name: PurgatoryX
sceneByURL:
  - action: scrapeXPath
    url:
      - tour.purgatoryx.com/view/
    scraper: sceneScraper
xPathScrapers:
  sceneScraper:
    scene:
      Title: //h1[@class="title"]/text()
      URL: 
        selector: //head/link[@rel="canonical"]/@href
        postProcess:
          - replace:
            - regex: $
              with: "?trilogy=1"
      Image: //video[@id="main-player"]/@poster
      Date:
        selector: //span[@class="date"]/text()
        postProcess:
          - replace:
            - regex: ^\w+day\s+
              with: ""
          - parseDate: January 02, 2006
      Details: //div[@class="description"]/p/text()
      Performers:
        Name:
          selector: //div[@class="model-wrap"]//li/h5
      # They use the same tags for all scenes (blowjobs,multi scene porn,exclusive videos, pornstars, hardcore, fantasy, milfs, teens, facials, trilogy)
      #Tags:
      #  Name:
      #    selector: //meta[@name="keywords"]/@content
      #    postProcess:
      #      - replace:
      #        - regex: \s*,\s*
      #          with: ","
      #    split: ","
      Studio:
        Name:
          selector: //p[@class="series"]//span/text()
          postProcess:
            - replace:
              - regex: " Series"
                with: ""
      # URL need to have "?trilogy=" to get the name of the Trilogy
      Movies:
        Name: //span[contains(text(),"Part of")]/following-sibling::text()
# Last Updated June 27, 2022