Web Data To Excel Scraper
Pricing
Pay per event + usage
Extract user-defined fields from repeated records on public static webpages. Normalize text, numbers, dates, booleans, and URLs into validated dataset rows and a filterable XLSX workbook.
You can access the Web Data To Excel Scraper 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": "0.1", "x-build-id": "KLJP8Qe6klwIwJ1hY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~schema-guided-web-data-to-excel/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-schema-guided-web-data-to-excel", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~schema-guided-web-data-to-excel/runs": { "post": { "operationId": "runs-sync-automation-lab-schema-guided-web-data-to-excel", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~schema-guided-web-data-to-excel/run-sync": { "post": { "operationId": "run-sync-automation-lab-schema-guided-web-data-to-excel", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "recordSelector", "fields" ], "properties": { "startUrls": { "title": "Public webpage URLs", "minItems": 1, "maxItems": 50, "type": "array", "description": "Static, anonymously reachable HTTP(S) pages that contain the same kind of repeated records. Up to 50 URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "recordSelector": { "title": "Record CSS selector", "minLength": 1, "type": "string", "description": "CSS selector for each repeated record, evaluated against every page.", "default": "article.product_pod" }, "fields": { "title": "Field schema", "minItems": 1, "maxItems": 50, "type": "array", "description": "Columns to extract relative to each matched record. Field names become Excel column names.", "items": { "type": "object", "required": [ "name", "type" ], "properties": { "name": { "title": "Column name", "description": "Unique Excel-safe name beginning with a letter and containing only letters, numbers, or underscores.", "type": "string", "pattern": "^[A-Za-z][A-Za-z0-9_]{0,63}$" }, "selector": { "title": "Field CSS selector", "description": "Selector relative to the record. Omit it to read the record element itself.", "type": "string" }, "source": { "title": "Value source", "description": "Read visible text, inner HTML, or an HTML attribute.", "type": "string", "enum": [ "text", "html", "attribute" ], "default": "text" }, "attribute": { "title": "Attribute name", "description": "Required when source is attribute, for example href, src, or title.", "type": "string" }, "type": { "title": "Output type", "description": "Normalize the value as a string, number, integer, boolean, absolute URL, or ISO date.", "type": "string", "enum": [ "string", "number", "integer", "boolean", "url", "date" ] }, "pattern": { "title": "Extraction pattern", "description": "Optional regular expression. The first capture group is used when present.", "type": "string", "maxLength": 200 }, "required": { "title": "Required field", "description": "Add a validation warning when the field is missing or cannot be converted.", "type": "boolean", "default": false }, "multiple": { "title": "Combine all matches", "description": "Extract every matching element and join values into one cell.", "type": "boolean", "default": false }, "delimiter": { "title": "Multiple-value delimiter", "description": "Separator used when combining multiple matches.", "type": "string", "default": ", " }, "fallback": { "title": "Fallback value", "description": "Optional value to normalize when the selector returns no content.", "type": "string" } } }, "default": [ { "name": "title", "selector": "h3 a", "source": "attribute", "attribute": "title", "type": "string", "required": true }, { "name": "price", "selector": ".price_color", "type": "number", "pattern": "([0-9.]+)", "required": true }, { "name": "productUrl", "selector": "h3 a", "source": "attribute", "attribute": "href", "type": "url", "required": true } ] }, "maxItems": { "title": "Maximum rows", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum dataset and Excel rows across all pages.", "default": 100 }, "includeInvalidRows": { "title": "Include rows with warnings", "type": "boolean", "description": "Keep partially extracted records and expose validation warnings instead of dropping them.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 60, "type": "integer", "description": "Per-page HTTP timeout in seconds.", "default": 30 }, "sheetName": { "title": "Excel sheet name", "maxLength": 31, "type": "string", "description": "Worksheet name, up to 31 characters.", "default": "Web data" } } }, "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 Web Data To Excel Scraper 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: