{ "openapi": "3.0.1", "info": { "title": "Naver Blog Scraper - Clean Content & Review Intelligence", "description": "Scrapes titles of websites using Crawlee and BeautifulSoup.The only Naver Blog scraper that properly extracts clean content from Naver's iframe architecture. Sponsor detection, metadata, engagement stats, and Google Sheets integration.", "version": "0.0", "x-build-id": "x9d2XUk9MF3iC4AFO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hanpro~naver-blog-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hanpro-naver-blog-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hanpro~naver-blog-scraper/runs": { "post": { "operationId": "runs-sync-hanpro-naver-blog-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hanpro~naver-blog-scraper/run-sync": { "post": { "operationId": "run-sync-hanpro-naver-blog-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Blog Post URLs", "type": "array", "description": "List of Naver Blog post URLs to scrape directly. Example: https://blog.naver.com/username/123456789. When provided, keyword search is skipped.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyword": { "title": "Search Keyword", "type": "string", "description": "Korean keyword to search on Naver Blog (e.g. '강남 맛집', '셀프 인테리어'). Ignored when startUrls is provided." }, "maxPosts": { "title": "Max Posts", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of blog posts to scrape. Each post makes 2-3 HTTP requests (page + iframe + like API).", "default": 10 }, "sort": { "title": "Sort Order", "enum": [ "sim", "date" ], "type": "string", "description": "Sort order for keyword search results. 'sim' ranks by relevance, 'date' shows newest posts first.", "default": "sim" }, "dateStart": { "title": "Date Start", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only include posts published on or after this date. Format: YYYY-MM-DD. Applies to keyword search mode only." }, "dateEnd": { "title": "Date End", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only include posts published on or before this date. Format: YYYY-MM-DD. Applies to keyword search mode only." }, "contentType": { "title": "Content Type", "enum": [ "text", "html" ], "type": "string", "description": "Choose output format for blog content. 'text' returns clean readable text. 'html' returns the original HTML markup with scripts/styles removed.", "default": "text" }, "sponsoredFilter": { "title": "Sponsored Content Filter", "enum": [ "all", "organic_only", "sponsored_only" ], "type": "string", "description": "Filter posts by sponsorship status. Detects Korean sponsor keywords (협찬, 광고, 체험단) and organic keywords (내돈내산, 직접 구매).", "default": "all" }, "deduplicate": { "title": "Remove Duplicates", "type": "boolean", "description": "Automatically skip duplicate blog posts based on URL. Recommended when scraping keyword search results where the same post may appear multiple times.", "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 } } } } } } } } } }