{ "openapi": "3.0.1", "info": { "title": "Instant web data scraper - Scrape any website", "description": "Scrape any public and private website data by providing just URL and optionally cookies and proxy information. \nThis scraper is similar to instant data scraper but runs on cloud and can be used as API too!", "version": "1.0", "x-build-id": "z2Qbjpd1qobbkiUXF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/curious_coder~instant-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-curious_coder-instant-web-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/curious_coder~instant-web-scraper/runs": { "post": { "operationId": "runs-sync-curious_coder-instant-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/curious_coder~instant-web-scraper/run-sync": { "post": { "operationId": "run-sync-curious_coder-instant-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "url" ], "properties": { "action": { "title": "⛏️ Select action to perform", "enum": [ "findTables", "scrapeData" ], "type": "string", "description": "First run the actor with 'Find tables' option to get possible output data table formats. Then choose the desired format and use it's table number to scrape the data by choosing 'Scrape' option", "default": "scrapeData" }, "cookies": { "title": "🍪 Cookies", "minItems": 1, "type": "array", "description": "Cookie used to authorize actor with website. Install [Cookie-Editor](https://chromewebstore.google.com/detail/cookie-editor/hlkenndednhfkekhgcdicdfddnkalmdm) chrome extension. Login to your website account. Click on the extension and export the website cookies. Insert the contents here" }, "url": { "title": "URL to scrape", "type": "string", "description": "Enter the link to the page to start scraping data" }, "columnMappings": { "title": "Column name mappings", "type": "array", "description": "Assign column names to data obtained from scraping. By default scraper will assign 0 based number to each column. You will need to manually assign names to these columns by mapping column names to column numbers in 'Find tables' output", "default": [], "items": { "type": "object", "required": [ "key", "value" ], "properties": { "key": { "type": "string", "title": "Key" }, "value": { "type": "string", "title": "Value" } } } }, "tableNumber": { "title": "Table number to scrape", "type": "integer", "description": "Scraper will automatically detact all the tables in the given page. But to decide which table to scrape, scraper needs either sample data or table number. Run the scraper with 'Find tables' action and choose the value from 'Table number' column from the output dataset. Choose the value from the row of your preferred data format", "default": 1 }, "additionalColumns": { "title": "Include additional columns", "type": "boolean", "description": "Include additional columns that are not included in columns mappings. These columns will have names like column_1, column_2, etc", "default": false }, "nextPageSelector": { "title": "Next page selector", "type": "string", "description": "Copy the CSS selector of the next page button or link. Leave it empty if the method of loading more data is by scrolling down. To get the selector of next page element, Right click on the element and click 'Inspect element'. Then on the popup, Right click on the highlighted element and click on 'Copy > Copy selector'" }, "count": { "title": "#️⃣ Total number of records required", "type": "integer", "description": "Leave this field empty if you want to scrape all items." }, "proxy": { "title": "Proxy", "type": "object", "description": "You can use proxy from your account's country if needed for extra safety." }, "minDelay": { "title": "⏱️ Minimum wait duration", "minimum": 2, "type": "integer", "description": "Minimum duration in seconds to wait before scraping next page", "default": 2 }, "maxDelay": { "title": "⏱️ Maximum wait duration", "minimum": 2, "type": "integer", "description": "Maximum duration in seconds to wait before scraping next page", "default": 2 } } }, "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 } } } } } } } } } }