{ "openapi": "3.0.1", "info": { "title": "PDF Revision Monitor - Text, Pages & Change Evidence", "description": "Extract text from public PDFs with page citations and hashes. Compare complete observations for text or byte-only changes. Bounded downloads and parsing; no OCR or API key.", "version": "1.0", "x-build-id": "vKYH6dsMGJwdkGLUc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maydit~pdf-revision-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maydit-pdf-revision-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maydit~pdf-revision-monitor/runs": { "post": { "operationId": "runs-sync-maydit-pdf-revision-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maydit~pdf-revision-monitor/run-sync": { "post": { "operationId": "run-sync-maydit-pdf-revision-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "documents": { "title": "Public PDF URLs and document IDs", "type": "array", "description": "Up to 20 URLs or objects {url,documentId,externalId}. documentId intentionally links changing source URLs to one report; default identity is the supplied URL. No passwords or private downloads.", "default": [ { "url": "https://www.census.gov/retail/marts/www/marts_current.pdf", "documentId": "census-monthly-retail-release" } ] }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 100, "type": "integer", "description": "Read from page 1 through this cap. Larger documents return a partial observation; no baseline update or removed-page assertion.", "default": 100 }, "maxFileSizeMb": { "title": "Maximum PDF download size (MiB)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Reject a larger response before parsing. Applies to every document; redirects and DNS destinations are checked.", "default": 10 }, "maxCharactersPerDocument": { "title": "Maximum extracted characters per document", "minimum": 1000, "maximum": 1000000, "type": "integer", "description": "Stop extraction at this bound and mark the observation partial. Partial text never replaces a complete baseline.", "default": 250000 }, "comparePrevious": { "title": "Compare with previous complete observation", "type": "boolean", "description": "Opt in to named-store history. First complete run establishes a baseline. Unchanged checks still return and bill a real observation.", "default": false }, "baselineKey": { "title": "Saved baseline namespace", "pattern": "^[-\\w]{1,80}$", "type": "string", "description": "One writer per namespace. A separate namespace starts independent history. Letters, digits, underscores and hyphens only.", "default": "default" }, "maxRunSeconds": { "title": "Run time budget (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Total work budget, also bounded by the platform deadline minus 25 seconds. Unfinished work is reported.", "default": 240 } } }, "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 } } } } } } } } } }