{ "openapi": "3.0.1", "info": { "title": "Web Page Scraper — ScrapingBee Alternative", "description": "Scrape public web pages into Markdown, text, or HTML. Supply URLs and receive browser-rendered content, source links, and optional screenshots for content research, page QA, or downstream analysis.", "version": "0.1", "x-build-id": "fhKPBBtKjSnE25HH7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~scrapingbee-alternative/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-scrapingbee-alternative", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/khadinakbar~scrapingbee-alternative/runs": { "post": { "operationId": "runs-sync-khadinakbar-scrapingbee-alternative", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/khadinakbar~scrapingbee-alternative/run-sync": { "post": { "operationId": "run-sync-khadinakbar-scrapingbee-alternative", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Public page URLs", "minItems": 1, "maxItems": 10, "type": "array", "description": "One to ten authorized public http(s) page URLs, such as https://example.com. The Actor rejects localhost, private-network, credential-bearing, malformed, and non-http URLs before navigation. It fetches page snapshots only; this is not a site crawler or private-account exporter.", "items": { "type": "string", "minLength": 8, "maxLength": 2048 } }, "outputFormat": { "title": "Page output format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Choose the page representation returned in each dataset record: markdown, text, or html. Defaults to markdown for compact agent-readable content. Markdown is a clean text representation, not a semantic reconstruction of every visual element.", "default": "markdown" }, "renderJavaScript": { "title": "Render JavaScript", "type": "boolean", "description": "Allow external script requests during the browser page load so client-rendered public content can appear before extraction. Defaults to true. When false, the Actor blocks external script resources; inline scripts may still run. It does not bypass logins, CAPTCHAs, access controls, or target terms.", "default": true }, "waitUntil": { "title": "Page readiness condition", "enum": [ "domcontentloaded", "networkidle" ], "type": "string", "description": "Choose when content collection may begin: DOM content loaded for the standard fast path, or network idle for pages that settle after their first document event. Network idle can use more of the per-page timeout and is not a guarantee for every site.", "default": "domcontentloaded" }, "takeScreenshot": { "title": "Save page screenshot", "type": "boolean", "description": "Save a full-page PNG in the run's default key-value store and return its record key. Defaults to false to keep storage and output light. This is a diagnostic artifact, not visual-diff monitoring or browser-session replay.", "default": false }, "timeoutSecs": { "title": "Per-page timeout seconds", "minimum": 10, "maximum": 60, "type": "integer", "description": "Maximum browser navigation time for each page, from 10 to 60 seconds. Defaults to 30 seconds and applies independently to each accepted URL. It is not a guarantee that every anti-bot-protected page can be reached.", "default": 30 }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route this authorized public-page run through the account's configured Apify Proxy. Defaults to false for direct access; proxy platform usage is paid by the caller when enabled. This does not expose a standalone proxy endpoint, credentials, country targeting, or a guarantee against blocks.", "default": false } } }, "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 } } } } } } } } } }