53 lines
1.5 KiB
YAML
53 lines
1.5 KiB
YAML
name: Naughty Natural
|
|
sceneByURL:
|
|
- action: scrapeXPath
|
|
url:
|
|
- naughtynatural.com/videos/
|
|
scraper: sceneScraper
|
|
galleryByURL:
|
|
- action: scrapeXPath
|
|
url:
|
|
- naughtynatural.com/photos/
|
|
scraper: galleryScraper
|
|
xPathScrapers:
|
|
sceneScraper:
|
|
common:
|
|
$url: //link[@rel="canonical"]/@href
|
|
scene:
|
|
Title: &title //h1[@class="entry-title"]/text()
|
|
Studio: &studio
|
|
Name:
|
|
fixed: Naughty Natural
|
|
Date: &date
|
|
selector: //meta[@property="article:published_time"]/@content
|
|
postProcess:
|
|
- replace:
|
|
- regex: (^\d{4}-\d{2}-\d{2}).*
|
|
with: $1
|
|
- parseDate: 2006-01-02
|
|
Details:
|
|
selector: //p[@class="description"]/text()
|
|
Tags: &tags
|
|
Name: //span[@class="categories"]/a
|
|
Performers: &performers
|
|
Name: //span[@class="post_author"]/a
|
|
Image:
|
|
selector: //script[@type="text/javascript"][contains(text(),"jwplayer") and contains(text(),"jpg")]
|
|
postProcess:
|
|
- replace:
|
|
- regex: .*(wp-content.+jpg).*(https:\/\/[^\/]*).*
|
|
with: $2/$1
|
|
URL: &url
|
|
selector: $url
|
|
galleryScraper:
|
|
common:
|
|
$photopage: //section[@id='photos_page-page']
|
|
gallery:
|
|
Title: *title
|
|
Studio: *studio
|
|
Date: *date
|
|
Details:
|
|
selector: //div[@class="gallery_description"]/p/text()
|
|
Tags: *tags
|
|
Performers: *performers
|
|
# Last Updated September 03, 2023 |