action dataflowkit_serp {
  label: "Collect search results from search engines"
  description: "To crawl search engine result pages, you can use `/serp` endpoint. SERP collection service extracts a list of organic results, news, images, and more.  Specify configuration parameters, such as country or languages, to customize output SERP data.\nThe following search engines are supported\n\n- google\n- google-image\n- google-news\n- google-shopping\n- bing\n- duckduckgo\n- baidu\n- yandex\n\n\nGenerate ready-to-run code for your favorite language at [https://dataflowkit.com/serp](https://dataflowkit.com/serp)"
  provider: dataflowkit
  method: POST
  path: "/serp"
  encoding: json
  input: {
    type: "object"
    required: ["format", "name", "proxy", "type", "url"]
    properties: {
      fields: {
        type: "array"
        description: "Specify CSS selectors (patterns) used to gather data from Search Engine Result Pages.\n\nReady-to-use payloads for collecting search results from the most popular Search Engines are available. These payloads are customizable, though.\n"
        items: {
          type: "object"
          required: ["attrs", "name", "selector", "type"]
          properties: {
            attrs: {
              type: "array"
              description: "A set of attributes to extract from a Field. Find more information about attributes"
              items: {
                type: "string"
                enum: ["text", "href", "src", "alt"]
              }
            }
            details: {
              description: "Details themself represent independent Parse request that extracts data from linked pages."
              type: "object"
            }
            filters: {
              type: "array"
              description: "Filters are used to pre-processing of text data when extracting."
              items: {
                type: "object"
              }
            }
            name: {
              type: "string"
              description: "Field name is used to aggregate results."
            }
            selector: {
              type: "string"
              description: "Selector represents a CSS selector for data extraction within the given block."
            }
            type: {
              type: "integer"
              description: "Selector type. ( 0 - image, 1 - text, 2 - link)"
              enum: [0, 1, 2]
            }
          }
        }
      }
      format: {
        type: "string"
        description: "Extracted data is returned either in CSV, MS Excel, JSON, JSON(Lines) or XML format."
        enum: ["csv", "json", "jsonl", "excel", "xml"]
      }
      name: {
        type: "string"
        description: "Collection name."
      }
      pageNum: {
        type: "integer"
        description: "Specify number of pages to crawl."
      }
      proxy: {
        type: "string"
        description: "Always specify proxy for sending SERP requests. Add choosen [country ISO code](https://en.wikipedia.org/wiki/ISO_3166-2) to `country-` value to send requests through a proxy in the specified country. Use `country-any` to use random geo-targets."
      }
      type: {
        type: "string"
        description: "For SERP requests you should _always_ use `chrome` type to fetch content with a Headless chrome browser"
      }
      url: {
        type: "string"
        description: "url holds the link to a Search Engine to use, and other optional parameters like languages or country."
      }
    }
  }
  output: {
    type: "object"
  }
}