name: LadyboyGold performerByURL: - action: scrapeXPath url: - ladyboygold.com/index.php scraper: performerScraper sceneByURL: - action: scrapeXPath url: - ladyboygold.com/tour - tsraw.com scraper: sceneScraper xPathScrapers: performerScraper: common: $infoPiece: //div[@class="info-box info"] performer: Name: selector: //div[contains(@class, "modelInfo")]/div[@class="profileModel"]/text() postProcess: - replace: - regex: .*Ladyboy (.*) with: $1 Gender: fixed: transgender_female Weight: selector: //div[@class="modelStats"]/ul/li[contains(text(), "Weight:")]/text() postProcess: - replace: - regex: .* \(([0-9]*)kg\) with: $1 Height: selector: //div[@class="modelStats"]/ul/li[contains(text(), "Height:")]/text() postProcess: - replace: - regex: .* \(([0-9]*)cm\) with: $1 Measurements: selector: //div[@class="modelStats"]/ul/li[contains(text(), "Measurements:")]/text() postProcess: - replace: - regex: Measurements. (.*) with: $1 Image: selector: //div[@class="photoUpdate-image col-lg-3 col-md-3 col-sm-6"]/a/img[@class="img-responsive"]/@src postProcess: - replace: - regex: ^ with: https://www.ladyboygold.com Details: //div[@class="profileBio"]/text() sceneScraper: scene: Title: selector: //div[contains(@class, "show_video")]//h2/text() postProcess: - replace: - regex: \ 4[Kk]$ with: "" Details: selector: //div[contains(@class, "setDescription")]/p[contains(@class, "d-none")]/text() concat: "\n\n" Tags: Name: //div[contains(@class, "tags")]//a/text() Performers: Name: selector: //div[contains(@class, "show_video")]//h3/text() postProcess: - replace: - regex: .*Ladyboy (.*) with: $1 split: ", " Studio: Name: selector: //footer//p[contains(text(), 'Copyright')]/text()[2] postProcess: - replace: - regex: ^(\d+\ )?(.+)\.\s+.* with: $2 - map: TSRAW.com: TSRaw LadyboyGold.com: LadyboyGold Image: selector: //div[contains(@class, "show_video")]//img/@style postProcess: - replace: - regex: (background:\ ?url\()(.+)(?:\).+) with: https://ladyboygold.com/$2 # Last Updated December 29, 2022