Subito Scraper

{
  "title": "Subito Scraper Input",
  "type": "object",
  "schemaVersion": 1,
  "properties": {
    "productUrls": {
      "title": "Product URLs",
      "type": "array",
      "description": "Add one or more product page URLs to scrape. Example product URLs:\n\n- https://www.subito.it/informatica/hp-omen-siracusa-663668013.htm",
      "prefill": [
        "https://www.subito.it/informatica/hp-omen-siracusa-663668013.htm"
      ],
      "default": [],
      "editor": "stringList"
    },
    "categoryUrls": {
      "title": "List URLs",
      "type": "array",
      "description": "Add one or more List URLs to scrape.\n\nSupported page types with examples:\n\n- Search page: https://www.subito.it/annunci-italia/vendita/usato/?q=iphone\n- Filtered result page: https://www.subito.it/annunci-italia/vendita/usato/?q=iphone&shp=true\n- Seller page: https://www.subito.it/utente/132955576\n- Category page: https://www.subito.it/annunci-italia/vendita/informatica/\n\nLeave blank if using direct product URLs instead.\n\nThe `scrapeProductDetails` option (labelled Include product details) decides what each List URL produces. When it is enabled, the Actor visits each product page and returns the full detail records; when it is disabled, the Actor returns one list-level record per product card with the fields that are always included.",
      "prefill": [
        "https://www.subito.it/annunci-italia/vendita/usato/?q=iphone&shp=true",
        "https://www.subito.it/annunci-italia/vendita/informatica/"
      ],
      "default": [],
      "editor": "stringList"
    },
    "maxResultsPerScrape": {
      "title": "Maximum results",
      "type": "integer",
      "description": "Maximum number of product records to save.",
      "default": 20,
      "minimum": 1,
      "maximum": 100000
    },
    "usePagination": {
      "title": "Use pagination",
      "type": "boolean",
      "description": "If this option is enabled and a List URL has more than one page, the Actor continues through the following pages until it reaches the Maximum results limit. If the option is disabled, the Actor only scrapes the first page of each List URL.",
      "prefill": true,
      "default": true
    },
    "scrapeProductDetails": {
      "title": "Include product details",
      "type": "boolean",
      "default": true,
      "description": "If this option is enabled, the Actor visits each product page and adds the full product details to every record. If it is disabled, the Actor returns one list-level result record per product card.\n\nFields that are always included:\n\n- `url`\n- `canonical_url`\n- `product_id`\n- `sku`\n- `name`\n- `price`\n- `currency`\n- `main_image`\n- `image_count`\n- `location`\n- `badges`\n- `shipping_available`\n- `scraped_at`\n\nFields that are only added when this option is enabled (set to true), and not added when it is disabled:\n\n- `in_stock`\n- `brand`\n- `category`\n- `breadcrumbs`\n- `breadcrumb_urls`\n- `images`\n- `description`\n- `description_html`\n- `color`\n- `size`\n- `material`\n- `attributes`\n- `seller_name`\n- `seller_url`\n- `condition`\n- `published_at`\n- `shipping_cost`\n- `shipping_currency`\n- `buyer_protection_available`\n- `secure_payment_available`\n- `seller_rating_value`\n- `seller_published_ads`\n- `seller_online_ads`\n- `seller_completed_deals`\n- `seller_member_since`\n- `seller_response_time`"
    }
  }
}

{
  "actorSpecification": 1,
  "fields": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "url": {
        "type": [
          "string",
          "null"
        ],
        "format": "uri"
      },
      "product_id": {
        "type": [
          "string",
          "null"
        ],
        "description": "Stable source-side product identifier."
      },
      "name": {
        "type": [
          "string",
          "null"
        ]
      },
      "price": {
        "type": [
          "number",
          "null"
        ]
      },
      "currency": {
        "type": [
          "string",
          "null"
        ],
        "description": "ISO 4217 currency code."
      },
      "in_stock": {
        "type": [
          "boolean",
          "null"
        ]
      },
      "sku": {
        "type": [
          "string",
          "null"
        ]
      },
      "brand": {
        "type": [
          "string",
          "null"
        ]
      },
      "category": {
        "type": [
          "string",
          "null"
        ]
      },
      "breadcrumbs": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "breadcrumb_urls": {
        "type": "array",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "main_image": {
        "type": [
          "string",
          "null"
        ],
        "format": "uri"
      },
      "images": {
        "type": "array",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "description": {
        "type": [
          "string",
          "null"
        ]
      },
      "description_html": {
        "type": [
          "string",
          "null"
        ],
        "description": "Sanitized rich-text product description with structural HTML only."
