name: "KristenBjorn"
sceneByURL:
  - action: scrapeXPath
    url:
      - kristenbjorn.com/video
    scraper: sceneScraper
movieByURL:
  - action: scrapeXPath
    url:
      - kristenbjorn.com/web/model/store/
    scraper: movieScraper
performerByURL:
  - action: scrapeXPath
    url:
      - kristenbjorn.com/gay-porn-star/
      - kristenbjorn.com/web/model/gay-porn-star/
    scraper: performerScraper

xPathScrapers:
  sceneScraper:
    common:
      $performer: //div[@class="scene-item"]/a[contains(@class,"scene-box")]
    scene:
      Title: //h1[@class="StoreHeaderNew"]/text()
      Details: //div[@class="med-text"]/p
      Code:
        selector: //meta[@property="og:url"]/@content
        postProcess:
          - replace:
              - regex: ^.*\/video-(\d+)\/.*$
                with: $1
      Date:
        selector: //div[@id="main"]//div[@class="date"][1]/text()
        postProcess:
          - parseDate: 02 Jan 2006
      Tags:
        Name:
          selector: //a[contains(@title,"Categorie:")]//text()
          postProcess:
            - replace:
                - regex: (.*)\s\(\d+\)
                  with: $1
      Performers:
        Name: $performer//h5/text()
        URL:
          selector: $performer/@href
          postProcess: &appendDomain
            - replace:
                - regex: ^
                  with: http://kristenbjorn.com
      Image: &imageAttr //meta[@property="og:image"]/@content
      Studio:
        Name:
          fixed: Kristen Bjorn
  movieScraper:
    movie:
      Name: //article/div[1]/span/text()
      Date:
        selector: //span[text()="Release Date:"]/following-sibling::text()
        postProcess:
          - replace:
              - regex: /20([0-9])
                with: /$1
              - regex: ^(\d/\d\d/\d\d)$
                with: 0$1
          - parseDate: 01/02/06
      Duration:
        selector: //span[text() = "Running Time:"]/following-sibling::text()
        postProcess:
          - replace:
              - regex: ^(\d+)\s*(?i:h)\D+$ # movies with only hours
                with: $1:00:00
              - regex: ^(\d+)\s*(?i:m)\D+$ # movies with only minutes
                with: "$1:00"
              - regex: ^(\d+)\s*(?i:h)\D+(\d+)\s*(?i:m)\D+$ # movies with hours and minutes
                with: "$1:$2:00"
      Synopsis: //div[@class="more"]
      Director: //span[text()="Director:"]/following-sibling::text()
      Studio:
        Name: //span[text()="Studio:"]/following-sibling::text()
      FrontImage:
        selector: //div[@id="imagen0"]//img/@src
        postProcess: *appendDomain
      BackImage:
        selector: //div[@id="imagen1"]//img/@src
        postProcess: *appendDomain
  performerScraper:
    performer:
      Name:
        selector: //h1/text()
        postProcess:
          - replace:
              - regex: "^Gay Porn Star: (.*)$"
                with: $1
      Gender:
        fixed: Male
      Country:
        selector: //h2[contains(text(),"Nationality:")]/following-sibling::text()[1]
      Height:
        selector: //h2[contains(text(),"Height:")]/following-sibling::text()[1]
        postProcess:
          - feetToCm: true
      Weight:
        selector: //h2[contains(text(),"Weight:")]/following-sibling::text()[1]
        postProcess:
          - replace:
              - regex: ^(\d+).+
                with: $1
          - lbToKg: true
      Measurements:
        selector: //h2[contains(text(), "Dick:")]/following-sibling::text()[1]
        postProcess:
          - replace:
              - regex: '[^\s]+ \((.*) cms\).*$'
                with: $1
      Image: *imageAttr
# Last Updated December 23, 2022