{"uid":"cap_DXn9wAbe6iTxXr-ReO4CB","slug":"web2markdown-web-page-pdf-to-clean-markdown-18cb792a","name":"Web2Markdown: Web Page / PDF to Clean Markdown","description":"Fetch any public web page or PDF and return clean main-content Markdown for AI agents / LLMs (boilerplate, nav and ads removed) plus title & metadata. CJK-aware; optional Simplified<->Traditional (incl. Hong Kong / Taiwan) conversion. Respects robots.txt. $0.002 per call, USDC on Base (x402). Failed extractions are not charged.","url":"https://lin-desk-x402.lindesk.workers.dev/v1/extract?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"zh":{"enum":["none","s2t","t2s","s2hk","s2tw","hk2s","tw2s"],"type":"string","description":"Optional Chinese script conversion (OpenCC). Default none"},"url":{"type":"string","description":"Public http(s) URL of an HTML page, PDF or text file"},"links":{"enum":["0","1"],"type":"string","description":"Keep hyperlinks in Markdown (1) or not (0, default)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"zh":{"type":"string"},"url":{"type":"string"},"kind":{"type":"string"},"chars":{"type":"integer"},"title":{"type":"string"},"markdown":{"type":"string"},"metadata":{"type":"object"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"elapsed_ms":{"type":"integer"}}}}}}},"responseSchema":{"type":"json","example":{"zh":"none","url":"https://example.com/","kind":"html","chars":120,"title":"Example Domain","markdown":"This domain is for use in documentation examples...","metadata":{},"final_url":"https://example.com/","truncated":false,"elapsed_ms":350}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_6H5sFA9GSPq9D1gTgyhvf","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches any public web page or PDF by URL and returns clean, LLM-ready Markdown text with title and metadata, billed per-call via x402.","exampleAgentPrompt":"Can you fetch the page at https://en.wikipedia.org/wiki/Large_language_model and give me the content as clean Markdown, keeping the hyperlinks?","exampleUseCases":[{"title":"Summarize a news article for briefing","prompt":"Grab the article at https://www.bbc.com/news/technology-12345678 and convert it to clean Markdown so I can summarize it for my morning briefing."},{"title":"Extract PDF report content for analysis","prompt":"Pull the PDF at https://example.com/annual-report-2024.pdf and convert it to Markdown text so I can analyze the key figures."},{"title":"Feed competitor page into AI pipeline","prompt":"Fetch https://competitor.com/pricing and return the content as clean Markdown without hyperlinks so I can pass it into my LLM for comparison."}],"resultDescription":"A JSON object containing the extracted Markdown text ('markdown'), page title ('title'), document type ('kind' e.g. 'html' or 'pdf'), character count ('chars'), the resolved final URL ('final_url'), original URL ('url'), metadata object, a boolean indicating if the content was truncated ('truncated'), applied Chinese conversion setting ('zh'), and processing time in milliseconds ('elapsed_ms').","failureModes":["URL is not publicly accessible or behind authentication — returns error","URL points to unsupported content type (e.g. binary file, video) — empty or error response","PDF is scanned/image-based with no selectable text — returns empty or minimal Markdown","Network timeout fetching the remote page — may return error or truncated content","Malformed or invalid URL provided — request fails with validation error","Payment not received or x402 flow incomplete — 402 response before extraction occurs"],"whenToPreferThis":"Choose this endpoint when you need to quickly convert any public HTML page or PDF into clean, LLM-ready Markdown without setting up an API key or managing credentials. It is ideal for AI agent pipelines that need on-demand, pay-per-call web content extraction with no subscription overhead. Prefer it over browser automation tools when you just need readable text content rather than interactive page rendering. The optional Chinese script conversion (OpenCC) and hyperlink preservation make it useful for multilingual or link-aware workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T00:32:00.788Z","isFirstParty":false,"canonicalSlug":"web2markdown-web-page-pdf-to-clean-markdown-18cb792a"}