{ "openapi": "3.0.1", "info": { "title": "Scrapy Cloud Runner", "description": "Run Scrapy spiders on Apify with request queue, dataset export, proxy rotation, scheduling, and cloud-ready deployment.", "version": "0.1", "x-build-id": "Doza1wgni36tg02D1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~scrapy-cloud-runner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-scrapy-cloud-runner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~scrapy-cloud-runner/runs": { "post": { "operationId": "runs-sync-solutionssmart-scrapy-cloud-runner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~scrapy-cloud-runner/run-sync": { "post": { "operationId": "run-sync-solutionssmart-scrapy-cloud-runner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "spiderName": { "title": "Spider name", "type": "string", "description": "The Scrapy spider name to run. The bundled default is page_meta.", "default": "page_meta" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Entry URLs for the spider. For most spiders, each item only needs a url field.", "items": { "type": "object", "additionalProperties": false, "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "Starting URL for the crawl." } } } }, "allowedDomains": { "title": "Allowed domains", "type": "array", "description": "Optional domain allowlist. If empty, the actor derives domains from startUrls for the bundled page_meta spider.", "items": { "type": "string" } }, "followLinks": { "title": "Follow links", "type": "boolean", "description": "For the bundled page_meta spider, continue crawling internal links discovered on each page.", "default": true }, "sameHostnameOnly": { "title": "Same hostname only", "type": "boolean", "description": "Restrict link following to the exact host names from startUrls. This avoids drifting into subdomains with different rate limits or blocking rules.", "default": true }, "includeHtml": { "title": "Include HTML", "type": "boolean", "description": "Include raw HTML in dataset items. Keep disabled unless you really need full page source.", "default": false }, "maxRequestsPerCrawl": { "title": "Max requests per crawl", "minimum": 1, "type": "integer", "description": "Hard cap for processed pages.", "default": 100 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "type": "integer", "description": "How far the spider may follow links from the initial pages.", "default": 1 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 256, "type": "integer", "description": "Maximum concurrent Scrapy requests.", "default": 16 }, "requestTimeoutSecs": { "title": "Request timeout in seconds", "minimum": 1, "maximum": 300, "type": "integer", "description": "Download timeout applied to each request.", "default": 30 }, "downloadDelaySecs": { "title": "Download delay in seconds", "minimum": 0, "maximum": 60, "type": "number", "description": "Optional delay between requests to the same site.", "default": 1 }, "retryTimes": { "title": "Retry times", "minimum": 0, "maximum": 20, "type": "integer", "description": "Maximum retries for failed requests.", "default": 2 }, "useAutoThrottle": { "title": "Use AutoThrottle", "type": "boolean", "description": "Enable Scrapy AutoThrottle to adapt request rate based on observed site latency.", "default": true }, "autoThrottleTargetConcurrency": { "title": "AutoThrottle target concurrency", "minimum": 0.1, "maximum": 16, "type": "number", "description": "Average concurrent requests Scrapy should aim for per remote site.", "default": 1 }, "autoThrottleStartDelaySecs": { "title": "AutoThrottle start delay in seconds", "minimum": 0, "maximum": 60, "type": "number", "description": "Initial delay before AutoThrottle adapts.", "default": 1 }, "autoThrottleMaxDelaySecs": { "title": "AutoThrottle max delay in seconds", "minimum": 1, "maximum": 300, "type": "number", "description": "Maximum delay AutoThrottle may apply when latency rises.", "default": 15 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Enable Scrapy robots.txt handling.", "default": true }, "useHttpCache": { "title": "Use HTTP cache", "type": "boolean", "description": "Cache responses in the default Apify key-value store to speed up repeated runs.", "default": false }, "httpCacheExpirationSecs": { "title": "HTTP cache expiration in seconds", "minimum": 0, "type": "integer", "description": "How long cached responses stay valid when HTTP cache is enabled.", "default": 7200 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy configuration passed into the Scrapy integration." }, "spiderArgs": { "title": "Spider arguments", "type": "array", "description": "Optional spider arguments entered as key/value rows in the Console form.", "items": { "type": "object", "additionalProperties": false, "required": [ "key", "value" ], "properties": { "key": { "title": "Argument name", "type": "string", "description": "Spider argument name." }, "value": { "title": "Argument value", "type": "string", "description": "Spider argument value passed as a string." } } }, "default": [] }, "spiderArgsJson": { "title": "Spider arguments JSON", "type": "object", "description": "Optional structured spider arguments for API callers. Merged over Spider arguments on duplicate keys.", "default": {} } } }, "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 } } } } } } } } } }