Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Move LeWood to AEC Scraper #2224

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 14 additions & 14 deletions scrapers/AdultEmpireCash.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ sceneByURL:
- jodiwest.com/
- kingsoffetish.com/
- latinoguysporn.com/
- lewood.com/
- only3x.com/
- pornstarstroker.com/ # aggregator site?
- reaganfoxx.com/
Expand All @@ -44,6 +45,7 @@ movieByURL:
- elegantangel.com/
- filthykings.com/
- forbiddenfruitsfilms.com/
- lewood.com/
- rodneymoorestore.com
- severesexfilms.com/
# - shemalestrokers.com/ # Scenes published as movies?
Expand All @@ -56,8 +58,8 @@ movieByURL:
xPathScrapers:
sceneScraper:
scene:
Title: //h1[@class="description"]/text()
Date:
Title: &TitleSel //h1[@class="description"]/text()
Date: &DateSel
selector: //div[@class="release-date"][1]/text()
postProcess:
- parseDate: Jan 02, 2006
Expand All @@ -71,10 +73,13 @@ xPathScrapers:
Studio:
Name:
selector: //div[@class="studio"]/span[contains(text(),"Studio:")]/following-sibling::*
postProcess:
postProcess: &PP
# Override studio name only when needed
- map:
Evil Angel - LeWood: LeWood
Jay Rock Clips: Jay's POV
LeWood Productions: LeWood
LeWood Selects: LeWood
- replace:
# 'Jane Doe Clips' => 'Jane Doe'
- regex: \sClips$
Expand All @@ -90,6 +95,8 @@ xPathScrapers:
with: " "
- regex: " ,"
with: ","
- regex: "Francesca Le, Mark Wood"
with: "Le Wood"
Code:
selector: //meta[@name="og:url"]/@content
postProcess:
Expand All @@ -101,11 +108,8 @@ xPathScrapers:

movieScraper:
movie:
Name: //h1[@class="description"]/text()
Date:
selector: //div[@class="release-date"][1]/text()
postProcess:
- parseDate: Jan 02, 2006
Name: *TitleSel
Date: *DateSel
Synopsis:
selector: //div[@class="synopsis"]//text()
concat: "\n\n"
Expand All @@ -121,15 +125,11 @@ xPathScrapers:
Studio:
Name:
selector: //div[@class="studio"]/a
postProcess:
- replace:
# 'Jane Doe Clips' => 'Jane Doe'
- regex: \sClips$
with:
postProcess: *PP
FrontImage: //link[@rel="image_src"]/@href
BackImage: //div[@class="carousel-item"]/img/@data-src
driver:
headers:
- Key: "Cookie"
Value: "ageConfirmed=true"
# Last Updated October 27, 2024
# Last Updated March 9, 2025
7 changes: 3 additions & 4 deletions scrapers/Algolia/Algolia.py
Original file line number Diff line number Diff line change
Expand Up @@ -50,11 +50,10 @@
"devilstgirls": "https://www.devilstgirls.com/en/dvd",
"diabolic": "https://www.diabolic.com/en/movie",
"falconstudios": "https://www.falconstudios.com/en/movie",
"ragingstallion": "https://www.ragingstallion.com/en/movie",
"ragingstallion": "https://www.ragingstallion.com/en/movie",
"evilangel": "https://www.evilangel.com/en/movie",
"genderx": "https://www.genderxfilms.com/en/movie",
"girlfriendsfilms": "https://www.girlfriendsfilms.com/en/movie",
"lewood": "https://www.lewood.com/en/movie",
"hothouse": "https://www.hothouse.com/en/movie",
"outofthefamily": "https://www.outofthefamily.com/en/dvd",
"peternorth": "https://www.peternorth.com/en/dvd",
Expand Down Expand Up @@ -102,7 +101,7 @@
"Dpfanatics": "DP Fanatics",
"FalconStudios.com": "Falcon Studios",
"Gloryholesecrets": "Gloryhole Secrets",
"RagingStallion.com": "Raging Stallion",
"RagingStallion.com": "Raging Stallion",
"Janedoe": "Jane Doe Pictures",
"ModernDaySins": "Modern-Day Sins",
"Transgressivexxx": "TransgressiveXXX",
Expand All @@ -123,7 +122,7 @@
"Devil's Film",
"Evil Angel",
"FalconStudios.com",
"RagingStallion.com",
"RagingStallion.com",
"GenderXFilms",
"Give Me Teens",
"Gloryholesecrets",
Expand Down
5 changes: 1 addition & 4 deletions scrapers/EvilAngel/EvilAngel.yml
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@ sceneByURL:
- action: script
url:
- evilangel.com/en/video/
- lewood.com/en/video/
- pansexualx.com/en/video/
- transgressivexxx.com/en/video/
- tsfactor.com/en/video/
Expand All @@ -16,7 +15,6 @@ movieByURL:
- action: script
url:
- evilangel.com/en/movie/
- lewood.com/en/movie/
- pansexualx.com/en/movie/
- transgressivexxx.com/en/movie/
- tsfactor.com/en/movie/
Expand Down Expand Up @@ -49,7 +47,6 @@ galleryByURL:
- action: script
url:
- evilangel.com/en/photo/
- lewood.com/en/photo/
- pansexualx.com/en/photo/
- transgressivexxx.com/en/photo/
- tsfactor.com/en/photo/
Expand All @@ -58,4 +55,4 @@ galleryByURL:
- ../Algolia/Algolia.py
- evilangel
- gallery
# Last Updated December 26, 2022
# Last Updated March 9, 2025