name: "CzechVR" sceneByURL: - action: scrapeXPath url: - czechar.com - czechvr.com - czechvrcasting.com - czechvrfetish.com - czechvrnetwork.com - vrintimacy.com scraper: sceneScraper movieByURL: - action: scrapeXPath url: - czechar.com - czechvr.com - czechvrcasting.com - czechvrfetish.com - czechvrnetwork.com - vrintimacy.com scraper: movieScraper xPathScrapers: sceneScraper: common: $info: &infoSel //div[@class="post"] $url: &urlSel //meta[@name="dl8-customization-brand-url"]/@content scene: Title: &title # Czech VR Network uses h1, the substudios use h2 selector: &titleSel $info//h1|$info//h2 postProcess: - replace: - regex: ".+ - " with: Date: &date selector: $info//div[@class="datum"]/text() postProcess: - parseDate: Jan 2, 2006 Details: &detailsSel //div[@class="text"]/text() Tags: Name: //div[@class="tag new"]/a/text() Performers: Name: $info//div[@class="modelky"]//a//span/text() Studio: &studio Name: selector: *titleSel postProcess: - replace: - regex: "\\d* - .+" with: Image: &image selector: $url|//dl8-video/@poster concat: " " postProcess: - replace: - regex: \s\./category with: /category - replace: - regex: \/\/ with: "/" - replace: - regex: :\/ with: "://" movieScraper: common: $info: *infoSel $url: *urlSel movie: Name: *title Duration: $info//div[@class="cas"]/text() Date: *date Studio: *studio Synopsis: *detailsSel FrontImage: *image driver: cookies: - CookieURL: "https://www.czechvr.com" Cookies: - Name: "iagree" Domain: ".czechvr.com" Value: "ano" Path: "/" headers: - Key: User-Agent Value: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:79.0) Gecko/20100101 Firefox/79.0) # Last Updated April 2, 2024