name: BreedItRaw sceneByURL: - action: scrapeXPath url: - breeditraw.net/tour/trailers/ scraper: sceneScraper performerByURL: - action: scrapeXPath url: - breeditraw.net/tour/models/ scraper: performerScraper xPathScrapers: sceneScraper: common: $performer: //li[@class="update_models"]/a scene: Title: //div[@class="videoDetails clear"]//h3/text() Date: selector: //span[contains(., "Date Added:")]/following-sibling::text() postProcess: - replace: - regex: ^\s* with: - parseDate: January 2, 2006 Details: //div[@class="videoDetails clear"]/p Tags: Name: //li[contains(text(), "Tags:")]/following-sibling::li/a/text() Performers: Name: $performer/text() URL: $performer/@href Image: selector: //script[contains(text(),"poster")]/text() postProcess: - replace: - regex: '.+poster="([^"]+)".+' with: https://www.breeditraw.net$1 - regex: 1x\.jpg with: "2x.jpg" # 3,4 is also possible but the images get too big Studio: Name: fixed: Breed it Raw performerScraper: performer: Name: selector: //meta[@property="og:title"]/@content postProcess: - replace: - regex: " - .*$" with: Gender: fixed: Male Height: selector: //strong[contains(., "Height:")]/following-sibling::text() postProcess: - feetToCm: true Weight: selector: //strong[contains(., "Weight:")]/following-sibling::text() postProcess: - lbToKg: true Measurements: selector: //strong[contains(., "Dick Size:")]/following-sibling::text() postProcess: - replace: - regex: ^ with: 0' - feetToCm: true Image: selector: //div[@class="profile-pic"]/img/@src0_2x # 3x is either too big or an upscale so imho not worth it postProcess: - replace: - regex: ^ with: https://www.breeditraw.net/ # Last Updated December 18, 2022