{ "openapi": "3.0.1", "info": { "title": "Page Scraping Analyzer", "description": "Performs analysis of a webpage to figure out the best way how to scrape its data. Provide a URL and data points to find and get back a detailed dashboard showing how the data can be scraped. Works with initial and rendered HTML, JavaScript variables and dynamically loaded data.", "version": "0.0", "x-build-id": "KEWgs2hPsnc3CZ3Fe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/apify~page-analyzer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-apify-page-analyzer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/apify~page-analyzer/runs": { "post": { "operationId": "runs-sync-apify-page-analyzer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/apify~page-analyzer/run-sync": { "post": { "operationId": "run-sync-apify-page-analyzer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "keywords" ], "properties": { "url": { "title": "Page URL", "type": "string", "description": "URL of a website to by analyzed. Use a page URL that you would want to scrape. You can run this actor again for different page type (e.g. one run for search results page, another run for product detail page).", "default": "http://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html" }, "keywords": { "title": "Keywords", "type": "array", "description": "Keywords to be searched for during analysis", "default": [ "A Light in the Attic", "51.77", "In stock", "22 available", "a897fe39b1053632", "It's hard to imagine a world without A Light in the Attic. This now-classic collection of poetry and drawings from Shel Silverstein celebrates its 20th anniversary with this special edition. Silverstein's humorous and creative verse can amuse the dowdiest of readers. Lemon-faced adults and fidgety kids sit still and read these rhythmic words and laugh and smile and love th It's hard to imagine a world without A Light in the Attic. This now-classic collection of poetry and drawings from Shel Silverstein celebrates its 20th anniversary with this special edition. Silverstein's humorous and creative verse can amuse the dowdiest of readers. Lemon-faced adults and fidgety kids sit still and read these rhythmic words and laugh and smile and love that Silverstein. Need proof of his genius? RockabyeRockabye baby, in the treetopDon't you know a treetopIs no safe place to rock?And who put you up there,And your cradle, too?Baby, I think someone down here'sGot it in for you. Shel, you never sounded so good. ...more" ], "items": { "type": "string" } }, "proxyConfig": { "title": "Proxy configuration", "type": "object", "description": "You should use proxies for scraping. Use datacenter proxies but fallback to residential ones if blocked too much.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }