name: POV Train
sceneByURL:
  - action: scrapeXPath
    url:
      - povtrain.com/tour/trailer.php?id=
    scraper: sceneScraper
sceneByName:
  action: scrapeXPath
  queryURL: https://www.povtrain.com/tour/search.php?query={}
  scraper: sceneSearch
sceneByQueryFragment:
  action: scrapeXPath
  queryURL: "{url}"
  scraper: sceneScraper
xPathScrapers:
  sceneSearch:
    scene:
      Title: //ul[@class="slides"]/li//h3
      URL: //ul[@class="slides"]/li/a/@href
      Date:
        selector: //ul[@class="slides"]/li//comment()[contains(., "Date")]
        postProcess: &parseDate
          - replace:
              - regex: .*</strong>\s*(.*)<.*
                with: $1
          - parseDate: January 2, 2006
      Image:
        selector: //ul[@class="slides"]/li/a/img/@src
        postProcess:
          - replace:
              - regex: ^
                with: https://povtrain.com/
  sceneScraper:
    scene:
      Title: //h2
      Details: //div[@class="desc"]/p
      Date:
        selector: //comment()[contains(., "Date Added")]
        postProcess: *parseDate
      Image:
        # Sometimes they put the preview image in a script tag, sometimes it's an actual img
        selector: //script[contains(., "image:")]/text() | //div[contains(@class, "alpha")]//img[contains(@id, "set-target")]/@src
        postProcess:
          - replace:
              # This regex will only match when we have a script tag
              # and gives the same result as the img tag, a relative URL
              - regex: .*image:\s*"([^"]+).*
                with: $1
              - regex: ^
                with: https://povtrain.com
      Studio:
        Name:
          fixed: POV Train
      Tags:
        Name: //h5[@class="video_categories"]/a
      Performers:
        Name: //h5[@class="featuring_model"]/a
# Last Updated March 10, 2024