Add scene and performer URL scrapers for RichardNailder network sites (#1807)

* Create RichardNailder.yml

Scene and Performer URL scrapers for the following sites:
- bringmeyoursister.com
- glassmannequin.com
- realcoloradogirls.com
- richardnailder.com

* Update SCRAPERS-LIST.md

Added sites using RichardNailder.yml:
bringmeyoursister.com
glassmannequin.com
realcoloradogirls.com
richardnailder.com
This commit is contained in:
MortonBridges 2024-05-01 22:46:01 -04:00 committed by GitHub
parent 3d1cabcf2e
commit cc2e374b02
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 136 additions and 0 deletions

View File

@ -357,6 +357,7 @@ brett-tyler.com|PornsiteManager.yml|:heavy_check_mark:|:x:|:heavy_check_mark:|:x
brickyates.com|brickyates.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
bride4k.com|Vip4K.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
bringmeaboy.com|MarsMedia.yml|:heavy_check_mark:|:x:|:x:|:x:|-|Gay
bringmeyoursister.com|RichardNailder.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|-|-
britstudio.xxx|Andomark.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
brittanyandrewsxxx.com|Andomark.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
brittanysbubbles.com|Andomark.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
@ -859,6 +860,7 @@ girlswhofuckgirls.com|Vivid.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
girlycast.com|Shopmaker.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
givemepink.com|sapphix.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
givemeteens.com|Adultime.yml|:heavy_check_mark:|:x:|:x:|:x:|Python|-
glassmannequin.com|RichardNailder.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|-|-
gloryhole.com|Dogfartnetwork.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|Python|-
gloryholehookups.com|CJXXX.yml|:heavy_check_mark:|:x:|:x:|:x:|-|Gay
gloryholeinitiations.com|Dogfartnetwork.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|Python|-
@ -1603,6 +1605,7 @@ rawfuckclub.com|RawFuckClub.yml|:heavy_check_mark:|:x:|:x:|:x:|-|Gay
rawroadnation.com|OLBMedia.yml|:heavy_check_mark:|:x:|:x:|:x:|-|Gay
reaganfoxx.com|AdultEmpireCash.yml|:heavy_check_mark:|:x:|:x:|:x:|-|MILF
realbikinigirls.com|WankItNow.yml|:heavy_check_mark:|:x:|:x:|:x:|-|VR
realcoloradogirls.com|RichardNailder.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|-|-
realfuckingdating.com|ThirdRockEnt.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
realitydudes.com|RealityDudes/RealityDudes.yml|:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|Python|Gay
realityjunkies.com|MileHighMedia_Straight/MileHighMedia_Straight.yml|:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|:heavy_check_mark:|Python|-
@ -1628,6 +1631,7 @@ renderfiend.com|insex.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
restrictedsenses.com|RestrictedSenses.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
retroporncz.com|PornCZ.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
richardmannsworld.com|InnOfSin.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-
richardnailder.com|RichardNailder.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|-|-
rickysroom.com|KBProductions.yml|:heavy_check_mark:|:x:|:x:|:heavy_check_mark:|Python|-
ridleydovarez.com|PornsiteManager.yml|:heavy_check_mark:|:x:|:heavy_check_mark:|:x:|-|Gay
riggsfilms.vip|RiggsFilms.yml|:heavy_check_mark:|:x:|:x:|:x:|-|-

132
scrapers/RichardNailder.yml Normal file
View File

@ -0,0 +1,132 @@
name: RichardNailder
sceneByURL:
- action: scrapeXPath
url:
- bringmeyoursister.com/movie_viewer
- glassmannequin.com/movie_viewer
- realcoloradogirls.com/movie_viewer
- richardnailder.com/movie_viewer
scraper: sceneScraper
performerByURL:
- action: scrapeXPath
url:
- bringmeyoursister.com/model_bio
- glassmannequin.com/model_bio
- realcoloradogirls.com/model_bio
- richardnailder.com/model_bio
scraper: performerScraper
xPathScrapers:
sceneScraper:
scene:
Title: //h2
Details: //p[span[@class='title']]/text()
Date:
selector: //li[contains(.,'Published:')]
postProcess:
- replace:
- regex: 'Published:'
with: ''
- parseDate: 2 Jan 2006
Tags:
Name:
selector: //ul[contains(@class,'square')]/li[contains(.,'Tags:') or contains(.,'Category')]/a
postProcess:
- replace:
- regex: '^#'
with: ''
Performers:
Name: //li[contains(.,'Featuring:')]/a
Image:
selector: //a[text()='Members Login']/@href | //img[contains(@src,'image.php')][1]/@src
concat: '/'
postProcess:
- replace:
- regex: 'members\.'
with: ''
Studio:
Name: //li[contains(.,'Published on:')]/a | //a[text()='Members Login']/@title
performerScraper:
performer:
Name:
selector: //article/h2
postProcess:
- replace:
- regex: "('s )?Bio$"
with: ''
Image:
selector: //a[text()='Members Login']/@href | //img[contains(@src,'size=3')]/@src
concat: '/'
postProcess:
- replace:
- regex: 'members\.'
with: ''
Gender:
selector: //li[contains(.,'Gender:')]
postProcess:
- replace:
- regex: 'Gender:'
with: ''
HairColor:
selector: //li[contains(.,'Hair Color:')]
postProcess:
- replace:
- regex: 'Hair Color:'
with: ''
EyeColor:
selector: //li[contains(.,'Eye Color:')]
postProcess:
- replace:
- regex: 'Eye Color:'
with: ''
Tattoos:
selector: //li[contains(.,'Tattoos:')]
postProcess:
- replace:
- regex: 'Tattoos:'
with: ''
Piercings:
selector: //li[contains(.,'Piercings:')]
postProcess:
- replace:
- regex: 'Piercings:'
with: ''
Ethnicity:
selector: //li[contains(.,'Ethnicity:')]
postProcess:
- replace:
- regex: 'Ethnicity:'
with: ''
FakeTits:
selector: //li[contains(.,'Real Boobs:')]
postProcess:
- replace:
- regex: 'Real Boobs:'
with: ''
- regex: '^\s*Yes'
with: '%No'
- regex: '^\s*No'
with: '%Yes'
- regex: '^%'
with: ''
Height:
selector: //li[contains(.,'Height:')]
postProcess:
- replace:
- regex: '[^\d]:'
with: ''
- regex: ^
with: '0.'
- feetToCm: true
Weight:
selector: //li[contains(.,'Weight:')]
postProcess:
- replace:
- regex: '[^\d]'
with: ''
- lbToKg: true
Details: //div[contains(@class,'contentWrapper')]//div[@class='panel']
# Last Updated May 1, 2024