105 lines
3.2 KiB
YAML
105 lines
3.2 KiB
YAML
name: "GroobyNetwork-Partial"
|
|
sceneByURL:
|
|
- action: scrapeXPath
|
|
url: &urls
|
|
# Gone through list at: grooby.com/about/websites/
|
|
- asiantgirl.com
|
|
- blacktgirlshardcore.com
|
|
- black-tgirls.com
|
|
- bobstgirls.com
|
|
- brazilian-transsexuals.com
|
|
- femout.xxx
|
|
- femoutsex.xxx #Scenes on 'femout.xxx' can some times be found on this one as well
|
|
- franks-tgirlworld.com
|
|
- grooby-archives.com
|
|
- groobygirls.com
|
|
- ladyboy-ladyboy.com
|
|
- ladyboy.xxx
|
|
- realtgirls.com
|
|
- tgirlsex.xxx
|
|
- tgirls.porn
|
|
- tgirls.xxx
|
|
- tgirlsfuck.com
|
|
- tgirlshookup.com
|
|
- tgirltops.com
|
|
- transexpov.com
|
|
- transgasm.com
|
|
- transnificent.com
|
|
scraper: sceneScraper
|
|
- action: scrapeXPath
|
|
url:
|
|
- groobyvr.com
|
|
scraper: sceneScraperGroobyVR
|
|
galleryByURL:
|
|
- action: scrapeXPath
|
|
url: *urls
|
|
scraper: galleryScraper
|
|
xPathScrapers:
|
|
sceneScraper:
|
|
scene:
|
|
Title: &title //p[@class="trailertitle"]/text()|//div[@class="trailer_toptitle_left"]/text()
|
|
Date: &date
|
|
selector: //div[@class="setdesc"]//b[contains(.,"Added")]/following-sibling::text()[1]
|
|
postProcess:
|
|
- parseDate: January 2, 2006
|
|
Details: &details
|
|
selector: //div[@class="trailerpage_info"]/p[not(@class)]/descendant-or-self::*/text()
|
|
concat: "\n\n"
|
|
Performers: &performers
|
|
Name: //div[@class="setdesc"]//a/text()
|
|
Studio: &studio
|
|
Name: //meta[@name="author"]/@content
|
|
URL:
|
|
selector: //link[@rel="canonical"]/@href
|
|
postProcess:
|
|
- replace:
|
|
- regex: (https://[^/]*)/.*
|
|
with: $1
|
|
Image:
|
|
selector: //link[@rel="canonical"]/@href|//img[contains(@class, "update_thumb thumbs stdimage")]/@src|//img[contains(@class, "update_thumb thumbs stdimage")]/@src0_1x|//div[@class="trailerposter"]/img/@src0
|
|
concat: "__SEPARATOR__"
|
|
postProcess:
|
|
- replace:
|
|
- regex: ^.*__SEPARATOR__// # bobstgirls
|
|
with: "https://"
|
|
- regex: ^(https://[^/]*)/.*(__SEPARATOR__.*)$
|
|
with: $1$2
|
|
- regex: content//
|
|
with: content/
|
|
- regex: __SEPARATOR__
|
|
with: ''
|
|
Tags: &tags
|
|
Name: //div[@class="set_tags"]/ul/li//a/text()
|
|
galleryScraper:
|
|
gallery:
|
|
Title: *title
|
|
Date: *date
|
|
Details: *details
|
|
Performers: *performers
|
|
Studio: *studio
|
|
Tags: *tags
|
|
sceneScraperGroobyVR:
|
|
scene:
|
|
Title: *title
|
|
Date:
|
|
selector: //div[@class="set_meta"]//b[contains(.,"Added")]/following-sibling::text()[1]
|
|
postProcess:
|
|
- parseDate: January 2, 2006
|
|
Details:
|
|
selector: //div[@class="trailerblock"]/p[not(@class)]/text()
|
|
concat: "\n\n"
|
|
Performers:
|
|
Name: //div[@class="trailer_toptitle_left"]//a/text()
|
|
Studio: *studio
|
|
Image:
|
|
selector: //dl8-video/@poster
|
|
postProcess:
|
|
- replace:
|
|
- regex: content// # errant double slash
|
|
with: content/
|
|
- replace:
|
|
- regex: ^/
|
|
with: https://www.groobyvr.com/
|
|
Tags: *tags
|
|
# Last Updated July 27, 2023
|