{ "openapi": "3.0.1", "info": { "title": "SHEIN Product Scraper", "description": "[💰 $0.70 / 1K] Scrape SHEIN search, category, selection, tag, and product pages over HTTP. Get clean product IDs, titles, images, prices, discounts, URLs, and optional detail-page metadata in an Apify dataset.", "version": "0.2", "x-build-id": "jzQQSi38TGQoDLCm3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fetchfinch~shein-product-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fetchfinch-shein-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fetchfinch~shein-product-scraper/runs": { "post": { "operationId": "runs-sync-fetchfinch-shein-product-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/fetchfinch~shein-product-scraper/run-sync": { "post": { "operationId": "run-sync-fetchfinch-shein-product-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": { "startUrl": { "title": "Start URL", "type": "string", "description": "One SHEIN search/category/product URL. This matches the common public actor input format.", "default": "" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Additional SHEIN search/category/product URLs. Sitemap discovery is used only when this and searchTerms are empty.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A SHEIN page URL", "type": "string" } } }, "default": [] }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Terms such as bluetooth headphones. Each term becomes a SHEIN /pdsearch/ URL.", "items": { "type": "string" }, "default": [] }, "locale": { "title": "SHEIN locale", "type": "string", "description": "SHEIN hostname prefix, for example us, uk, de, or au.", "default": "us" }, "results_wanted": { "title": "Results wanted", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum unique product records to emit. This name matches the public competitor actor." }, "maxProducts": { "title": "Maximum products (legacy alias)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Alias for results_wanted, retained for backwards compatibility with the MVP." }, "page": { "title": "Starting page", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Page number to start with for listing URLs.", "default": 1 }, "maxPages": { "title": "Maximum listing pages", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum pages to fetch per listing URL.", "default": 1 }, "extractDetails": { "title": "Enrich with product pages", "type": "boolean", "description": "Fetch each product detail page to add descriptions, brand, JSON-LD, prices, and availability. This uses one additional request per product.", "default": false }, "maxDetailPages": { "title": "Maximum detail pages", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Limit optional detail-page enrichment requests.", "default": 20 }, "maxSitemaps": { "title": "Maximum sitemaps", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum sitemap documents to fetch, including the root sitemap.", "default": 10 }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Delay used between HTTP requests. Keep this conservative for personal use.", "default": 1000 }, "includeHtml": { "title": "Include HTML", "type": "boolean", "description": "Include a truncated product-detail HTML snapshot in enriched product records.", "default": false }, "proxyUrl": { "title": "Proxy URL", "type": "string", "description": "Optional HTTP/HTTPS proxy URL. SHEIN_PROXY_URL is used when this is empty.", "default": "" }, "proxyConfiguration": { "title": "Apify proxy configuration", "type": "object", "description": "Optional standard Apify proxy configuration. Used when proxyUrl and SHEIN_PROXY_URL are empty.", "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 } } } } } } } } } }