name: "FinishesTheJob" sceneByURL: - action: scrapeXPath url: - finishesthejob.com/scene/ - mrpov.com/scene/ - manojob.com/scene/ - thedicksuckers.com/scene/ scraper: sceneScraper xPathScrapers: sceneScraper: common: $content: //main//div[contains(@class,"col")] scene: Title: $content/h1/text() Details: $content/p[2]/text() # only works when url is from finishesthejob.com Date: selector: $content/meta[@itemprop="uploadDate"]/@content postProcess: - replace: - regex: "^(.+?)T.*" with: $1 - parseDate: "2006-01-02" Performers: Name: $content/h3/a/text() Tags: Name: $content/p/a/text() Image: selector: //video/@poster postProcess: - replace: - regex: (.+scenes\/)([a-z]+)(.+) with: https://www.$2.com$1$2$3 Studio: Name: selector: $content/h2/text() postProcess: - replace: - regex: "Presented By: " with: "" URL: //link[@rel='canonical']/@href # Last Updated October 19, 2023