{
  "openapi": "3.0.1",
  "info": {
    "title": "Shopify Products Scraper — Descriptions, Specs & Tags",
    "description": "Shopify Products Scraper extracts detailed product data from Shopify stores. Collect product titles, prices, variants, SKUs, images, descriptions, and availability for eCommerce research, price tracking, and catalog automation.",
    "version": "0.1",
    "x-build-id": "pRAYGSnCbXZcakDNg"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/scrapio~shopify-products-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-scrapio-shopify-products-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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/scrapio~shopify-products-scraper/runs": {
      "post": {
        "operationId": "runs-sync-scrapio-shopify-products-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/scrapio~shopify-products-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-scrapio-shopify-products-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
          "shopDomains": {
            "title": "🛍️ Shopify stores",
            "type": "array",
            "description": "One or more Shopify storefronts. Accepts a full URL (https://rothys.com), a bare hostname (rothys.com) or a myshopify domain (example.myshopify.com). Every store is processed in turn. Example: [\"https://www.tentree.com\", \"https://rothys.com\"].",
            "items": {
              "type": "string"
            }
          },
          "startUrls": {
            "title": "🔗 Store URLs (legacy field)",
            "type": "array",
            "description": "The original store-URL field, kept so an existing input file keeps working unchanged. Leave empty and use Shopify stores above. Used only when Shopify stores is empty.",
            "items": {
              "type": "string"
            }
          },
          "parseDescription": {
            "title": "📝 Parse the product description",
            "type": "boolean",
            "description": "Turn the merchant's description into plain text plus structure fields (descriptionText, descriptionWordCount, bullets, headings, spec pairs). Turn this off to skip description parsing entirely; the description filters below then have nothing to work on. Default is on.",
            "default": true
          },
          "descriptionOutput": {
            "title": "📄 How much description detail",
            "enum": [
              "text",
              "structure",
              "full"
            ],
            "type": "string",
            "description": "Plain text only = descriptionText and descriptionWordCount. Text + structure adds bullets, headings, links and images found inside the description. Text + structure + spec pairs also returns label/value pairs such as \"Material: 100% organic cotton\". Default is text + structure + spec pairs.",
            "default": "full"
          },
          "extractSpecPairs": {
            "title": "🔬 Extract spec pairs",
            "type": "boolean",
            "description": "Pull \"Label: value\" lines out of the description into descriptionSpecs. Switch off to keep the structure fields but drop the spec pairs. Only applies when the detail level above is set to text + structure + spec pairs. Default is on.",
            "default": true
          },
          "specLabelSeparators": {
            "title": "➗ Spec label separators",
            "type": "array",
            "description": "Characters that separate a spec label from its value. A colon binds directly to the label (\"Fit: Oversized\"); a dash or pipe must stand alone between spaces. Default is colon, dash and pipe.",
            "items": {
              "type": "string"
            }
          },
          "keepDescriptionHtml": {
            "title": "🧾 Keep the original description markup",
            "type": "boolean",
            "description": "Adds a descriptionHtml column holding the merchant's description exactly as published, alongside the parsed fields. Adds several kilobytes per row. Default is off.",
            "default": false
          },
          "parseTagAttributes": {
            "title": "🏷️ Parse the tag taxonomy",
            "type": "boolean",
            "description": "Split the shop's tags into a key/value attribute map (tagAttributes) and a list of unstructured tags (plainTags). Turn off to return tags as a plain array only. Default is on.",
            "default": true
          },
          "tagFormat": {
            "title": "🧩 Tag convention",
            "enum": [
              "auto",
              "pair",
              "three",
              "arrow",
              "underscore",
              "none"
            ],
            "type": "string",
            "description": "Auto-detect handles all four conventions in the same run and is recommended. Pick a single convention to parse only that shape and leave everything else as a plain tag. Examples: key:value = \"Type:CORE TRUNK\"; key:sub:value = \"storefront:category:Womens Shoes\"; namespace::key => value = \"brand::edition => limited\"; key_value = \"collection_men\". Default is auto-detect.",
            "default": "auto"
          },
          "mergeTagKeyCase": {
            "title": "🔠 Merge tag keys that differ only by case",
            "type": "boolean",
            "description": "Some shops publish both \"Category:\" and \"category:\". Off keeps them as two separate keys exactly as the merchant wrote them. On merges them into one lower-case key whose value list is the union of both. Default is off.",
            "default": false
          },
          "emitPlainTags": {
            "title": "🔖 Return the unstructured tags too",
            "type": "boolean",
            "description": "Include the plainTags list of tags that carry no key/value structure. plainTagCount is always returned either way, so attributeTagCount + plainTagCount always equals tagCount. Default is on.",
            "default": true
          },
          "descriptionKeywords": {
            "title": "🔍 Description must contain",
            "type": "array",
            "description": "Keep only products whose description text contains at least one of these phrases (case-insensitive). Example: [\"organic cotton\"]. Leave empty for no keyword filter.",
            "items": {
              "type": "string"
            }
          },
          "excludeDescriptionKeywords": {
            "title": "🚫 Description must NOT contain",
            "type": "array",
            "description": "Drop products whose description text contains any of these phrases (case-insensitive). Example: [\"gift card\"].",
            "items": {
              "type": "string"
            }
          },
          "minDescriptionWords": {
            "title": "📏 Minimum description words",
            "minimum": 0,
            "type": "integer",
            "description": "Keep only products whose description reaches this many words. Products with no description are dropped when this is above 0. Example: 20. Default is 0 (no minimum).",
            "default": 0
          },
          "requireTagKeys": {
            "title": "🗝️ Require these tag keys",
            "type": "array",
            "description": "Keep only products whose tag taxonomy contains every one of these keys. Example: [\"storefront:category\"]. Matching ignores case.",
            "items": {
              "type": "string"
            }
          },
          "tagAttributeFilters": {
            "title": "🎯 Require these tag attribute values",
            "type": "array",
            "description": "Keep only products whose tag taxonomy holds a specific value, written as key=value. Example: [\"Type=CORE TRUNK\"]. Several entries combine with AND. Matching ignores case.",
            "items": {
              "type": "string"
            }
          },
          "vendors": {
            "title": "🏭 Vendors",
            "type": "array",
            "description": "Keep only products from these vendors (case-insensitive exact match). Example: [\"Rothy's\"].",
            "items": {
              "type": "string"
            }
          },
          "productTypes": {
            "title": "📚 Product types",
            "type": "array",
            "description": "Keep only products with one of these product types (case-insensitive exact match). Note that many shops leave product type blank and put the category in a tag instead - use the tag filters above for those.",
            "items": {
              "type": "string"
            }
          },
          "maxProductsPerShop": {
            "title": "📦 Max products per shop",
            "minimum": 0,
            "type": "integer",
            "description": "How many products to read from each store. 0 means the whole catalogue. Example: 50 returns the first 50 products of every store listed. Default is 50."
          },
          "maxItems": {
            "title": "🔢 Max items (legacy field)",
            "minimum": 0,
            "type": "integer",
            "description": "The original per-store limit, kept so an existing input file keeps working unchanged. Used only when Max products per shop is empty."
          },
          "proxyConfiguration": {
            "title": "🌐 Proxy configuration",
            "type": "object",
            "description": "Choose which proxies to use. By default no proxy is used. If a store does not answer on the default route the run automatically tries an alternative one."
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}