{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler | Bulk Text & Markdown", "description": "Fetch public website pages in bulk and export clean text, titles, Markdown and source evidence, with bounded concurrency, robots checks and explicit partial results.", "version": "0.1", "x-build-id": "DfksG9ppOUHeO5CME" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/peerless_columbine~independent-bulk-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-peerless_columbine-independent-bulk-content-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/peerless_columbine~independent-bulk-content-crawler/runs": { "post": { "operationId": "runs-sync-peerless_columbine-independent-bulk-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/peerless_columbine~independent-bulk-content-crawler/run-sync": { "post": { "operationId": "run-sync-peerless_columbine-independent-bulk-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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" ], "properties": { "startUrls": { "title": "Start URLs", "minItems": 0, "maxItems": 100000, "type": "array", "description": "Bare domains, IDNs, or full public HTTP(S) URLs. One supplied page per entry.", "items": { "type": "string" }, "default": null }, "maxConcurrency": { "title": "maxConcurrency", "minimum": 1, "maximum": 64, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 16 }, "maxRequests": { "title": "maxRequests", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 30000 }, "maxPages": { "title": "maxPages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 10000 }, "maxBodyBytes": { "title": "maxBodyBytes", "minimum": 1024, "maximum": 10000000, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 2000000 }, "maxTextChars": { "title": "maxTextChars", "minimum": 100, "maximum": 2000000, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 500000 }, "maxRedirects": { "title": "maxRedirects", "minimum": 0, "maximum": 10, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 5 }, "pageTimeoutSecs": { "title": "pageTimeoutSecs", "minimum": 1, "maximum": 120, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 40 }, "runTimeoutSecs": { "title": "runTimeoutSecs", "minimum": 1, "maximum": 3600, "type": "integer", "description": "Resource safety limit; reached limits are reported explicitly.", "default": 240 }, "fakeIpDohFallback": { "title": "Clash fakeIP DoH fallback", "type": "boolean", "description": "Only all-fakeIP OS DNS uses fixed public Cloudflare DoH, validated answers, pinned TCP and hostname TLS. No fallback for other DNS failures.", "default": 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 }, "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 } } } } } } } } } }