{ "openapi": "3.0.1", "info": { "title": "Ai Content Scraper Cleaner", "description": "AI Content Scraper & Cleaner — Scrapes structured content (documentation, articles, FAQs, blog posts) and converts it into clean, normalized JSON datasets for LLM training. Extracts text, detects content types, estimates tokens, and removes boilerplate to produce ready-to-use training data.", "version": "0.0", "x-build-id": "L4Y3slxpLSE0Ba4TP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dashjeevanthedev~ai-content-scraper-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dashjeevanthedev-ai-content-scraper-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dashjeevanthedev~ai-content-scraper-cleaner/runs": { "post": { "operationId": "runs-sync-dashjeevanthedev-ai-content-scraper-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dashjeevanthedev~ai-content-scraper-cleaner/run-sync": { "post": { "operationId": "run-sync-dashjeevanthedev-ai-content-scraper-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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" ], "properties": { "startUrls": { "title": "Start URLs (comma-separated URLs)", "type": "string", "description": "Comma-separated list of URLs to start crawling from.", "default": "https://crawlee.dev/docs/introduction, https://docs.apify.com/platform/actors, https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Introduction, https://react.dev/learn, https://nextjs.org/docs/getting-started" }, "maxRequestsPerCrawl": { "title": "Max requests per crawl", "type": "string", "description": "Maximum number of requests allowed for this run.", "default": "50" }, "contentSelectors": { "title": "Content CSS selectors (comma-separated)", "type": "string", "description": "Comma-separated CSS selectors used to extract main content.", "default": "article, .doc-content, .post-content" }, "titleSelectors": { "title": "Title CSS selectors (comma-separated)", "type": "string", "description": "Comma-separated CSS selectors used to extract page title.", "default": "h1, .post-title" }, "minimumTextLength": { "title": "Minimum text length", "type": "string", "description": "Ignore content shorter than this many characters.", "default": "300" }, "contentType": { "title": "Content type override", "enum": [ "auto", "faq", "article", "guide", "documentation", "blog", "other" ], "type": "string", "description": "Force a specific content type.", "default": "auto" }, "maxDepth": { "title": "Max crawl depth", "type": "string", "description": "How deep the crawler is allowed to follow links.", "default": "2" }, "respectRobotsTxt": { "title": "Respect robots.txt", "enum": [ "true", "false" ], "type": "string", "description": "Whether the crawler should honor robots.txt rules.", "default": "true" }, "useProxy": { "title": "Use Apify Proxy", "enum": [ "true", "false" ], "type": "string", "description": "Rotate proxies via Apify proxy when available.", "default": "true" }, "language": { "title": "Language Filter", "type": "string", "description": "Optional language code (e.g. en). Leave empty for no filter.", "default": "en" } } }, "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 } } } } } } } } } }