name: Trans500 sceneByURL: - action: scrapeXPath url: - trans500.com/tour/ - trans500.com/tour3/ scraper: sceneScraper - action: scrapeXPath url: - behindtrans500.com/tour/ - ikillitts.com/tour/ - superramon.com/tour/ - trans500.com/tourespanol - transatplay.com/tour/ - tsgirlfriendexperience.com/tour/ scraper: sceneScraperEspanol xPathScrapers: sceneScraper: scene: Title: //div[@class="col-sm-12"]/p/../h2/text() Details: //p[@class="description"] Image: selector: //video[@id="my-video"]/@poster postProcess: - replace: - regex: ^ with: "http://www.trans500.com" Studio: Name: //p[@class="pull-right"]/b/text() sceneScraperEspanol: scene: Title: selector: //header[@id="scene-info"]/h1/text()[contains(., ":")] postProcess: - replace: - regex: .*:. with: Date: selector: //div[contains(text(), "Added:")]/text() # or //div[@class="scene-infobrick"][contains(text(), "Added:")]/text() postProcess: - replace: - regex: ".*:" with: - parseDate: 01/02/2006 Performers: Name: //div[@class="scene-infobrick"][contains(text(), "TSGirls:")]/a/text() Details: //section[@id="scene-desc"]/p/text() Image: selector: //video/@poster|//meta[@name="twitter:image0"]/@content postProcess: - replace: - regex: '^http:' with: 'https:' Studio: Name: selector: //div[@class="scene-infobrick"][contains(text(), "Categories:")]/a/text() concat: "," postProcess: - replace: - regex: .*(superramon).* with: "Super Ramon" - regex: .*(tsgirlfriendexperience).*|.*(TSGFE).* with: "TS Girlfriend Experience" - regex: .*(ikillitts).*|.*(I Kill it TS).*|.*(IKI).* with: "I Kill It TS" - regex: .*(transatplay).*|.*(TAP).*|.*(trans at play).* with: "Trans at Play" - regex: .*(behindtrans500).*|.*(behind the scenes).* with: "Behind Trans500" Tags: # Either //meta[@name="keywords"]/@content OR: //div[@class="scene-infobrick"][contains(text(), "Categories:")]/a/text() Name: //div[@class="scene-infobrick"][contains(text(), "Categories:")]/a/text() # Last Updated January 03, 2023