Product Spec Table Extractor
Pricing
from $6.50 / 1,000 product page scanneds
Extract product specification tables, attribute lists, dimensions, compatibility data, materials, warnings, and download or manual links from product pages.
Pricing
from $6.50 / 1,000 product page scanneds
Rating
0.0
(0)
Developer
junipr
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
17 days ago
Last modified
Categories
Share
You can access the Product Spec Table Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "IMImDPoOoWpuU3Ddj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~product-spec-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-product-spec-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/junipr~product-spec-table-extractor/runs": { "post": { "operationId": "runs-sync-junipr-product-spec-table-extractor", "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/junipr~product-spec-table-extractor/run-sync": { "post": { "operationId": "run-sync-junipr-product-spec-table-extractor", "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": { "startUrls": { "title": "startUrls", "type": "array", "description": "startUrls for Product Spec Table Extractor.", "items": { "type": "string" }, "default": [] }, "sitemapUrls": { "title": "sitemapUrls", "type": "array", "description": "sitemapUrls for Product Spec Table Extractor.", "items": { "type": "string" }, "default": [] }, "htmlInputs": { "title": "htmlInputs", "type": "array", "description": "htmlInputs for Product Spec Table Extractor.", "items": { "type": "object" }, "default": [ { "sourceUrl": "https://shop.example/p/laptop", "html": "<html><head><title>Atlas Laptop</title><script type=\"application/ld+json\">{\"@type\":\"Product\",\"name\":\"Atlas Laptop\",\"additionalProperty\":[{\"name\":\"Battery\",\"value\":\"70Wh\"}]}</script></head><body><h1>Atlas Laptop</h1><table><caption>Dimensions</caption><tr><th>Width</th><td>320mm</td></tr><tr><th>Weight</th><td>1.5 kg</td></tr></table><dl><dt>Material</dt><dd>Aluminum</dd></dl><a href=\"/manual.pdf\">Download manual</a></body></html>" } ] }, "allowedDomains": { "title": "allowedDomains", "type": "array", "description": "allowedDomains for Product Spec Table Extractor.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "maxPages", "minimum": 0, "type": "integer", "description": "maxPages for Product Spec Table Extractor.", "default": 5 }, "maxDepth": { "title": "maxDepth", "minimum": 0, "type": "integer", "description": "maxDepth for Product Spec Table Extractor.", "default": 5 }, "includeEvidence": { "title": "includeEvidence", "type": "boolean", "description": "includeEvidence for Product Spec Table Extractor.", "default": true }, "includeRawSnapshots": { "title": "includeRawSnapshots", "type": "boolean", "description": "includeRawSnapshots for Product Spec Table Extractor.", "default": false }, "requestDelayMs": { "title": "requestDelayMs", "minimum": 0, "type": "integer", "description": "requestDelayMs for Product Spec Table Extractor.", "default": 0 }, "timeoutMs": { "title": "timeoutMs", "minimum": 0, "type": "integer", "description": "timeoutMs for Product Spec Table Extractor.", "default": 15000 }, "userAgentMode": { "title": "userAgentMode", "type": "string", "description": "userAgentMode for Product Spec Table Extractor.", "default": "standard" }, "productUrls": { "title": "productUrls", "type": "array", "description": "productUrls for Product Spec Table Extractor.", "items": { "type": "string" }, "default": [] }, "attributeNameMap": { "title": "attributeNameMap", "type": "object", "description": "attributeNameMap for Product Spec Table Extractor.", "default": {}, "additionalProperties": true }, "includeDownloads": { "title": "includeDownloads", "type": "boolean", "description": "includeDownloads for Product Spec Table Extractor.", "default": true }, "normalizeUnits": { "title": "normalizeUnits", "type": "boolean", "description": "normalizeUnits for Product Spec Table Extractor.", "default": true }, "maxSpecRowsPerProduct": { "title": "maxSpecRowsPerProduct", "minimum": 0, "type": "integer", "description": "maxSpecRowsPerProduct for Product Spec Table Extractor.", "default": 5 }, "tableSelectors": { "title": "tableSelectors", "type": "array", "description": "tableSelectors for Product Spec Table Extractor.", "items": { "type": "string" }, "default": [] }, "maxProductPages": { "title": "maxProductPages", "minimum": 0, "type": "integer", "description": "maxProductPages for Product Spec Table Extractor.", "default": 3 }, "maxSpecRowsPerPage": { "title": "maxSpecRowsPerPage", "minimum": 0, "type": "integer", "description": "maxSpecRowsPerPage for Product Spec Table Extractor.", "default": 20 }, "maxTablesPerPage": { "title": "maxTablesPerPage", "minimum": 0, "type": "integer", "description": "maxTablesPerPage for Product Spec Table Extractor.", "default": 5 }, "maxChargeUsd": { "title": "maxChargeUsd", "minimum": 0, "type": "number", "description": "maxChargeUsd for Product Spec Table Extractor.", "default": 15 }, "includeReport": { "title": "includeReport", "type": "boolean", "description": "includeReport for Product Spec Table Extractor.", "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 } } }, "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 Product Spec Table Extractor 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: