{ "openapi": "3.0.1", "info": { "title": "Puppeteer Improved Inputs Scraper", "description": "Add the following options to inputs: Use Live View, Inject Query, and Inject Underscore", "version": "0.0", "x-build-id": "y7Fyw38cdBbwSB4aR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/barry8schneider~puppeteer20191228/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-barry8schneider-puppeteer20191228", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/barry8schneider~puppeteer20191228/runs": { "post": { "operationId": "runs-sync-barry8schneider-puppeteer20191228", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/barry8schneider~puppeteer20191228/run-sync": { "post": { "operationId": "run-sync-barry8schneider-puppeteer20191228", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "pageFunction" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "URLs to start with", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pseudoUrls": { "title": "Pseudo-URLs", "type": "array", "description": "Pseudo-URLs to match links in the page that you want to enqueue. Combine with Link selector to tell the scraper where to find links. Omitting the Pseudo-URLs will cause the scraper to enqueue all links matched by the Link selector.", "default": [], "items": { "type": "object", "required": [ "purl" ], "properties": { "purl": { "type": "string", "title": "Pseudo-URL of a web page" } } } }, "linkSelector": { "title": "Link selector", "type": "string", "description": "CSS selector matching elements with 'href' attributes that should be enqueued. To enqueue urls from
tags, you would enter div.my-class. Leave empty to ignore all links." }, "clickableElementsSelector": { "title": "Clickable elements selector", "type": "string", "description": "For pages where simple 'href' links are not available, this attribute allows you to specify a CSS selector matching elements that the scraper will mouse click after the page function finishes. Any triggered requests, navigations or open tabs will be intercepted and the target URLs will be filtered using Pseudo URLs and subsequently added to the request queue. Leave empty to prevent the scraper from clicking in the page. Using this setting will have a performance impact." }, "keepUrlFragments": { "title": "Keep URL fragments", "type": "boolean", "description": "URL fragments (the parts of URL after a #) are not considered when the scraper determines whether a URL has already been visited. This means that when adding URLs such as https://example.com/#foo and https://example.com/#bar, only the first will be visited. Turn this option on to tell the scraper to visit both.", "default": false }, "injectJQuery": { "title": "Inject jQuery to work in Page.Evaluate()", "type": "boolean", "description": "Indicates that the jQuery library should be injected into each page before Page function is invoked so jQuery can be used within the Page.Evaluate() function. Note that the jQuery object will not be registered into global namespace in order to avoid conflicts with libraries used by the web page. It can only be accessed through context.jQuery. For more information ", "default": true }, "injectUnderscoreJs": { "title": "Inject Underscore.js to work in Page.Evaluate()", "type": "boolean", "description": "Indicates that the Underscore.js library should be injected into each page before Page function is invoked so Underscore.js can be used within the Page.Evaluate() function. Note that the Underscore object will not be registered into global namespace in order to avoid conflicts with libraries used by the web page. It can only be accessed through context.underscoreJs.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Choose to use no proxy, Apify Proxy, or provide custom proxy URLs.", "default": {} }, "ignoreSslErrors": { "title": "Ignore SSL errors", "type": "boolean", "description": "Scraper will ignore SSL certificate errors.", "default": true }, "debugLog": { "title": "Debug log", "type": "boolean", "description": "Debug messages will be included in the log. Use context.log.debug('message') to log your own debug messages.", "default": false }, "customData": { "title": "Custom data", "type": "object", "description": "This object will be available on pageFunction's context as customData.", "default": {} }, "pageFunction": { "title": "Page function", "type": "string", "description": "Function executed for each request" }, "preGotoFunction": { "title": "Pre goto function", "type": "string", "description": "This function is executed before navigation to a given URL. It can be useful to do pre-processing, changes to the page that allow bypassing anti-scraping protections or just setting cookies." }, "initialCookies": { "title": "Initial cookies", "type": "array", "description": "The provided cookies will be pre-set to all pages the scraper opens.", "default": [] }, "useChrome": { "title": "Use Chrome", "type": "boolean", "description": "The scraper will use a real Chrome browser instead of a Chromium masking as Chrome. Using this option may help with bypassing certain anti-scraping protections, but risks that the scraper will be unstable or not work at all.", "default": false }, "useStealth": { "title": "Use Stealth", "type": "boolean", "description": "The scraper will apply various browser emulation techniques to match a real user as closely as possible. This feature works best in conjunction with the Use Chrome option and also carries the risk of making the scraper unstable.", "default": false }, "ignoreCorsAndCsp": { "title": "Ignore CORS and CSP", "type": "boolean", "description": "Scraper will ignore CSP (content security policy) and CORS (cross origin resource sharing) settings of visited pages and requested domains. This enables you to freely use XHR/Fetch to make HTTP requests from the scraper.", "default": false }, "downloadMedia": { "title": "Download media", "type": "boolean", "description": "Scraper will download media such as images, fonts, videos and sounds. Disabling this may speed up the scrape, but certain websites could stop working correctly.", "default": false }, "downloadCss": { "title": "Download CSS", "type": "boolean", "description": "Scraper will download CSS stylesheets. Disabling this may speed up the scrape, but certain websites could stop working correctly.", "default": false }, "useLiveView": { "title": "Use LiveView", "type": "boolean", "description": "Displays the first page of the browser. Disabling this may speed up the scrape.", "default": false }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Maximum number of times the request for the page will be retried in case of an error. Setting it to 0 means that the request will be attempted once and will not be retried if it fails.", "default": 3 }, "maxPagesPerCrawl": { "title": "Max pages per run", "minimum": 0, "type": "integer", "description": "Maximum number of pages that the scraper will open. 0 means unlimited.", "default": 0 }, "maxResultsPerCrawl": { "title": "Max result records", "minimum": 0, "type": "integer", "description": "Maximum number of results that will be saved to dataset. The scraper will terminate afterwards. 0 means unlimited.", "default": 0 }, "maxCrawlingDepth": { "title": "Max crawling depth", "minimum": 0, "type": "integer", "description": "Defines how many links away from the StartURLs will the scraper descend. 0 means unlimited.", "default": 0 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Defines how many pages can be processed by the scraper in parallel. The scraper automatically increases and decreases concurrency based on available system resources. Use this option to set a hard limit.", "default": 50 }, "pageLoadTimeoutSecs": { "title": "Page load timeout", "minimum": 1, "type": "integer", "description": "Maximum time the scraper will allow a web page to load in seconds.", "default": 60 }, "pageFunctionTimeoutSecs": { "title": "Page function timeout", "minimum": 1, "type": "integer", "description": "Maximum time the scraper will wait for the page function to execute in seconds.", "default": 60 }, "waitUntil": { "title": "Navigation wait until", "type": "array", "description": "The scraper will wait until the selected events are triggered in the page before executing the page function. Available events are domcontentloaded, load, networkidle2 and networkidle0. See Puppeteer docs.", "default": [ "networkidle2" ] }, "browserLog": { "title": "Browser log", "type": "boolean", "description": "Console messages from the Browser will be included in the log. This may result in the log being flooded by error messages, warnings and other messages of little value, especially with high concurrency.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }