name: SpunkWorthy
sceneByURL:
  - action: scrapeXPath
    url:
      - spunkworthy.com/preview/view_video
    scraper: sceneScraper

performerByURL:
  - action: scrapeXPath
    url:
      - spunkworthy.com/preview/view_guy
    scraper: performerScraper

xPathScrapers:
  sceneScraper:
    scene:
      Title:
        selector: //p[contains(@class, 'h1')]/span[contains(@class, 'h2')]/text()
      Performers:
        Name:
          selector: //div[@class="scene_models"]//p/a/text()
          postProcess:
            - replace:
              - regex: "More of "
                with: ""
        URL:
          selector: //div[@class="scene_models"]//p/a/@href
          postProcess:
            - replace:
              - regex: "(.*)"
                with: "https://www.spunkworthy.com$1"
      Details:
        selector: //div[contains(@class, 'video_synopsis')]//p[not(ancestor::div[@class="scene_models"]) and not(@class)][not (starts-with(text(),'Tags:'))]/text()
        concat: "\n\n"
      Tags:
        Name: //div[contains(@class, 'video_synopsis')]//p[contains(text(),"Tags:")]/a/text()
      Image:
        selector: //div[contains(@class, 'video_player')]/img[1]/@src
        postProcess:
          - replace:
            - regex: "(.*)"
              with: "https://www.spunkworthy.com$1"
      Studio:
        Name:
          fixed: SpunkWorthy

  performerScraper:
    performer:
      Name: //p[contains(@class, 'h1')]/span[contains(@class, 'h2')]/text()
      Gender:
        fixed: Male
      Weight:
        selector: //div[@class='model_left']/p[1]/text()[contains(.,'Weight')]
        postProcess:
          - replace:
            - regex: "Weight: "
              with: ""
          - lbToKg: true
      Height:
        selector: //div[@class='model_left']/p[1]/text()[contains(.,'Height')]
        postProcess:
          - replace:
            - regex: "Height: "
              with: ""
          - feetToCm: true
      Image:
        selector: //div[@class='model_left']/img[1]/@src
        postProcess:
          - replace:
            - regex: "(.*)"
              with: "https://www.spunkworthy.com$1"

# Last Updated October 02, 2023