FAQ Question Answer Extractor
Pricing
from $6.50 / 1,000 faq source page scanneds
Extract FAQ question-answer pairs from visible HTML and FAQPage schema, reconcile duplicates, and flag schema/visible mismatches
You can access the FAQ Question Answer Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "QLXBFG8LZm3pj0cT3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~faq-question-answer-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-faq-question-answer-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~faq-question-answer-extractor/runs": { "post": { "operationId": "runs-sync-junipr-faq-question-answer-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~faq-question-answer-extractor/run-sync": { "post": { "operationId": "run-sync-junipr-faq-question-answer-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": { "pageUrls": { "title": "FAQ page URLs", "type": "array", "description": "Public URLs containing visible FAQs or FAQPage structured data.", "items": { "type": "string" }, "default": [] }, "startUrls": { "title": "Additional page URLs", "type": "array", "description": "Optional public page URLs; pageUrls is preferred for role clarity.", "items": { "type": "string" }, "default": [] }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Optional public XML sitemap URLs. Accepted pages remain bounded by maxPages.", "items": { "type": "string" }, "default": [] }, "htmlInputs": { "title": "Captured FAQ HTML", "type": "array", "description": "Optional records with sourceUrl and html or currentHtml for deterministic extraction.", "items": { "type": "object" }, "default": [] }, "includeFaqSchema": { "title": "Extract FAQPage structured data", "type": "boolean", "description": "Extract FAQPage structured data when present.", "default": true }, "compareVisibleAndSchema": { "title": "Compare visible and structured answers", "type": "boolean", "description": "Compare visible FAQ text against FAQPage structured data.", "default": true }, "dedupeQuestions": { "title": "Deduplicate questions across pages", "type": "boolean", "description": "Deduplicate repeated questions across scanned pages.", "default": true }, "questionFilters": { "title": "Question filters", "type": "array", "description": "Optional case-insensitive phrases. Only questions containing at least one phrase are retained.", "items": { "type": "string" }, "default": [] }, "maxFaqPairsPerPage": { "title": "Maximum FAQ pairs per page", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum FAQ question-answer pairs to emit per page.", "default": 50 }, "allowedDomains": { "title": "Allowed domains", "type": "array", "description": "Optional hostname allowlist for fetched pages.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "Maximum fetched pages", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum pages to fetch in one run.", "default": 1 }, "maxDepth": { "title": "Link depth", "minimum": 0, "maximum": 0, "type": "integer", "description": "General link discovery is disabled.", "default": 0 }, "includeEvidence": { "title": "Include evidence", "type": "boolean", "description": "Include short source evidence snippets in output rows.", "default": true }, "includeRawSnapshots": { "title": "Store raw snapshots", "type": "boolean", "description": "Opt in to raw HTML artifacts in key-value storage.", "default": false }, "requestDelayMs": { "title": "Request delay in milliseconds", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Delay in milliseconds between outbound page requests.", "default": 250 }, "timeoutMs": { "title": "Request timeout in milliseconds", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Maximum time in milliseconds to wait for a page request.", "default": 15000 }, "userAgentMode": { "title": "User-agent mode", "enum": [ "standard", "browser" ], "type": "string", "description": "User agent profile to use for public page requests.", "default": "standard" }, "maxChargeUsd": { "title": "Maximum charge", "minimum": 0, "maximum": 15, "type": "number", "description": "Maximum estimated PPE spend before the actor exits gracefully.", "default": 15 }, "includeReport": { "title": "Write reports", "type": "boolean", "description": "Write the markdown summary report to the run key-value store.", "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 FAQ Question Answer 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: