{ "openapi": "3.0.1", "info": { "title": "Quora Scraper By Language Portal", "description": "Quora Scraper: Extract questions, answers, topics, authors, timestamps, and engagement data from selected language portals. Analyze discussions, audience interests, content trends, and expert insights for research, competitor analysis, SEO, and content strategy.", "version": "0.1", "x-build-id": "I4GeEC9RQiqeH6cYi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-empire~quora-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-empire-quora-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-empire~quora-scraper/runs": { "post": { "operationId": "runs-sync-api-empire-quora-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-empire~quora-scraper/run-sync": { "post": { "operationId": "run-sync-api-empire-quora-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "portal": { "title": "🌍 Language Portal", "enum": [ "EN", "ES", "FR", "DE", "IT", "JP", "ID", "PT", "HI", "NL", "DA", "FI", "NO", "SV", "MR", "BN", "TA", "AR", "HE", "GU", "KN", "ML", "TE", "PL" ], "type": "string", "description": "Which localized Quora portal to search and scrape. Each is a separate site ({lang}.quora.com) with its own questions and community. Example: ES scrapes es.quora.com and searches site:es.quora.com. Default is EN (www.quora.com).", "default": "EN" }, "searchQueries": { "title": "🔍 Search Keywords", "type": "array", "description": "Keywords to search on the selected portal. Each keyword is resolved to relevant Quora URLs (site:{portal}.quora.com) and scraped automatically. Leave empty to only use direct URLs.", "items": { "type": "string" } }, "directUrls": { "title": "🔗 Direct Quora URLs", "type": "array", "description": "Paste Quora URLs to scrape in bulk — questions, profiles (/profile/...), topics (/topic/...) or spaces (/q/...). Plain www.quora.com URLs are automatically routed to the chosen portal host. Example: https://es.quora.com/Para-qué-se-usa-Python", "items": { "type": "string" } }, "maxResults": { "title": "📊 Maximum Results", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Max results per search keyword, and max answers scraped per question URL. Example: 10. Default is 50.", "default": 50 }, "includeHtmlContent": { "title": "📄 Include Raw HTML", "type": "boolean", "description": "✅ On: add a contentHtml field to each item — rendered HTML markup (paragraphs, links, images) alongside the plain text the scraper already emits, for downstream parsing. ⬜ Off: clean text only. Default is off.", "default": false }, "aiEnhancement": { "title": "🤖 AI Enrichment (Translate + Detect)", "type": "boolean", "description": "✅ On: detect each item's language and translate its text/title to English, adding aiLanguage + aiTranslatedText + aiTranslatedTitle. Best-effort — fields are null if the AI call fails or no key is set. ⬜ Off (default): no AI, no AI cost.", "default": false }, "aiModel": { "title": "🤖 AI Model / Provider", "enum": [ "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "gpt-4o-mini", "gpt-4o", "gpt-4.1-mini", "gemini-2.0-flash-lite", "gemini-2.0-flash", "gemini-2.5-flash", "grok-3-mini", "deepseek-chat", "sonar", "mistral-small-latest" ], "type": "string", "description": "Provider auto-detected from the name: claude-*=Anthropic, gpt-*/o1/o3=OpenAI, gemini-*=Google, grok-*=xAI, deepseek-*=DeepSeek, sonar*=Perplexity, mistral-*=Mistral. Cheaper mini/flash/haiku/lite models are recommended for translation.", "default": "claude-haiku-4-5" }, "aiApiKey": { "title": "🔑 AI API Key", "type": "string", "description": "API key for the selected provider. If blank, the matching environment variable is used: ANTHROPIC_API_KEY / OPENAI_API_KEY / GEMINI_API_KEY / XAI_API_KEY / DEEPSEEK_API_KEY / PERPLEXITY_API_KEY / MISTRAL_API_KEY. Only used when AI Enrichment is on." }, "requestDelay": { "title": "⏱️ Request Delay (seconds)", "minimum": 0, "maximum": 30, "type": "number", "description": "Polite delay (seconds) before each request. Example: 0.5. Default is 0.5.", "default": 0.5 }, "concurrency": { "title": "🔀 Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of pages fetched in parallel. Example: 6. Default is 6.", "default": 6 }, "useBrowserFallback": { "title": "🧭 Headless Browser Fallback", "type": "boolean", "description": "Render hard-blocked pages in a real headless browser as a last resort. Default is on.", "default": true }, "proxyConfiguration": { "title": "🛡️ Proxy Configuration", "type": "object", "description": "Proxy settings. The scraper starts DIRECT (no proxy) and only escalates to datacenter, then residential, if Quora blocks the request — sticking with residential afterwards." } } }, "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 } } } } } } } } } }