52 lines
1.4 KiB
YAML
52 lines
1.4 KiB
YAML
name: "BadPuppy"
|
|
sceneByURL:
|
|
- action: scrapeXPath
|
|
url:
|
|
- badpuppy.com
|
|
- clubamateurusa.com
|
|
scraper: sceneScraper
|
|
xPathScrapers:
|
|
sceneScraper:
|
|
scene:
|
|
Title:
|
|
selector: //div/h3
|
|
Details:
|
|
selector: //td[@colspan="2"]
|
|
Performers:
|
|
Name:
|
|
selector: //td[@class="ten" and not(a[contains(@href,"categories")])]
|
|
postProcess:
|
|
- replace:
|
|
- regex: \([^)]+\)
|
|
with: ""
|
|
- regex: \s+
|
|
with: " "
|
|
split: ','
|
|
Image:
|
|
selector: //base/@href | //script[contains(.,"image:")]
|
|
concat: "__SEP__"
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^(.+)?__SEP__.+image:"([^"]+)?.+$
|
|
with: $1/$2
|
|
Date:
|
|
selector: //td/b[contains(text(),"Added")]
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^Added:\s*
|
|
with: ""
|
|
- parseDate: Jan 2, 2006
|
|
Tags:
|
|
Name: //a[@class="model_category_link" and contains(@href,"categories")]
|
|
Studio:
|
|
Name:
|
|
selector: //base/@href
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^.+?\.([^\.]+).+
|
|
with: $1
|
|
- map:
|
|
"badpuppy": BadPuppy
|
|
"clubamateurusa": ClubAmateurUSA
|
|
# Last Updated March 24, 2024
|