56 lines
1.7 KiB
YAML
56 lines
1.7 KiB
YAML
name: AkiraLaneProductions
|
|
sceneByURL:
|
|
- action: scrapeXPath
|
|
url:
|
|
- akiralane.com/tour/
|
|
- akiralanebound.com/tour/
|
|
- pantyhoselane.com/tour/
|
|
scraper: sceneScraper
|
|
xPathScrapers:
|
|
sceneScraper:
|
|
scene:
|
|
Title:
|
|
selector: //h1
|
|
Details: //div[@class="videocontent"]/p
|
|
Image:
|
|
selector: //base/@href | //script[contains(.,'poster')]
|
|
concat: __SEP__
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^.*(https://[^/]+).+src0_.x="([^"]+).+
|
|
with: $1$2
|
|
Date:
|
|
selector: //div[@class="videodetails"]/p[@class="date"]
|
|
postProcess:
|
|
- replace:
|
|
- regex: "^([0-9/]+).*"
|
|
with: $1
|
|
- parseDate: 01/02/2006
|
|
Tags:
|
|
Name: //div[@class="videodetails"]//a[contains(@href,"categories")]/text()
|
|
Performers:
|
|
Name:
|
|
selector: //p[@class="modelname"]/comment()
|
|
postProcess:
|
|
- replace:
|
|
# Try to extract model names from comment
|
|
# https://regex101.com/r/IF0T90/1
|
|
- regex: .*?>([A-Z][^<>]+).*?(:?</a>\s*</span>\s*-->)?
|
|
with: "$1|"
|
|
# Default to Akira Lane if the comment is empty (it's hardcoded in the site as well)
|
|
- regex: "<!-- -->"
|
|
with: "Akira Lane"
|
|
split: "|"
|
|
Studio:
|
|
Name:
|
|
selector: //base/@href
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^.*https://(www\.)?([^\.]+).+
|
|
with: $2
|
|
- map:
|
|
akiralane: Akira Lane
|
|
akiralanebound: Akira Lane Bound
|
|
pantyhoselane: Pantyhose Lane
|
|
# Last Updated April 1, 2024
|