name: English Lads sceneByURL: - action: scrapeXPath url: - englishlads.com/video scraper: sceneScraper performerByURL: - action: scrapeXPath url: - englishlads.com/model scraper: performerScraper galleryByURL: - action: scrapeXPath url: - englishlads.com/photo scraper: galleryScraper xPathScrapers: sceneScraper: scene: Title: selector: //div[@class="shoot-title"]/h2 postProcess: - replace: - regex: ^(.*?)-(.*)-(.*?)$ with: "$2" Date: selector: //div[@class="shoot-title"]/h2 postProcess: - replace: - regex: ^(.*?)-(.*)-(.*?)$ with: "$1" - regex: (st|nd|rd|th)\b with: "" - parseDate: "2 Jan 2006" Performers: Name: selector: //div[@class="shoot-title"]/h2 postProcess: - replace: - regex: ^(.*?)-(.*)-(.*?)$ with: "$3" split: "," URL: selector: //div[@class="shoot-title"]/h2/a/@href postProcess: - replace: - regex: "(.*)" with: "https://www.englishlads.com$1" Details: selector: //div[not(@class) and @style] Tags: Name: //a[@class="more" and contains(@href, "tag=")] Image: selector: //img[@class="shoot-splash-image"]/@src | //video/@data-poster postProcess: - replace: - regex: "(.*)" with: "https://www.englishlads.com$1" Studio: Name: fixed: English Lads performerScraper: performer: Name: //h1[@itemprop="name"]/text() Gender: fixed: Male Height: selector: //span[@itemprop='title'] postProcess: - replace: - regex: (.*)(\b\d+\'\d{1,2}")(.*) with: "$2" - feetToCm: true Measurements: selector: //span[@itemprop='title'] postProcess: - replace: - regex: \s+|\xA0+ with: "_" - regex: _+ with: " " - regex: (\d{2}\s*yo)\s*(\d{1,2}'\d{1,2}")\s*(\s*\d{2}")\s*(\d{2}")(.*) with: "Waist: $3, Chest: $4" PenisLength: selector: //span[@itemprop='title'] postProcess: - replace: - regex: ^(.*?)(\d+\.?\d?)("\s+cock)$ with: "0'$2" - feetToCm: true Circumcised: selector: //div[@class='model-text'] postProcess: - replace: - regex: (.*?)(uncut|cut)(.*) with: $2 - map: uncut: UNCUT cut: CUT Details: selector: //div[@class='model-text']/i Image: selector: //script[contains(.,"modelimage")] postProcess: - replace: - regex: (.*?)(\/public.*?)',(.*) with: "$2" - regex: "(.*)" with: "https://www.englishlads.com$1" galleryScraper: gallery: Title: selector: //div[@class="shoot-title"]/h2 postProcess: - replace: - regex: ^(.*?)-(.*)-(.*?)$ with: "$2" Date: selector: //div[@class="shoot-title"]/h2 postProcess: - replace: - regex: ^(.*?)-(.*)-(.*?)$ with: "$1" - regex: (st|nd|rd|th)\b with: "" - parseDate: "2 Jan 2006" Performers: Name: selector: //div[@class="shoot-title"]/h2 postProcess: - replace: - regex: ^(.*?)-(.*)-(.*?)$ with: "$3" split: "," URL: selector: //div[@class="shoot-title"]/h2/a/@href postProcess: - replace: - regex: "(.*)" with: "https://www.englishlads.com$1" Details: selector: //div[not(@class) and @style] Tags: Name: //a[@class="more" and contains(@href, "tag=")] Studio: Name: fixed: English Lads # Last Updated October 03, 2023