name: PornhubPremium
performerByName:
  action: scrapeXPath
  queryURL: https://www.pornhubpremium.com/pornstars/search?search={}
  scraper: performerSearch
performerByURL:
  - action: scrapeXPath
    url:
      - pornhubpremium.com
    scraper: performerScraper
sceneByURL:
  - action: scrapeXPath
    url:
      - pornhubpremium.com/view_video.php?viewkey=
    scraper: sceneScraper
sceneByFragment:
  action: scrapeXPath
  queryURL: https://www.pornhubpremium.com/view_video.php?viewkey={filename}
  queryURLReplace:
    filename:
      - regex: (?:.*[^a-zA-Z\d])+(ph(?:[a-zA-Z\d]+)).+
        with: $1
      - regex: .*\.[^\.]+$ # if no ph id is found in the filename
        with: # clear the filename so that it doesn't leak to ph
  scraper: sceneScraper

xPathScrapers:
  performerSearch:
    performer:
      Name: //div[@class="wrap"]/div[@class="thumbnail-info-wrapper"]/a[@class="title"]/text()
      URL:
        selector: //div[@class="wrap"]/div[@class="thumbnail-info-wrapper"]/a[@class="title"]/@href
        postProcess:
          - replace:
              - regex: ^
                with: "https://www.pornhubpremium.com"
  performerScraper:
    common:
      $infoPiece: //div[@class="infoPiece"]
      $infoContainer: //div[@class="infoContainer"]
      $smallInfo: span[@class="smallInfo"]

    performer:
      Name: //h1[@itemprop="name"]|$infoContainer//h1
      Birthdate:
        selector: //span[@itemprop="birthDate"]|$infoPiece[contains(span,"Born:")]/text()
        postProcess:
          - parseDate: Jan 2, 2006
          - parseDate: 2006-01-02
      Country:
        selector: $infoPiece[contains(span,"Birthplace:")]/text()|$infoPiece[contains(span,"City and Country:")]/$smallInfo|$infoPiece[contains(span,"Birth Place:")]/$smallInfo
        postProcess:
          - replace:
              - regex: .+,\s?([^,]+$)
                with: $1
          - map:
              US: "USA"
              United States of America: "USA"
      Gender: $infoPiece[contains(span,"Gender:")]/$smallInfo
      Twitter: //ul[contains(@class,"socialList")]//a[contains(@href,"twitter.com/")]/@href
      Instagram: //ul[contains(@class,"socialList")]//a[contains(@href,"instagram.com/")]/@href
      Measurements: $infoPiece[contains(span,"Measurements:")]/$smallInfo|$infoPiece[contains(span,"Measurements:")]/text()
      Weight:
        selector: $infoPiece[contains(span,"Weight:")]/$smallInfo|$infoPiece[contains(span,"Weight:")]/text()
        postProcess:
          - replace:
              - regex: .*\((\d+)\s*kg\)
                with: $1
      Height:
        selector: $infoPiece[contains(span,"Height:")]/$smallInfo|$infoPiece[contains(span,"Height:")]/text()
        postProcess:
          - replace:
              - regex: .*\((\d+)\s*cm\)
                with: $1
      Details: //div[@itemprop="description" or starts-with(@class,"text longBio")]
      Ethnicity: $infoPiece[contains(span,"Ethnicity:")]/$smallInfo|$infoPiece[contains(span,"Ethnicity:")]/text()
      FakeTits: $infoPiece[contains(span,"Fake Boobs:")]/$smallInfo
      Piercings: $infoPiece[contains(span,"Piercings:")]/$smallInfo
      Tattoos: $infoPiece[contains(span,"Tattoos:")]/$smallInfo
      HairColor: $infoPiece[contains(span,"Hair Color:")]/$smallInfo
      CareerLength:
        selector: $infoPiece[contains(span,"Career Start and End:")]/$smallInfo
        postProcess:
          - replace:
              - regex: \s+to\s+
                with: "-"
      URL: //link[@rel="canonical"][1]/@href
      Image: //div[@class="thumbImage"]/img/@src|//img[@id="getAvatar"]/@src
  sceneScraper:
    common:
      $performer: //div[@class="pornstarsWrapper js-pornstarsWrapper"]/a[@data-mxptype="Pornstar"]
      $studio: //div[@data-type="channel"]/a
    scene:
      Title: //h1[@class="title"]/span/text()
      Details: //meta[@property="og:description"][1]/@content
      Date:
        selector: //script[contains(., 'uploadDate')]/text()
        postProcess:
          - replace:
              - regex: .+(?:"uploadDate":\s")([^"]+).+
                with: $1
              - regex: (.+)T.+
                with: $1
          - parseDate: 2006-01-02
      Tags:
        Name: //div[@class="categoriesWrapper"]//a[not(@class="add-btn-small ")]|//div[@class="tagsWrapper"]//a[not(@class="add-btn-small")]
      Image:
        selector: //meta[@property="og:image"][1]/@content
      Performers:
        Name: $performer/@data-mxptext
        URL: $performer/@href
      Studio:
        Name: $studio
        URL: $studio/@href
driver:
  cookies:
    - CookieURL: "https://pornhubpremium.com"
      Cookies:
        - Name: "il"
          Domain: ".pornhubpremium.com"
          Value: "<'il' cookie value>"
          Path: "/"
# Reference: https://github.com/stashapp/CommunityScrapers/blob/master/scrapers/Pornhub.yml
# Last Updated October 11, 2021