      },
      "color": {
        "type": [
          "string",
          "null"
        ]
      },
      "size": {
        "type": [
          "string",
          "null"
        ]
      },
      "material": {
        "type": [
          "string",
          "null"
        ]
      },
      "attributes": {
        "type": "object",
        "description": "Additional source product attributes."
      },
      "seller_name": {
        "type": [
          "string",
          "null"
        ]
      },
      "seller_url": {
        "type": [
          "string",
          "null"
        ],
        "format": "uri"
      },
      "canonical_url": {
        "type": [
          "string",
          "null"
        ],
        "format": "uri"
      },
      "scraped_at": {
        "type": "string",
        "format": "date-time"
      },
      "badges": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Result-card badges displayed for the listing, such as Vetrina or Urgente."
      },
      "condition": {
        "type": [
          "string",
          "null"
        ],
        "description": "Displayed listing or vehicle condition."
      },
      "image_count": {
        "type": [
          "integer",
          "null"
        ],
        "description": "Number of images the result card reports for the listing."
      },
      "location": {
        "type": [
          "string",
          "null"
        ],
        "description": "Advertiser location label displayed on the result card."
      },
      "published_at": {
        "type": [
          "string",
          "null"
        ],
        "description": "Source publication timestamp when exposed in page metadata."
      },
      "shipping_available": {
        "type": "boolean",
        "description": "Whether the listing prominently offers shipping."
      },
      "shipping_cost": {
        "type": [
          "number",
          "null"
        ],
        "description": "Displayed shipping charge when shipping is offered."
      },
      "shipping_currency": {
        "type": [
          "string",
          "null"
        ],
        "description": "Currency of the displayed shipping charge."
      },
      "buyer_protection_available": {
        "type": "boolean",
        "description": "Whether Subito buyer protection is displayed for the listing."
      },
      "secure_payment_available": {
        "type": "boolean",
        "description": "Whether secure Subito payment is displayed for the listing."
      },
      "seller_rating_value": {
        "type": [
          "number",
          "null"
        ],
        "description": "Displayed seller rating average; not a product rating."
      },
      "seller_published_ads": {
        "type": [
          "integer",
          "null"
        ],
        "description": "Displayed seller lifetime approved-ad count."
      },
      "seller_online_ads": {
        "type": [
          "integer",
          "null"
        ],
        "description": "Displayed seller online-ad count."
      },
      "seller_completed_deals": {
        "type": [
          "integer",
          "null"
        ],
        "description": "Displayed seller completed-deal count."
      },
      "seller_member_since": {
        "type": [
          "string",
          "null"
        ],
        "description": "Displayed seller membership month in YYYY-MM form."
      },
      "seller_response_time": {
        "type": [
          "string",
          "null"
        ],
        "description": "Displayed seller response-time label."
      }
    },
    "required": [
      "url",
      "name"
    ]
  },
  "views": {
    "overview": {
      "title": "Overview",
      "transformation": {
        "fields": [
          "main_image",
          "url",
          "product_id",
          "name",
          "price",
          "currency",
          "in_stock",
          "brand",
          "seller_name",
          "scraped_at"
        ]
      },
      "display": {
        "component": "table",
        "properties": {
          "main_image": {
            "label": "Image",
            "format": "image"
          },
          "url": {
            "label": "Product URL",
            "format": "link"
          },
          "product_id": {
            "label": "Product ID",
            "format": "text"
          },
          "name": {
            "label": "Product name",
            "format": "text"
          },
          "price": {
            "label": "Current price",
            "format": "number"
          },
          "currency": {
            "label": "Currency",
            "format": "text"
          },
          "in_stock": {
            "label": "In stock",
            "format": "boolean"
          },
          "brand": {
            "label": "Brand",
            "format": "text"
          },
          "seller_name": {
            "label": "Seller",
            "format": "text"
          },
          "scraped_at": {
            "label": "Scraped at",
            "format": "datetime"
          }
        }
      }
    },
    "allFields": {
      "title": "All fields",
      "description": "Every stored field.",
      "transformation": {
        "fields": [
          "url",
          "product_id",
          "name",
          "price",
          "currency",
          "in_stock",
          "sku",
          "brand",
          "category",
          "breadcrumbs",
          "breadcrumb_urls",
          "main_image",
          "images",
          "description",
          "description_html",
          "color",
          "size",
          "material",
          "attributes",
          "seller_name",
          "seller_url",
          "canonical_url",
          "scraped_at",
          "badges",
          "condition",
          "image_count",
          "location",
          "published_at",
          "shipping_available",
          "shipping_cost",
          "shipping_currency",
          "buyer_protection_available",
          "secure_payment_available",
          "seller_rating_value",
          "seller_published_ads",
          "seller_online_ads",
          "seller_completed_deals",
          "seller_member_since",
          "seller_response_time"
        ]
      },
      "display": {
        "component": "table"
      }
    }
  }
}