# yaml-language-server: $schema=../validator/scraper.schema.json

name: "BaDoink"

sceneByURL:
  - action: scrapeXPath
    url: &urls
      - 18vr.com
      - babevr.com
      - badoinkvr.com
      - kinkvr.com
      - realvr.com
      - vrcosplayx.com
    scraper: sceneScraper
    queryURL: "{url}"
    queryURLReplace:
      url:
        # remove the members part of the url since the scrapper would not attempt to login
        - regex: "/members/"
          with: "/"

sceneByFragment:
  action: scrapeXPath
  # url format: https://{studio}.com/vrpornvideo/{title}-{code}
  # The url without the code is what we will use for scrapping
  # since it will forward to the correct one:
  #   url format: https://{studio}.com/vrpornvideo/{title}
  # both studio and title are part of the official file name
  queryURL: "{filename}"
  queryURLReplace:
    # filename format:
    #   {studio}_{title}_{res}_{vrtype}.{ext}
    #     res: oculus|\d+k
    #     vrtype: stuff we do not care about but could contain '_'
    filename:
      - regex: (?i)^(18vr|babevr|badoinkvr|kinkvr|realvr|vrcosplayx)_(.+)_(?:oculus|\dk)_.+$
        with: https://$1.com/vrpornvideo/$2
  scraper: sceneScraper

performerByURL:
  - action: scrapeXPath
    url: *urls
    scraper: performerScraper
movieByURL:
  - action: scrapeXPath
    url: *urls
    scraper: movieScraper
# Uncomment this section to enable Performer Search on this scraper
# performerByName:
#   action: scrapeXPath
#   queryURL: https://kinkvr.com/bdsm-performers/search/{}?all=1
#   scraper: performerSearch
xPathScrapers:
  sceneScraper:
    common:
      $details: &detailsAttr //div[@class="video-rating-and-details"]
    scene:
      Title: //h1[contains(@class, "video-title")]/text()
      Date: &dateSel
        selector: $details//p[@class="video-upload-date"]/text()
        postProcess:
          - replace:
              - regex: Uploaded:\s
                with:
          - parseDate: January 02, 2006
      Details: &detailsSel $details//p[@class="video-description"]/text()
      Tags:
        Name: $details//p[@class="video-tags"]//a/text()
      Performers:
        Name: $details//p[@class="video-actors"]/a/text()
      Studio:
        Name: &studioName //meta[@name="dl8-customization-brand-name"]/@content
      Image: &imageSel
        selector: //img[@class="video-image"]/@src
        postProcess:
          - replace:
              - regex: \?.+
                with: ""
      URL: &sceneUrl //link[@rel="canonical"]/@href
      Code:
        selector: *sceneUrl
        postProcess:
          - replace:
              - regex: '^(.+)-(\d+)/?$'
                with: $2
              - regex: '^.*[^\d].*$' # if no code is found in the url
                with: # return an empty string
  # Uncomment this section to user Performer Search on this scraper
  # performerSearch:
  #   common:
  #     $girlA: //div[@class="girl-card-info"]/a
  #   performer:
  #     Name: $girlA/span
  #     URL:
  #       selector: $girlA/@href
  #       postProcess:
  #         - replace:
  #             - regex: .*badoinkvr\.com/girl/redirect/([^\?]+).+
  #               with: https://badoinkvr.com/vr-pornstar/$1
  #             - regex: .*vrcosplayx\.com/girl/redirect/([^\?]+).+
  #               with: https://vrcosplayx.com/cosplaygirl/$1
  #             - regex: .*18vr\.com/girl/redirect/([^\?]+).+
  #               with: https://18vr.com/vrgirl/$1
  #             - regex: .*babesvr\.com/girl/redirect/([^\?]+).+
  #               with: https://babevr.com/vrbabe/$1
  #             - regex: .*realvr\.com/girl/redirect/([^\?]+).+
  #               with: https://realvr.com/pornstar/$1
  #             - regex: ^/
  #               with: https://kinkvr.com/
  performerScraper:
    common:
      $stats: //ul[@id='girlOptionDetails']
    performer:
      Name: //div[@class='girl-details-info']/h1/text()
      Gender:
        fixed: female
      URL: //link[@rel='canonical']/@href
      Twitter: //a[contains(@class,'social-media') and contains (@href,'twitter')]/@href
      Instagram: //a[contains(@class,'social-media') and contains (@href,'instagram')]/@href
      Ethnicity:
        selector: $stats/li[span[contains(.,'Ethnicity')]]/span[contains(@class,'value')]/text()
        postProcess:
          - map:
              Caucasian: white
              Asian: asian
              Black: black
              Latin: hispanic
      Country: $stats/li[span[contains(.,'Country')]]/span[contains(@class,'value')]/text()
      EyeColor: $stats/li[span[contains(.,'Eyes')]]/span[contains(@class,'value')]/text()
      Height:
        selector: $stats/li[span[contains(.,'Height')]]/span[contains(@class,'value')]/text()
        postProcess:
          - feetToCm: true
      Measurements: $stats/li[span[contains(.,'Measure')]]/span[contains(@class,'value')]/text()
      Aliases: $stats/li[span[contains(.,'Aka')]]/span[contains(@class,'value')]/text()
      Image: //img[@id='girlImage']/@src
  movieScraper:
    common:
      $details: *detailsAttr
    movie:
      Name:
        selector: //meta[@name="dl8-customization-brand-name"]/@content|$details/h1/text()
        concat: " - "
      Duration:
        selector: $details//p[@class="video-duration"]/text()
        postProcess:
          - replace:
              - regex: Duration:\s
                with: ""
              - regex: \smin
                with: ":00"
      Date: *dateSel
      Synopsis: *detailsSel
      Studio:
        Name: *studioName
      FrontImage: *imageSel
# Last Updated November 25, 2022