{
  "openapi": "3.0.1",
  "info": {
    "title": "WooCommerce Scraper",
    "description": "Scrape products, variations, prices, stock, categories and customer reviews from WooCommerce stores, including stores that have turned their product API off. Start from store domains, URLs or a search query. Export JSON, CSV or Excel, or call it as an API.",
    "version": "0.0",
    "x-build-id": "A0jNqLFNN3IMPIwWM"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/autofacts~woocommerce-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-autofacts-woocommerce-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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/autofacts~woocommerce-scraper/runs": {
      "post": {
        "operationId": "runs-sync-autofacts-woocommerce-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/autofacts~woocommerce-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-autofacts-woocommerce-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": "WooCommerce store start URLs",
            "type": "array",
            "description": "A WooCommerce store URL: the store root, a category page, a tag page, a search URL or a single product page (category, tag and search URLs need a store with an open API). The scraper asks the store what a URL is, so you do not need to know how it configured its permalinks. Mix several stores in one run. To name stores by bare domain, use the <b>Store domains</b> field below instead.",
            "items": {
              "type": "object",
              "required": [
                "url"
              ],
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL of a web page",
                  "format": "uri"
                }
              }
            }
          },
          "domains": {
            "title": "Store domains",
            "type": "array",
            "description": "Bare domains, one per line (<code>mystore.com</code>) — the simplest way to name whole stores. Each one is crawled like a start URL of <code>https://mystore.com/</code>. Can be combined with start URLs.",
            "items": {
              "type": "string"
            }
          },
          "maxProducts": {
            "title": "Max products",
            "minimum": 0,
            "type": "integer",
            "description": "How many product records to save in this run, across all stores. Each product is one billed result, so this is the run's cost cap for products. <code>0</code> = no limit — bound spend with the run's <b>Max total charge</b> setting instead. Categories and reviews are capped separately and never count against this number."
          },
          "maxProductsPerStore": {
            "title": "Max products per store",
            "minimum": 0,
            "type": "integer",
            "description": "Cap for each individual store in the run, so one large catalog cannot consume the whole budget before the next start URL is reached. <code>0</code> = no per-store limit. Two start URLs on the same store share one cap.",
            "default": 0
          },
          "includeVariations": {
            "title": "Include product variations",
            "type": "boolean",
            "description": "Fetch every variation of variable products (size/colour combinations) with its own SKU, price and stock, nested inside the product record. Variations are <b>not billed separately</b>, but they cost extra requests: stores average about 7 variations per variable product, so a variation-heavy catalog takes noticeably longer. When off, a variable product still produces one record with a single synthetic variant, and <code>extraInfo.variationsOmitted</code> reports how many were skipped.",
            "default": true
          },
          "includeReviews": {
            "title": "Include product reviews",
            "type": "boolean",
            "description": "Save customer reviews as separate <code>Review</code> records (rating, text, reviewer, verified-buyer flag, date), one per review, joined to the product by <code>productId</code>. Reviews are billed per review. Only available on stores with an open Store API — the HTML fallback has no review surface, and the run says so in its log rather than silently producing none.",
            "default": false
          },
          "maxReviewsPerProduct": {
            "title": "Max reviews per product",
            "minimum": 0,
            "type": "integer",
            "description": "Newest reviews to keep for each product. <code>0</code> = all of them. Review counts are unbounded — one surveyed store carries 15,152 reviews on 96 products — so keep this small unless reviews are what you came for.",
            "default": 20
          },
          "query": {
            "title": "Search query",
            "type": "string",
            "description": "Search term. Every store root or domain in the run is searched for it instead of being crawled whole, and a category or tag URL is searched within that category or tag. Requires a store with an open API — stores on the HTML fallback path have no search surface and report an error for that URL rather than silently crawling the whole catalog."
          },
          "allowHtmlFallback": {
            "title": "Allow HTML fallback for stores without an open API",
            "type": "boolean",
            "description": "A meaningful share of WooCommerce stores have their JSON API disabled or firewalled (28 of 53 stores had it open in our own 2026-09-03 survey). For those, the scraper falls back to parsing product pages directly. This works, but costs roughly <b>100x more requests and 15x more traffic per product</b> than the API path, so it is billed as a separate surcharge event and capped below. Turn this off to scrape only stores with an open API.",
            "default": true
          },
          "maxHtmlDetailRecords": {
            "title": "Max HTML-fallback records per run",
            "minimum": 0,
            "type": "integer",
            "description": "Hard cap on how many products may be produced through the expensive HTML fallback path in one run. Only applies when the fallback is enabled. Set to <code>0</code> for unlimited.",
            "default": 200
          },
          "maxConcurrency": {
            "title": "Max concurrent requests",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "Most WooCommerce stores are small self-hosted WordPress sites and start returning errors under load — the default of 2 is deliberately conservative and is what keeps runs from being throttled or blocked. Raise it only for stores you know are on serious hosting.",
            "default": 2
          },
          "proxy": {
            "title": "Proxy configuration",
            "type": "object",
            "description": "Select proxies to be used by your crawler. The scraper escalates on its own when a store's firewall blocks a request, so datacenter proxies are a reasonable default — residential is only needed for the minority of heavily protected stores."
          },
          "maxResults": {
            "title": "Max results",
            "minimum": 0,
            "type": "integer",
            "description": "Maximum number of products to return. Hidden parameter, overrides maxProducts if set.",
            "default": 0
          },
          "maxRequestsPerCrawl": {
            "title": "Max products (deprecated name)",
            "minimum": 0,
            "type": "integer",
            "description": "Deprecated alias of maxProducts, kept so tasks saved before version 0.2.0 keep working. Ignored when maxProducts is set."
          }
        }
      },
      "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
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "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
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}