{ "openapi": "3.0.1", "info": { "title": "Newegg Product Scraper", "description": "Scrape Newegg product listings in bulk: title, brand, price, list price, discount, rating, reviews, shipping, model number, stock and image. Paste category or search URLs (or keywords) and it paginates deep, 96 products per page. Clean JSON/CSV, one row per product. No login.", "version": "0.1", "x-build-id": "StjsmV6LGcYNsFxAB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapeworks~newegg-product-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapeworks-newegg-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapeworks~newegg-product-scraper/runs": { "post": { "operationId": "runs-sync-scrapeworks-newegg-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapeworks~newegg-product-scraper/run-sync": { "post": { "operationId": "run-sync-scrapeworks-newegg-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Newegg listing URLs", "uniqueItems": true, "type": "array", "description": "One or more newegg.com listing pages to scrape. Each can be a category or subcategory 'browse' page (e.g. https://www.newegg.com/Desktop-Graphics-Cards/SubCategory/ID-48), a store or brand-store page, or a keyword search-results page (e.g. https://www.newegg.com/p/pl?d=rtx+4090). To get a URL: open newegg.com, browse or search to the products you want, and copy the page URL from your browser. Every URL is paginated DEEP automatically (96 products per page), so a few URLs return thousands of rows. Category / subcategory / store browse URLs are the MOST RELIABLE input; keyword-search pages guard harder and are routed through the proxy on a block. Results are billed per product, so more URLs = more rows.", "items": { "type": "string" } }, "searchKeywords": { "title": "Search keywords (optional)", "uniqueItems": true, "type": "array", "description": "Optional convenience: keywords to search Newegg for (each becomes a https://www.newegg.com/p/pl?d= search and is paginated deep). Newegg's keyword-search route guards harder than its category pages, so results here run through the residential proxy on a block; if you get few/no rows for a keyword, use the matching category/subcategory 'browse' URL in the Newegg listing URLs field instead (that path is the most reliable).", "items": { "type": "string" } }, "maxResultsPerUrl": { "title": "Max results per start URL", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum products to return for EACH start URL or keyword. The actor paginates automatically (96 products per page). Set high to pull a whole category; lower it to sample.", "default": 5000 }, "maxPagesPerUrl": { "title": "Max pages per start URL", "minimum": 1, "maximum": 500, "type": "integer", "description": "Hard limit on how many result pages to fetch per start URL (a safety cap on top of Max results per start URL). Newegg serves 96 products per page, so 100 pages is roughly 9,600 products. The actor also stops automatically at the listing's real last page.", "default": 100 }, "maxResults": { "title": "Max results overall (optional)", "minimum": 1, "maximum": 500000, "type": "integer", "description": "Optional overall cap across ALL start URLs and keywords combined. Leave empty for no overall cap (each URL is still bounded by Max results / Max pages per URL). Useful to cap total billed rows for a run." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Fallback proxy for reaching newegg.com. The actor fetches DIRECTLY first with a real Chrome TLS fingerprint (Newegg's server-rendered category/browse pages return fine this way) and only routes through this proxy - rotating exits - if a request is blocked (e.g. on Newegg's stricter keyword-search route). The default (Apify Residential, US) is a safe fallback; leave it in place. Keep the country US so prices stay in USD.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }