name: Combat Zone

sceneByURL:
  - action: scrapeXPath
    scraper: sceneScraper
    url:
      - tour.blackmarketxxx.com/trailers/
      - tour.combatzonexxx.com/trailers/
      - tour.fillyfilms.com/trailers/
      - tour.smashpictures.com/trailers/

movieByURL:
  - action: scrapeXPath
    scraper: movieScraper
    url:
      - combatzone.us/distributor/

xPathScrapers:
  sceneScraper:
    scene:
      Title: //div[contains(@class, "title")]/h2
      Date:
        selector: //div[@class="info"]/p/text()[contains(., "Added:")]
        postProcess:
          - replace:
              - regex: ^Added:\s+
                with:
          - parseDate: January 2, 2006
      Details: //div[@class="description"]/p
      Tags:
        Name: //ul[@class="tags"]//a
      Performers:
        Name: //div[@class="info"]//a[contains(@href, "/models/")]
      Image:
        selector: //div[@id="fakeplayer"]//img/@src
        postProcess:
          - replace:
              - regex: ^
                with: https://tour.combatzonexxx.com
      Studio:
        Name:
          # Search for the scene in order to get the correct studio
          selector: //div[contains(@class, "title")]/h2
          postProcess:
            - replace:
                - regex: \s
                  with: +
                - regex: ^(.+)$
                  with: https://tour.combatzonexxx.com/search.php?st=advanced&qall=$1&cat[]=5
            - subScraper: //i[@class="site_badge"]/text()
            - map:
                BM: Black Market XXX
                CZ: Combat Zone XXX
                FF: Filly Films
                SP: Smash Pictures

  movieScraper:
    movie:
      Name: //h1
      Date:
        selector: //p[span[contains(text(), "Release Date:")]]/text()[2]
        postProcess:
          - parseDate: January 2, 2006
      Synopsis: //p[span[contains(text(), "Synopsis:")]]/text()[2]
      Director: //p[span[contains(text(), "Director:")]]/text()[2]
      FrontImage:
        selector: //img[starts-with(@src, "/distributor/cvr/") and contains(@alt, "front cover")]/@src
        postProcess:
          - replace:
              - regex: ^/(.+)-s([fb]\.jpg)$
                with: https://www.combatzone.us/$1-l$2
      BackImage:
        selector: //img[starts-with(@src, "/distributor/cvr/") and contains(@alt, "back cover")]/@src
        postProcess:
          - replace:
              - regex: ^/(.+)-s([fb]\.jpg)$
                with: https://www.combatzone.us/$1-l$2
      Studio:
        Name: //p[span[contains(text(), "Studio:")]]/text()[2]

# Last Updated November 17, 2020