name: extrapackage sceneByURL: - action: scrapeXPath scraper: sceneScraper url: - extrapackage.com/video movieByURL: - action: scrapeXPath scraper: movieScraper url: - extrapackage.com/dvd xPathScrapers: sceneScraper: scene: Title: selector: //div[@class="boxGradientTop gradient section"]//p[contains(.,"Information")] postProcess: - replace: - regex: 'Information - \s*' with: "" Date: selector: //div[@class="wrpHighlightUpdated"] postProcess: - parseDate: 2006-01-02 Performers: Name: //li[contains(.,"Pornstars:")]/a Tags: Name: //li[contains(.,"Categories :")]/a Details: selector: //div[@class="video-info mt-3"]/p Movies: Name: //div[@class="gblViewInfo"]//div[contains(.,"DVD :")]/a URL: selector: //div[@class="gblViewInfo"]//div[contains(.,"DVD :")]/a/@href postProcess: - replace: - regex: ^ with: "http://www.extrapackage.com" Image: selector: //script[contains(text(),"videoJsResolutionSwitcher")]/text() postProcess: - replace: - regex: .*?(https?:\/\/\S*\.jpg).* with: $1 Studio: Name: selector: //div[@class="gblViewInfo"]//div[contains(.,"Studio:")]/a movieScraper: movie: Name: selector: //div[@class="boxGradientTop gradient section"]//p[contains(.,"Information")] postProcess: - replace: - regex: 'Information - \s*' with: "" Date: selector: //td[@align="right"] postProcess: - parseDate: 2006-01-02 Duration: selector: //td/div postProcess: - replace: - regex: $ with: ":00" Studio: Name: selector: //div[@class="gblViewInfo"]//li[contains(.,"Studio")]/a FrontImage: //div[@class="gblViewHighlight"]/img/@src BackImage: selector: //div[@class="gblViewHighlight"]/img/@onmouseover postProcess: - replace: - regex: .*?(https?:\/\/\S*\.jpg).* with: $1 # Last Updated May 20, 2021