name: Xvideos
sceneByURL:
  - action: scrapeXPath
    url:
      - xvideos.com
      - xvideos2.com
      #- xvideos.es
      - xvideos.red
    scraper: sceneScraper

sceneByFragment:
  action: scrapeXPath
  scraper: sceneScraper
  queryURL: https://www.xvideos.com/video{filename}/x
  queryURLReplace:
    filename:
      # expects an id in square brackets before extension, as saved by yt-dlp by default
      - regex: '.*\[([0-9a-zA-Z]{4,})\]\.[^\.]+'
        with: $1
      # or expects an id
      - regex: '^.*?(\d+)\..+$'
        with: $1
      # if no id is found in the filename
      - regex: .*\.[^\.]+$
        with: # clear the filename so that it doesn't leak

xPathScrapers:
  sceneScraper:
    scene:
      Title: //h2[@class="page-title"]/text()[1]
      Tags:
        Name: //li/a[@class="is-keyword btn btn-default"]/text()
      Performers:
        Name: //li[@class="model"]/a/span[1]/text()
      Studio:
        Name: //li[@class="main-uploader"]/a[
          starts-with(@href,'/channels')          or
          starts-with(@href,'/amateur-channels')  or
          starts-with(@href,'/model-channels')    or
          starts-with(@href,'/pornstar-channels')
          ]/span[@class="name"]/text()
      Image:
        selector: //script[contains(text(), "setThumbUrl169")]/text()|//div[@id="html5video"][span[@class="premium-log-overlay"]]/div[@class="embed-responsive-item"]/@style
        postProcess:
          - replace:
              - regex: ^.+(?:setThumbUrl169|url)\('(.+?\.jpg).+$
                with: $1
      URL: //link[@rel="alternate" and @hreflang="x-default"]/@href
      Date:
        selector: //script[@type="application/ld+json"]/text()
        postProcess:
          - replace:
              - regex: '[\S\s]+"uploadDate"\s*:\s*"(\d+-\d{2}-\d{2})[^"]+"[\S\s]+'
                with: $1
          - parseDate: 2006-01-02
# Last Updated February 15, 2023