From 01f5283b15e11fcf6f3e9e22e8dfdde53188f9af Mon Sep 17 00:00:00 2001 From: Maista6969 Date: Sat, 8 Jul 2023 21:35:24 +0200 Subject: [PATCH] Update RandyBlue for new site layout --- scrapers/RandyBlue.yml | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/scrapers/RandyBlue.yml b/scrapers/RandyBlue.yml index 1bc7c1296..4b0616dfa 100755 --- a/scrapers/RandyBlue.yml +++ b/scrapers/RandyBlue.yml @@ -2,29 +2,32 @@ name: "RandyBlue" sceneByURL: - action: scrapeXPath url: - - randyblue.com/video/ + - randyblue.com/scenes/ scraper: sceneScraper xPathScrapers: sceneScraper: + common: + $titleArea: //div[@class="title-zone"] scene: - Title: //h2[@class="content-item-name"] + Title: $titleArea/h1 Date: - selector: //div[@id="info"]//li[@class="added"]/span + selector: $titleArea/div[@class="calendar"] postProcess: - parseDate: 01/02/2006 - Details: //div[@class="short-description"] - Tags: - Name: //div[@class="tagcloud"]/a/text() - Performers: - Name: //a[@itemprop="actor"] - Image: - selector: "//script[contains(text(), 'image: ')]" + Details: + selector: //div[@id="collapseTwo"] postProcess: - replace: - - regex: '^.*image: "([^"]+)",.*$' - with: $1 + - regex: \x{0020}|\x{00A0} # unicode SP, NBSP + with: " " + Tags: + Name: $titleArea/ul[@class="scene-tags"]/li/a + Performers: + Name: $titleArea/ul[@class="scene-models-list"]/li/a + Image: //meta[@itemprop="thumbnailUrl"]/@content + URL: //link[@rel="canonical"]/@href Studio: Name: fixed: Randy Blue -# Last Updated December 17, 2021 +# Last Updated July 8, 2023