name: AmateurAllure galleryByURL: - action: scrapeXPath url: &urls - amateurallure.com/tour/scenes/ - swallowsalon.com/scenes/ scraper: galleryScraper sceneByURL: - action: scrapeXPath url: *urls scraper: sceneScraper xPathScrapers: galleryScraper: common: &commonAttr $sceneinfo: //div[@class="scene-info"] $title: //span[@class='title_bar_hilite'] $logo: //div[@id="logo"]//a/@href gallery: Title: &titleSel $title Date: &dateAttr selector: //div[@class="backgroundcolor_info"]//div[@class='cell update_date'] postProcess: - parseDate: 01/02/2006 Details: &detailsSel //span[@class='update_description'] Tags: &tagsAttr Name: //span[@class='update_tags']//a/text() Performers: &performersAttr Name: //div[@class='backgroundcolor_info']//span[@class='update_models']//a Studio: &studioAttr Name: selector: $logo postProcess: - replace: - regex: '[^.]+\.([^.]+)\.com/.*' with: $1 - map: amateurallure: Amateur Allure swallowsalon: Swallow Salon sceneScraper: common: *commonAttr scene: Title: *titleSel Date: *dateAttr Details: *detailsSel Tags: *tagsAttr Performers: *performersAttr Image: selector: $logo|$title concat: "|" postProcess: - replace: - regex: \s with: "+" - regex: ^([^|]+)\|(.+) with: "${1}/search.php?st=advanced&qall=&qany=&qex=$2" - subScraper: selector: //div[@id="logo"]//a/@href|//img/@srcset concat: "|" postProcess: - replace: - regex: ^([^|]+amateurallure[^|]+)\|.+(/content/contentthumbs/\d+/\d+/[^/]+\.jpg) 1920w with: $1$2 - regex: ^([^|]+swallowsalon[^|]+)\|.+360w,\s((?:/tour)?/content/contentthumbs/\d+/\d+/[^/]+\.jpg).* with: $1$2 Studio: *studioAttr # Last Updated December 13, 2021