{ "openapi": "3.0.1", "info": { "title": "Webpage Content Scraper to Markdown", "description": "Focus on cost, Scrape any webpage content into LLM-ready Markdown for RAG. Uses a smart hybrid 6 tier engine: Apify for crawling + Cloudflare Browser API Rendering for perfect extraction. Automatically saves costs by detecting native markdown support.", "version": "0.1", "x-build-id": "s45njdOPyPucG1vLS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/riisager~tulabot-cloudflare-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-riisager-tulabot-cloudflare-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/riisager~tulabot-cloudflare-markdown/runs": { "post": { "operationId": "runs-sync-riisager-tulabot-cloudflare-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/riisager~tulabot-cloudflare-markdown/run-sync": { "post": { "operationId": "run-sync-riisager-tulabot-cloudflare-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls", "cfAccountId", "cfApiToken" ], "properties": { "startUrls": { "title": "Start URLs (Batch or Single)", "type": "array", "description": "Enter the URLs you want to scrape or crawl. You can also upload a text file with a list of URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "cfAccountId": { "title": "Cloudflare Account ID", "type": "string", "description": "Your Cloudflare Account ID found in the dashboard." }, "customUserAgent": { "title": "Custom User-Agent", "type": "string", "description": "Optional: Supply a custom User-Agent string to bypass specific blocks. If left empty, the Actor will use the default browser User-Agent." }, "cfApiToken": { "title": "Cloudflare API Token", "type": "string", "description": "Your Cloudflare API Token with Browser Rendering permissions." }, "crawlingEnabled": { "title": "Enable Website Crawling", "type": "boolean", "description": "If enabled, the actor will follow links on the same domain.", "default": false }, "maxDepth": { "title": "Max Crawl Depth", "type": "integer", "description": "Depth of links to follow from the start URLs.", "default": 1 }, "excludeCss": { "title": "Block CSS/Images (Faster)", "type": "boolean", "description": "If true, blocks CSS, images, and fonts to speed up crawling.", "default": true }, "enableTier0FileRouting": { "title": "Enable Tier 0 (File Routing)", "type": "boolean", "description": "Automatically detect and extract content from PDFs, Word, Excel, PPTX, CSV, JSON, and XML files.", "default": true }, "enableSafeGuard": { "title": "Enable Safe-Guard (Skip Binaries)", "type": "boolean", "description": "Recommended: Instantly skip heavy/binary files (images, video, archives) to save compute and avoid crashes.", "default": true }, "enableTier1Native": { "title": "Enable Tier 1 (Native Markdown)", "type": "boolean", "description": "Attempt to fetch native markdown from the server first (Fastest & Free).", "default": true }, "enableTier2Local": { "title": "Enable Tier 2 (Local Readability)", "type": "boolean", "description": "Attempt to extract markdown locally using Mozilla Readability (Free & Fast).", "default": true }, "enableTier3Cloudflare": { "title": "Enable Tier 3 (Cloudflare Browser)", "type": "boolean", "description": "Use Cloudflare Browser Rendering if local extraction fails (Premium & High Quality).", "default": true }, "enableTier4Apify": { "title": "Enable Tier 4 (Apify Browser)", "type": "boolean", "description": "Use Apify Headless Browser + Proxy as ultimate fallback if Cloudflare fails (Robust but uses more RAM).", "default": true }, "enableTier5Stealth": { "title": "Enable Tier 5 (Stealth Browser + Residential Proxy)", "type": "boolean", "description": "Premium Anti-Bot Bypass: Uses Puppeteer Stealth. WARNING: You MUST configure Residential Proxies in the Proxy Configuration below for this to work on Enterprise sites. Significantly slower and more expensive.", "default": true }, "enableDebugScreenshots": { "title": "Enable Error Screenshots (Slower/Costs Storage)", "type": "boolean", "description": "If enabled, the Actor will capture and save a full screenshot to the Key-Value Store whenever Tier 4 or Tier 5 completely fails. Excellent for debugging blocked pages, but consumes Apify Storage and slows down error recovery.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration (Tier 1, 2 & 4)", "type": "object", "description": "Select proxies. Tier 1 & 2 use this for initial requests. Tier 4 uses this for the fallback browser. Default is set to Datacenter proxies for lowest cost.", "default": { "useApifyProxy": true, "apifyProxyGroups": [] } }, "minContentLength": { "title": "Min Content Length (Chars) for Tier 2", "minimum": 0, "type": "integer", "description": "Minimum characters required from local extraction to be considered successful. If less, falls back to higher tiers.", "default": 500 }, "maxConcurrency": { "title": "Max Concurrency", "type": "integer", "description": "Maximum number of pages processed in parallel. Be careful with Cloudflare rate limits.", "default": 5 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }