PDF Extractor 2.0
Pricing
$30.00/month + usage
Go to Apify Store
PDF Extractor 2.0
💫 Extract PDF Document Contents including Metadata, Images, Pages, Tables, Attachments, etc.
0.0 (0)
Pricing
$30.00/month + usage
6
129
25
Last modified
a month ago
Pricing
$30.00/month + usage
💫 Extract PDF Document Contents including Metadata, Images, Pages, Tables, Attachments, etc.
0.0 (0)
Pricing
$30.00/month + usage
6
129
25
Last modified
a month ago
You can access the PDF Extractor 2.0 programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.2", "x-build-id": "SWcCvKDYlncJhroh9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jupri~pdf-extractor-2-0/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jupri-pdf-extractor-2-0", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/jupri~pdf-extractor-2-0/runs": { "post": { "operationId": "runs-sync-jupri-pdf-extractor-2-0", "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/jupri~pdf-extractor-2-0/run-sync": { "post": { "operationId": "run-sync-jupri-pdf-extractor-2-0", "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": { "url": { "title": "🕮 URL", "type": "array", "description": "💡 Document URL Location", "items": { "type": "string" } }, "password": { "title": "🔑 Password", "type": "string", "description": "💡 Document Password" }, "dev_fileupload": { "title": "Upload", "type": "string", "description": "" }, "content": { "title": "Content Format", "enum": [ "text", "svg", "jpeg", "png" ], "type": "string", "description": "💡 Content Format" }, "images": { "title": "Extract Images", "type": "boolean", "description": "💡 Extract Embedded Images" }, "attachments": { "title": "Extract Attachments", "type": "boolean", "description": "💡 Extract Embedded Files" }, "tables": { "title": "Extract Tables", "type": "boolean", "description": "💡 Extract Tables" }, "links": { "title": "Extract URL Links", "type": "boolean", "description": "💡 Extract URL Links" }, "dev_proxy_config": { "title": "🌐 PROXY NETWORKING", "type": "object", "description": "💡 <b>Supported protocol:</b><br><br><b>HTTP(S), SOCKS5</b><br><code>{http|socks5}://{user:pass}@{hostname|ip-address}:port</code><br><br><b>Example</b>: <code>socks5://example.com:9000</code>" }, "dev_custom_headers": { "title": "📜 HTTP HEADERS", "type": "array", "description": "💡 Additional HTTP Headers", "items": { "type": "object", "required": [ "key", "value" ], "properties": { "key": { "type": "string", "title": "Key" }, "value": { "type": "string", "title": "Value" } } } }, "dev_custom_cookies": { "title": "🍰 HTTP COOKIES", "type": "array", "description": "💡 Additional HTTP Cookies", "items": { "type": "object", "required": [ "key", "value" ], "properties": { "key": { "type": "string", "title": "Key" }, "value": { "type": "string", "title": "Value" } } } }, "dev_transform_fields": { "title": "♻️ CUSTOM FIELD", "type": "array", "description": "💡 <b>Transform the resulting output. Select only needed fields.</b><br><br>For nested object use <b>DOT</b>. For example: <pre>address.streetAddress</pre><br>For nested array use <b>NUMBER</b> <i>(index of array element starting from index=0)</i>. For example: <pre>images.0.url</pre>", "items": { "type": "object", "required": [ "key", "value" ], "properties": { "key": { "type": "string", "title": "Key" }, "value": { "type": "string", "title": "Value" } } } }, "dev_dataset_name": { "title": "📁 CUSTOM STORAGE", "type": "string", "description": "💡 <b>Save results into custom named Dataset, use mask to customize dataset name</b><br><br><code>{ACTOR} = actor name<br>{DATE} = date (YYYYMMDD)<br>{TIME} = time (HHMMSS)</code><br><br>This masks can be used to autogenerate Dataset Name.<br><br>example: <i><code>data-{DATE}</code></i><br>Depending on today date the dataset name will be: <code>data-20230603</code><i><br><br>default: <code>data-{ACTOR}-{DATE}-{TIME}</code></i>" }, "dev_dataset_clear": { "title": "Clear Storage", "type": "boolean", "description": "Clear Dataset before insert/update." }, "dev_no_strip": { "title": "Disable data cleansing", "type": "boolean", "description": "💡 Keep/Save empty values <i><code>(NULL, FALSE, empty ARRAY, empty OBJECT, empty STRING)</code></i>" } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for PDF Extractor 2.0 from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: