{ "data": { "id": "gYm9cjVYJRezeWD58", "userId": "HIMU0xktu1JeZb4Xl", "name": "web-page-to-markdown-extractor", "username": "fetch_cat", "description": "Convert public URLs into clean Markdown, text, metadata, links, images, and optional HTML for AI and automation workflows.", "isPublic": true, "createdAt": "2026-06-16T08:56:31.930Z", "modifiedAt": "2026-07-09T11:09:44.687Z", "taggedBuilds": { "latest": { "buildId": "dy8CnaX8s3tBogYSr", "finishedAt": "2026-07-09T11:09:44.687Z", "buildNumberInt": 100008, "buildNumber": "0.1.8" } }, "stats": { "totalBuilds": 8, "totalRuns": 139, "totalUsers": 2, "totalUsers7Days": 0, "totalUsers30Days": 1, "totalUsers90Days": 1, "lastRunStartedAt": "2026-07-09T11:46:36.987Z", "actorReviewCount": 0, "actorReviewRating": 0, "bookmarkCount": 0, "publicActorRunStats30Days": { "ABORTED": 0, "FAILED": 0, "SUCCEEDED": 24, "TIMED-OUT": 0, "TOTAL": 24 } }, "versions": [ { "versionNumber": "0.1", "sourceType": "SOURCE_FILES", "buildTag": "latest" } ], "defaultRunOptions": { "build": "latest", "timeoutSecs": 300, "memoryMbytes": 1024 }, "exampleRunInput": { "body": "{\"startUrls\":[{\"url\":\"https://blog.apify.com/web-scraping-for-ai/\"}],\"renderMode\":\"http\",\"maxPages\":1,\"includeLinks\":true,\"includeImages\":false,\"includeHtml\":false,\"timeoutSecs\":10}", "contentType": "application/json; charset=utf-8" }, "categories": [ "AI", "DEVELOPER_TOOLS", "AUTOMATION" ], "isDeprecated": false, "title": "Web Page to Markdown Extractor", "pictureUrl": "https://apify-image-uploads-prod.s3.us-east-1.amazonaws.com/HIMU0xktu1JeZb4Xl-actor-gYm9cjVYJRezeWD58-x8BFtQgKaU-web-page-to-markdown-extractor-actor-icon.png", "seoTitle": "Web Page to Markdown Extractor for AI Agents", "seoDescription": "Convert public URLs into clean Markdown, text, metadata, links, images, and optional HTML for AI agents, RAG, support, and automation workflows via API.", "pricingInfos": [ { "pricingModel": "PAY_PER_EVENT", "startedAt": "2026-06-16T09:00:00.000Z", "pricingPerEvent": { "actorChargeEvents": { "start": { "eventTitle": "Start", "eventDescription": "One-time fee per run", "eventPriceUsd": 0.005, "isOneTimeEvent": true }, "result": { "eventTitle": "HTTP page result", "eventDescription": "One public page converted using HTTP extraction", "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.00115 }, "BRONZE": { "tieredEventPriceUsd": 0.001 }, "SILVER": { "tieredEventPriceUsd": 0.00078 }, "GOLD": { "tieredEventPriceUsd": 0.0006 }, "PLATINUM": { "tieredEventPriceUsd": 0.0004 }, "DIAMOND": { "tieredEventPriceUsd": 0.00028 } } }, "browser_result": { "eventTitle": "Browser-rendered page result", "eventDescription": "One public page converted using JavaScript browser rendering", "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.00575 }, "BRONZE": { "tieredEventPriceUsd": 0.005 }, "SILVER": { "tieredEventPriceUsd": 0.0039 }, "GOLD": { "tieredEventPriceUsd": 0.003 }, "PLATINUM": { "tieredEventPriceUsd": 0.002 }, "DIAMOND": { "tieredEventPriceUsd": 0.0014 } } } } }, "apifyMarginPercentage": 0.2, "createdAt": "2026-06-16T09:01:26.738Z" }, { "pricingModel": "PAY_PER_EVENT", "startedAt": "2026-06-16T09:06:00.000Z", "pricingPerEvent": { "actorChargeEvents": { "start": { "eventTitle": "Run started", "eventDescription": "One-time fee charged when a run starts. Covers fixed startup cost.", "eventPriceUsd": 0.005, "isOneTimeEvent": true }, "result": { "eventTitle": "HTTP page result", "eventDescription": "One public page converted using HTTP extraction", "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.00018526 }, "BRONZE": { "tieredEventPriceUsd": 0.0001611 }, "SILVER": { "tieredEventPriceUsd": 0.00012566 }, "GOLD": { "tieredEventPriceUsd": 0.000096659 }, "PLATINUM": { "tieredEventPriceUsd": 0.000064439 }, "DIAMOND": { "tieredEventPriceUsd": 0.000045108 } } }, "browser_result": { "eventTitle": "Browser-rendered page result", "eventDescription": "One public page converted using JavaScript browser rendering", "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.00575 }, "BRONZE": { "tieredEventPriceUsd": 0.005 }, "SILVER": { "tieredEventPriceUsd": 0.0039 }, "GOLD": { "tieredEventPriceUsd": 0.003 }, "PLATINUM": { "tieredEventPriceUsd": 0.002 }, "DIAMOND": { "tieredEventPriceUsd": 0.0014 } } } } }, "apifyMarginPercentage": 0.2, "createdAt": "2026-06-16T09:06:22.091Z" }, { "pricingModel": "PAY_PER_EVENT", "startedAt": "2026-06-17T11:27:48.981Z", "pricingPerEvent": { "actorChargeEvents": { "start": { "eventTitle": "Run started", "eventDescription": "One-time fee charged when a run starts. Covers fixed startup cost.", "eventPriceUsd": 0.005, "isOneTimeEvent": true }, "result": { "eventTitle": "HTTP page result", "eventDescription": "One public page converted using HTTP extraction", "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.00018526 }, "BRONZE": { "tieredEventPriceUsd": 0.0001611 }, "SILVER": { "tieredEventPriceUsd": 0.00012566 }, "GOLD": { "tieredEventPriceUsd": 0.000096659 }, "PLATINUM": { "tieredEventPriceUsd": 0.000064439 }, "DIAMOND": { "tieredEventPriceUsd": 0.000045108 } }, "isPrimaryEvent": true }, "browser_result": { "eventTitle": "Browser-rendered page result", "eventDescription": "One public page converted using JavaScript browser rendering", "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.00575 }, "BRONZE": { "tieredEventPriceUsd": 0.005 }, "SILVER": { "tieredEventPriceUsd": 0.0039 }, "GOLD": { "tieredEventPriceUsd": 0.003 }, "PLATINUM": { "tieredEventPriceUsd": 0.002 }, "DIAMOND": { "tieredEventPriceUsd": 0.0014 } } } } }, "apifyMarginPercentage": 0.2, "createdAt": "2026-06-17T11:27:49.048Z" } ], "notice": "NONE", "isCritical": false, "isGeneric": false, "hasNoDataset": false, "isSourceCodeHidden": true, "standbyUrl": null, "actorPermissionLevel": "LIMITED_PERMISSIONS", "readmeSummary": "## Web Page to Markdown Extractor\n\nA web content extraction Actor that fetches public HTTP/HTTPS pages and converts them into cleaned, LLM-ready content and structured metadata. It supports fast HTTP extraction and optional full browser rendering for JavaScript-driven pages, plus an auto mode that attempts HTTP first and falls back to browser rendering when needed. The Actor outputs cleaned Markdown suitable for prompts and retrieval-augmented generation (RAG), plain text for search and summarization, page title and meta description, resolved final URL and HTTP response status, normalized links and image URLs with alt text, metadata flags, and optional truncated HTML. Technical controls include per-page timeouts, page-count caps, HTML byte caps, link and image extraction toggles, and error records for failed pages to keep runs inspectable.\n\n## Use cases\n\n- Collect context for LLM agents and agent-driven workflows \n- Prepare web pages for embeddings and RAG pipelines \n- Turn help-center and support documentation into knowledge snippets \n- Collect public articles and technical documentation for research or monitoring \n- Convert product and marketing pages into readable summaries for review \n- Build URL enrichment steps in no-code automation and workflow builders \n- Discover and normalize links and image URLs for content auditing or media extraction \n- QA checks for page status, metadata, and extracted content across batches", "deploymentKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDS45YGn/g8mnJxmLstty1UfiYzq5LDiNlMyU+Ix1sbzsIfFBDIdhl7om49Rt4F9VahkUvv4ajebFigLnZ6J+PqORvOS8SyRGrcX+J/qJQb1iaHsaJOas0czQdYFPmJtxq+1SMW6mrGA6wwLkDCLEqeVCR2lGwaWvbHsqvjtAJaf+qFIC0iuBB9ivYbHuo9pCsCfl8rd70+ku77OmOJ10HYR/mwF/dSBMiNnSPMd0sZDCs2lychiv9j80gfCg9mVeYsaLGUA/NJ2IekWxaJkxGnCrVp56OfWpg1Fgem8/oTIJkpK9YwqCh7Dq351N0WwzNqYpIhFEM9Mah6cU7YjIEX \n" } }