name: ExploitedX

sceneByURL:
  - action: scrapeXPath
    url:
      - backroomcastingcouch.com/trailers/
      - bbcsurprise.com/trailers/
      - blackambush.com/trailers/
      - hotmilfsfuck.com/trailers/
      - exploitedcollegegirls.com/trailers/
    scraper: sceneScraper
  - action: scrapeXPath
    url:
      - excogigirls.com/trailers/
    scraper: newSiteScraper

performerByURL:
  - action: scrapeXPath
    url:
      - backroomcastingcouch.com/models/
      - bbcsurprise.com/models/
      - blackambush.com/models/
      - hotmilfsfuck.com/models/
      - exploitedcollegegirls.com/models/
      - excogigirls.com/models/
    scraper: performerScraper

xPathScrapers:
  sceneScraper:
    common:
      $models: //div[contains(@class, "models-list-thumbs")]//a
    scene:
      Studio: &studio
        Name:
          selector: //a[contains(@class, "navbar-brand")]/@title
          postProcess:
            - map:
                OFFICIAL Backroom Casting Couch: Backroom Casting Couch
                Hot Milf Fuck Videos: Hot Milfs Fuck
                Excogi | Exploited College Girls: Exploited College Girls
                EXCOGI GIRLS: ExCoGi Girls
      Title: //div[@class="video-player"]//*[@class="section-title"]
      Performers:
        Name: $models/span
        URL: $models/@href
      Date: &date
        selector: //strong[text()="Released:"]/following-sibling::text()
        postProcess:
          - parseDate: January 2, 2006
      Tags: &tags
        Name: //ul[@class="tags"]//a
      Image: &image //div[@class="player-thumb"]//img[contains(@class, "update_thumb")]/@src0_1x
      Details: &details
        selector: //p[contains(@class, "descriptionFull")]//text()
        concat: "\n\n"
        postProcess:
          - replace:
              - regex: (.*?)\s*Read Less
                with: $1

  newSiteScraper:
    scene:
      Title: //h1
      Date: *date
      Image: *image
      Tags: *tags
      Studio: *studio
      Details: *details
      Performers:
        Name: //div[@class="card txt-lg-left"]//*[@class="model-name"]
        URL: //div[@class="card txt-lg-left"]//a/@href

  performerScraper:
    common:
      $detail: //div[@class="detail-div"]
    performer:
      Name: |
        //div[contains(@class, "main-article")]//h2
        |//section[contains(@class, "bio-section-head")]//h2
      Image:
        # URL is a CDN url with token auth, replace with orig url --> Works without token
        selector: //base/@href|//img[contains(@class, "model_bio_thumb")]/@src0_1x
        concat: "|"
        postProcess:
          - replace:
              - regex: "[|].+?\\.hwcdn.net/(.+?)\\?.+$"
                with: $1
      Measurements: $detail/p[contains(., "Measurements:")]/strong/following-sibling::text()
      Height:
        selector: $detail/p[contains(., "Height:")]/strong/following-sibling::text()
        postProcess:
          - feetToCm: true
# Last Updated June 07, 2022