name: "Woodman Casting X"
sceneByURL:
  - action: scrapeXPath
    url:
      - woodmancastingx.com
    scraper: sceneScraper
sceneByName:
  action: scrapeXPath
  queryURL: https://www.woodmancastingx.com/search?query={}
  scraper: sceneSearch
sceneByQueryFragment:
  action: scrapeXPath
  queryURL: "{url}"
  scraper: sceneScraper

xPathScrapers:
  sceneScraper:
    scene:
      Title: //h1
      Details: //p[@class="description"]
      Date:
        selector: //p[span="Published"]/text()
        postProcess:
          - replace:
              - regex: "^.*: "
                with: ""
          - parseDate: 2006-01-02
      Performers:
        Name: //a[@class="girl_item"]/span[@class="name"]
        URL:
          selector: //a[@class="girl_item"]/@href
          postProcess: &pp
            - replace:
                - regex: ^/
                  with: "https://www.woodmancastingx.com/"
      Studio:
        Name:
          selector: //div[@id="breadcrumb"]
          postProcess:
            - replace:
                - regex: ^[^>]*> (Casting|Sthuf).*$
                  with: "Woodman Casting X"
                - regex: ^[^>]*> (Scenes|Backstage|Live).*$
                  with: "Pierre Woodman"
      Tags:
        Name: //a[@class="tag"]
      Image:
        selector: //script[contains(.,'image')]
        postProcess:
          - replace:
              - regex: ^.*image:\s+"([^"]+)".*$
                with: $1
      URL:
        selector: //meta[@property="og:url"]/@content
        postProcess: *pp

  sceneSearch:
    common:
      $res: //div[contains(@class,("items container"))]/a[@class="item scene"]
    scene:
      Title: $res/img/@alt
      Image: $res/img/@src
      URL:
        selector: $res/@href
        postProcess: *pp
# Last Updated May 30, 2023