76 lines
2.2 KiB
YAML
76 lines
2.2 KiB
YAML
name: "Mature.nl"
|
|
sceneByURL: &byUrl
|
|
- action: scrapeXPath
|
|
url:
|
|
- mature.nl/
|
|
scraper: sceneScraper
|
|
galleryByURL: *byUrl
|
|
sceneByFragment:
|
|
action: scrapeXPath
|
|
queryURL: "{url}"
|
|
scraper: sceneScraper
|
|
|
|
xPathScrapers:
|
|
sceneScraper:
|
|
common:
|
|
$url: //link[@rel="canonical"]/@href
|
|
scene:
|
|
URL: &url
|
|
selector: $url
|
|
postProcess:
|
|
- replace:
|
|
- regex: (^https?:\/\/(?:www\.)?mature\.nl\/..\/update\/\d+)\/.+
|
|
with: $1
|
|
Code:
|
|
selector: $url
|
|
postProcess:
|
|
- replace:
|
|
- regex: .+\/update\/(\d+)\/.+
|
|
with: $1
|
|
Title: &title //div[@class="box"]/h1/text()
|
|
Details: &details
|
|
selector: //div/span[text()="Synopsis:"]/following-sibling::text() | //meta[@name="description"]/@content
|
|
postProcess:
|
|
- replace:
|
|
- regex: " Watch this amazing porn video on mature.nl as a member today!"
|
|
with:
|
|
Tags: &tags
|
|
Name: //div[@id="divPageUpdateNiches"]/a[contains(@class, "tag")]/text()
|
|
Performers: &performers
|
|
Name:
|
|
# This method is easier, but the names here are in uppercase
|
|
# selector: //div[contains(@class,"card-label")]/a/text()
|
|
selector: //div[@class="box-cnt"]//span[@class="col-accent"]/following-sibling::text()
|
|
postProcess:
|
|
- replace:
|
|
- regex: \s\(\w+\)
|
|
with:
|
|
- regex: \s\(EU\)
|
|
with:
|
|
- regex: " & "
|
|
with: ", "
|
|
- regex: (\w)\.,
|
|
with: $1,
|
|
split: ", "
|
|
Image:
|
|
selector: (//video/@poster | //span[@id="spnPageUpdateTrailer"]/a/img/@data-src | //img[@class="img-responsive lazy"][1]/@data-src)[1]
|
|
Date: &date
|
|
selector: //span[@class="val-m"][1]
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^(\d{1,2}-\d{1,2}-\d{4}).*$
|
|
with: $1
|
|
- parseDate: 2-1-2006
|
|
Studio: &studio
|
|
Name:
|
|
fixed: "Mature.nl"
|
|
gallery:
|
|
URL: *url
|
|
Title: *title
|
|
Details: *details
|
|
Tags: *tags
|
|
Performers: *performers
|
|
Date: *date
|
|
Studio: *studio
|
|
# Last Updated July 11, 2023
|