name: IMDB
performerByName:
  action: scrapeXPath
  queryURL: https://www.imdb.com/search/name-text/?bio={}
  scraper: performerSearch
performerByURL:
  - action: scrapeXPath
    url:
      - imdb.com
    scraper: performerScraper
sceneByName:
  action: scrapeXPath
  queryURL: https://www.imdb.com/find?q={}
  scraper: sceneSearch
sceneByQueryFragment:
  action: scrapeXPath
  queryURL: "{url}"
  scraper: sceneScraper
sceneByURL:
  - action: scrapeXPath
    url:
      - imdb.com/title/
    scraper: sceneScraper
movieByURL:
  - action: scrapeXPath
    url:
      - imdb.com/title/
    scraper: movieScraper
xPathScrapers:
  performerSearch:
    common:
      $listAnchor: //div[@class="lister-list"]/div[@class="lister-item mode-detail"]/div[@class="lister-item-content"]/h3/a
    performer:
      Name:
        selector: $listAnchor/text()
      URL:
        selector: $listAnchor/@href
        postProcess:
          - replace:
              - regex: ^
                with: https://www.imdb.com
  performerScraper:
    performer:
      Name: //td[@id="overview-top" or @class="name-overview-widget__section"]//h1/span[1]/text()
      Birthdate:
        selector: //time/@datetime
        postProcess:
          - parseDate: 2006-1-2
      Image: &imageAttr
        selector: //meta[@property="og:image"]/@content
        postProcess:
          - replace:
              - regex: '.*/imdb[^/]*\.png'
                with:
      Details:
        #        selector: //div[@class="name-trivia-bio-text"]/div/text()[1]
        selector: //span[@class='see-more inline nobr-only']/a/@href
        postProcess:
          - replace:
              - regex: ^
                with: "https://www.imdb.com/"
          - subScraper:
              selector: //div[@class="soda odd"]/p/text()

      URL: //div[@id='details-official-sites']/a[contains(text(),'Official Site')]/@href
      #     Facebook:  //div[@id='details-official-sites']/a[contains(text(),'Facebook')]/@href
      Instagram: //div[@id='details-official-sites']/a[contains(@href,"instagram.com/")]/@href
      Aliases:
        selector: //div[@id="details-akas"]/h4/following-sibling::text()
        concat: "|"
        postProcess:
          - replace:
              - regex: '\|+'
                with: ", "
      Height:
        selector: //div[@id="details-height"]/h4/following-sibling::text()
        postProcess:
          - replace:
              - regex: (.+)\s*\(.+$
                with: $1
          - feetToCm: true

  sceneSearch:
    common:
      $scenerow: //h3[text() = "Titles"]/following-sibling::table//tr[contains(@class, 'findResult')]
    scene:
      Title: $scenerow//td[@class='result_text']
      URL:
        selector: $scenerow//td[@class='result_text']/a/@href
        postProcess:
          - replace:
              - regex: ^
                with: https://imdb.com
      Image: $scenerow//td[@class='primary_photo']//img/@src

  sceneScraper:
    scene:
      Title: &title //section//h1
      URL: &url //meta[@property="og:url"]/@content
      Movies:
        Name: *title
        URL: *url
      Date: &date
        selector: //li[@data-testid='title-details-releasedate']/div/ul/li/a/text()
        postProcess:
          - replace:
              - regex: '\s*\(.+$'
                with: ""
              - regex: '^(\d\d\d\d)$'
                with: $1-01-01
          - parseDate: January 2, 2006
      Details: &desc //span[@data-testid="plot-xl"]
      Tags:
        Name: //div[@data-testid="genres"]/a/span
      Performers:
        Name: //a[@data-testid="title-cast-item__actor"]
      Image: *imageAttr
      Studio: &studio
        Name: (//li[@data-testid="title-details-companies"]/div//a)[1]
  movieScraper:
    movie:
      Name: *title
      URL: *url
      Date: *date
      Director: //section[@data-testid="title-cast"]//li[span[text()="Director"]]//a
      Duration:
        selector: //ul[@data-testid="hero-title-block__metadata"]/li[last()]
        postProcess:
          - replace:
              - regex: (\d+)h\s*
                with: "$1:"
              - regex: (\d+)m
                with: "$1:00"
              - regex: ":$" # only h
                with: ":00:00"
              - regex: ^(\d+:\d+)$ # only m
                with: "00:$1"
      Studio: *studio
      Synopsis: *desc
      FrontImage: *imageAttr
driver:
  headers:
    - Key: User-Agent
      Value: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:79.0) Gecko/20100101 Firefox/79.0)
# Last Updated August 13, 2022