{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown - Text, Scanned OCR & PDF转Markdown", "description": "Convert public PDF URLs to Markdown page text. One row per nonempty page: text, page number, extraction method, dimensions and download URL. PDF转Markdown、扫描PDF识别。 Optional English/Chinese OCR on pages without text. Free blank pages and ID/hash exclusions; bounded page ranges.", "version": "1.0", "x-build-id": "muUaRBwTDncMkZ7Cj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kestrel~pdf-to-markdown-pages/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kestrel-pdf-to-markdown-pages", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kestrel~pdf-to-markdown-pages/runs": { "post": { "operationId": "runs-sync-kestrel-pdf-to-markdown-pages", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kestrel~pdf-to-markdown-pages/run-sync": { "post": { "operationId": "run-sync-kestrel-pdf-to-markdown-pages", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "documentUrls": { "title": "documentUrls", "maxItems": 100, "type": "array", "description": "Public PDF URLs. Up to 100, 12 MB each. One billed nonempty page. Default digital text; enable ocrMode=auto for scanned pages without text. Use ocrLanguage=chi_sim or eng+chi_sim for Chinese.", "items": { "type": "string" }, "default": [ "https://raw.githubusercontent.com/jsvine/pdfplumber/stable/examples/pdfs/background-checks.pdf" ] }, "startPage": { "title": "startPage", "minimum": 1, "maximum": 10000, "type": "integer", "description": "First PDF page to inspect, one-based, e.g. 2. Default 1. Pages before this are not inspected or billed.", "default": 1 }, "maxPagesPerDocument": { "title": "maxPagesPerDocument", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum PDF pages inspected per document, 1–20. Default 5. Blank pages or pages with no tables still consume this scan limit but are free.", "default": 5 }, "ocrMode": { "title": "ocrMode", "enum": [ "disabled", "auto" ], "type": "string", "description": "\"disabled\" (default) extracts digital PDF text only. \"auto\" applies printed-text OCR only to pages with no extractable text. Does not OCR images on text-bearing pages or repair bad text layers. One billed nonempty page, same price. 扫描PDF识别。", "default": "disabled" }, "ocrLanguage": { "title": "ocrLanguage", "enum": [ "eng", "chi_sim", "eng+chi_sim" ], "type": "string", "description": "\"eng\" (default), \"chi_sim\" for simplified Chinese, or \"eng+chi_sim\" for mixed printed text. Used only when ocrMode=auto needs OCR; not automatic language detection. 中文扫描件识别。", "default": "eng" }, "maxResults": { "title": "maxResults", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum paid rows across the run, 1–1000, default 20. Example: 3 for a sample. Exclusions and empty results apply before the cap.", "default": 20 }, "excludeIds": { "title": "excludeIds", "maxItems": 5000, "type": "array", "description": "Prior output id values to skip before billing, up to 5,000. Empty [] disables. Suppresses that identity even if content changed.", "items": { "type": "string" }, "default": [] }, "excludeContentHashes": { "title": "excludeContentHashes", "maxItems": 5000, "type": "array", "description": "Prior output content_hash values (64 lowercase hex characters), up to 5,000. Empty [] disables. Matching snapshots are skipped before billing.", "items": { "type": "string" }, "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 }, "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 } } } } } } } } } }