaar_validation_error":null},"sonar_metrics":{"score":0.8496,"uptime":1,"paid_success_rate":0,"valid_result_rate":null,"latency_p50":469,"latency_p90":691,"price_drift_pct":0},"cdp_indexed":false,"confidence":"high"}