{ "openapi": "3.0.1", "info": { "title": "Product Feed Scraper: Google Merchant & XML Catalogs", "description": "Parse public Google Merchant and RSS 2.0 product feeds: GTIN, MPN, brand, price split into amount and currency, sale price, availability, shipping and images. The catalogue retailers publish deliberately.", "version": "0.0", "x-build-id": "eJGbEPxtQMflA2O2Y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/arman-bd~product-feed-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-arman-bd-product-feed-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/arman-bd~product-feed-scraper/runs": { "post": { "operationId": "runs-sync-arman-bd-product-feed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/arman-bd~product-feed-scraper/run-sync": { "post": { "operationId": "run-sync-arman-bd-product-feed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "feedUrls" ], "properties": { "feedUrls": { "title": "Product feed URLs", "type": "array", "description": "Public product feed URLs. Retailers usually link theirs from the Google Merchant Center setup docs of whichever cart they use. common paths are '/google-shopping.xml', '/googlebase.xml' and, on WooCommerce, '/wp-content/uploads/woo-feed/google/xml/.xml'. Gzipped feeds (.xml.gz or Content-Encoding: gzip) are decompressed automatically. A feed that 404s or is not RSS is recorded in RUN_SUMMARY.failures and the run continues.", "items": { "type": "string" } }, "maxProducts": { "title": "Max products (whole run)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Total saved products for the entire run, applied after filtering and shared evenly across the feeds. This is a ceiling on what you are charged, not a per-feed allowance: 200 across five feeds saves 200 products, not 1000. A feed that fails or runs short passes its unspent share to the others, so the total is reached whenever the feeds hold enough products between them. Catalogues run to tens of thousands of items, so the default stops a run at 1000. 0 means every product in every feed, however large.", "default": 1000 }, "maxProductsPerFeed": { "title": "Max products (former field name)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "The earlier name of 'maxProducts', accepted so existing calls keep working. It is applied as a run-wide total, exactly like 'maxProducts'; set 'maxProducts' instead." }, "inStockOnly": { "title": "In stock only", "type": "boolean", "description": "Keep only products whose availability is 'in_stock'. Feeds write this as either 'in stock' or 'in_stock' and both are recognised. Products that omit availability entirely are dropped by this filter, because there is no evidence they are buyable.", "default": false }, "brandFilter": { "title": "Brand filter", "type": "array", "description": "Keep only products whose 'g:brand' exactly matches one of these, case-insensitively. Empty keeps every brand. Note that many small merchants leave 'g:brand' blank or set it to their own store name.", "items": { "type": "string" } }, "minPrice": { "title": "Minimum price", "minimum": 0, "type": "integer", "description": "Keep only products priced at or above this amount, in the feed's own currency. feeds are single-currency, but no conversion is done, so check 'currency' before relying on it. Products with an unreadable price are dropped when this is set. Leave empty for no lower bound." }, "maxPrice": { "title": "Maximum price", "minimum": 0, "type": "integer", "description": "Keep only products priced at or below this amount, in the feed's own currency. Products with an unreadable price are dropped when this is set. Leave empty for no upper bound." } } }, "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 } } } } } } } } } }