{ "openapi": "3.0.1", "info": { "title": "Mohito Scraper", "description": "Fast and reliable scraper for extracting product data from Mohito.com (LPP Group fashion retailer). Uses Algolia API for lightning-fast data extraction - scrape 100+ products in under 1 second.", "version": "1.0", "x-build-id": "kYSv1nSK7kCAe3KCj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/trev0n~mohito-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-trev0n-mohito-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/trev0n~mohito-scraper/runs": { "post": { "operationId": "runs-sync-trev0n-mohito-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/trev0n~mohito-scraper/run-sync": { "post": { "operationId": "run-sync-trev0n-mohito-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "start_urls": { "title": "Start URLs", "type": "array", "description": "List of Mohito category/listing URLs to scrape. Leave empty to run in API-only mode (use /product endpoint). Must be category or subcategory pages (e.g., https://www.mohito.com/pl/pl/ubrania/kurtki-plaszcze).", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "category_filter": { "title": "Category Filter", "type": "array", "description": "Filter by main categories (e.g., ['ubrania', 'akcesoria', 'buty']). Leave empty to scrape all categories.", "default": [], "items": { "type": "string" } }, "subcategory_filter": { "title": "Subcategory Filter", "type": "array", "description": "Filter by subcategories (e.g., ['kurtki-plaszcze', 'sukienki', 'spodnice']). Leave empty to scrape all subcategories.", "default": [], "items": { "type": "string" } }, "product_seo_keyword_filter": { "title": "Product Keyword Filter", "type": "array", "description": "Filter by product SEO keywords in URL (e.g., ['kurtka', 'sukienka']). Leave empty to scrape all products.", "default": [], "items": { "type": "string" } }, "deduplicate_across_all_start_urls": { "title": "Deduplicate Products", "type": "boolean", "description": "If true, prevents the same product from appearing multiple times when scraping multiple categories or URLs.", "default": true }, "max_results": { "title": "Max Results", "minimum": 0, "type": "integer", "description": "Maximum number of products to scrape. Set to 0 for unlimited.", "default": 100 }, "scrape_product_details": { "title": "Scrape Product Details", "type": "boolean", "description": "If true, visits each product page to extract detailed information (sizes, materials, description, all images). This is slower but provides more complete data.", "default": false }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of pages to process in parallel. Higher values = faster scraping but more memory usage. Recommended: 3-5 for DOM scraping.", "default": 5 }, "maxRequestRetries": { "title": "Max Request Retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times to retry failed requests.", "default": 3 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings to avoid blocking. Residential proxies recommended for best results.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }