name: DartTechStudios
sceneByURL:
  - action: scrapeXPath
    url:
      - darttechstudios.com/Media.php
    scraper: sceneScraper

sceneByFragment:
  action: scrapeXPath
  queryURL: https://www.darttechstudios.com/Media.php?ID={filename}
  queryURLReplace:
    filename:
      # the filename of the file downloaded from the site is the ID with an mp4 extension
      - regex: (.*).mp4 # support filenames in the form 12345_performer_other_data.mp4
        with: $1
  scraper: sceneScraper

xPathScrapers:
  sceneScraper:
    scene:
      Title:
        selector: &titledateSelector //font[@size="+1"]/b/text()
        postProcess:
          - replace:
            - regex: ([^-]+).*
              with: $1
      Date:
        selector: *titledateSelector
        postProcess:
          - replace:
              - regex: .*([0-9]{2}/[0-9]{2}/[0-9]{4})
                with: $1
          - parseDate: 01/02/2006
      Performers:
        Name: //div[@class="item2"]/a[contains(@href, '/Videos.php?Model=')]
      Tags:
        Name: //div[@class="item2"]/a[contains(@href, '/Videos.php?Fetish=')]
      Details:
        selector: //div[@class="item2"]/text()
        concat: "\n\n"
        postProcess:
          - replace: 
            - regex: "\n\n,"
              with: ""
      Image:
        #selector: //div[@class="galleryEntry_UpdatePage"][1]//img/@src
        selector: &imgSelector //img[@alt="Main Image"]/@src
        postProcess:
          - replace: 
            - regex: (.*)
              with: https://www.darttechstudios.com$1
      Code:  
        selector: *imgSelector
        postProcess:
          - replace:
            - regex: &codeRegex /Content/[0-9]{4}_(.*)/Main.jpg
              with: $1
      URL:
        selector: *imgSelector
        postProcess:
          - replace:
            - regex: *codeRegex
              with: https://www.darttechstudios.com/Media.php?ID=$1
      Studio:
        Name: 
          fixed: Dart_Tech Studios
# Last Updated October 08, 2023