-
-
Notifications
You must be signed in to change notification settings - Fork 440
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
A small network of mostly gay sites whose structures were similar enough that I put them all in the same file
- Loading branch information
1 parent
c93f2e2
commit 1a16c5b
Showing
2 changed files
with
154 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,139 @@ | ||
| name: Raunchy Bastards | ||
| sceneByURL: | ||
| - action: scrapeXPath | ||
| url: | ||
| - boundjocks.com/scene/ | ||
| - boyshalfwayhouse.com/scene/ | ||
| - coltstudiogroup.com/scene/ | ||
| - daddycarl.com/scene/ | ||
| - hotoldermale.com/scene/ | ||
| - monstercub.com/scene/ | ||
| - naturalbornbreeders.com/scene/ | ||
| - older4me.com/scene/ | ||
| - raunchybastards.com/scene/ | ||
| - stockydudes.com/scene/ | ||
| - toplatindaddies.com/scene/ | ||
| scraper: oldStyleSite | ||
| - action: scrapeXPath | ||
| url: | ||
| - blackboyaddictionz.com/scene/ | ||
| - blacksondaddies.com/scene/ | ||
| - myfirstdaddy.com/scene/ | ||
| - playdaddy.com/scene/ | ||
| scraper: newStyleSite | ||
| xPathScrapers: | ||
| oldStyleSite: | ||
| common: | ||
| $scene: //div[contains(@class, "sceneContainer")] | ||
| scene: | ||
| Title: $scene/div[@class="sceneTitle"] | ||
| Code: | ||
| selector: $scene//div[contains(@class, "sceneImgBig")]/@id | ||
| postProcess: | ||
| - replace: | ||
| - regex: \D* | ||
| with: $1 | ||
| Date: | ||
| selector: $scene//span[contains(@class, "sceneDetails")] | ||
| postProcess: | ||
| - replace: | ||
| # https://regex101.com/r/rsjbb6/1 | ||
| - regex: ^(\w{3}\s*\d{1,2},\s*\d{4}).*?$ | ||
| with: $1 | ||
| - parseDate: Jan 2,2006 | ||
| # All of this can be replaced once scrapers get access to the URL they are scraping | ||
| Studio: | ||
| Name: | ||
| selector: &image > | ||
| $scene//video/@poster | ||
| | $scene//div[contains(@class, "sceneImgBig")]/img/@src | ||
| | //div[contains(@style, "background-image")]/@style | ||
| | //*[contains(@class, "videoTrailer") or contains(@class, "bgScene")]//@srcset | ||
| postProcess: &studioNameFromURL | ||
| - replace: | ||
| - regex: ^(?:https:\/\/[\w\.]*?)([^.]+)\.com.*$ | ||
| with: $1 | ||
| - map: | ||
| blackboyaddictionz: Black Boy Addictionz | ||
| blacksondaddies: Blacks on Daddies | ||
| boundjocks: Bound Jocks | ||
| boyshalfwayhouse: Boys Halfway House | ||
| coltstudiogroup: Colt Studio Group | ||
| daddycarl: Daddy Carl | ||
| hotoldermale: Hot Older Male | ||
| monstercub: Monster Cub | ||
| myfirstdaddy: My First Daddy | ||
| naturalbornbreeders: Natural Born Breeders | ||
| older4me: Older4Me | ||
| playdaddy: Play Daddy | ||
| raunchybastards: Raunchy Bastards | ||
| stockydudees: Stocky dudes | ||
| toplatindaddies: Top Latin Daddies | ||
| URL: | ||
| selector: *image | ||
| postProcess: | ||
| - replace: | ||
| - regex: ^(?:https:\/\/[\w\.]*?)([^.]+)\.com.*$ | ||
| with: https://$1.com | ||
| Performers: | ||
| Name: > | ||
| $scene//div[contains(@class, "scenePerformers")]/a | ||
| | $scene//div[@class="scenePerf"]/span[@class="perfName"] | ||
| URL: > | ||
| $scene//div[contains(@class, "scenePerformers")]/a/@href | ||
| | $scene//div[@class="scenePerf"]/@data-href | ||
| Tags: | ||
| Name: $scene//a[@class="sceneTagsLnk"]/text() | ||
| Details: | ||
| selector: $scene//div[contains(@class, "sceneDescription")]/text() | ||
| concat: "\n\n" | ||
| Image: | ||
| selector: *image | ||
| postProcess: | ||
| - replace: | ||
| - regex: .*url\("(.*)"\).* | ||
| with: $1 | ||
| - regex: \s*2x$ | ||
| with: | ||
|
|
||
| newStyleSite: | ||
| common: | ||
| $details: //div[contains(@class, "container_styled_1")] | ||
| scene: | ||
| Title: //h2[@class="main_title"] | ||
| Code: | ||
| selector: //link[@rel="canonical"]/@href | ||
| postProcess: | ||
| - replace: | ||
| - regex: \D* | ||
| with: $1 | ||
| # All of this can be replaced once scrapers get access to the URL they are scraping | ||
| Studio: | ||
| Name: | ||
| selector: //link[@rel="canonical"]/@href | ||
| postProcess: *studioNameFromURL | ||
| URL: | ||
| selector: //link[@rel="canonical"]/@href | ||
| postProcess: | ||
| - replace: | ||
| - regex: ^(?:https:\/\/[\w\.]*?)([^.]+)\.com.*$ | ||
| with: https://$1.com | ||
| Performers: | ||
| Name: $details//span[contains(@class, "perfImage")]/a | ||
| URL: $details//span[contains(@class, "perfImage")]/a/@href | ||
| Details: | ||
| selector: $details//p/text() | ||
| concat: "\n\n" | ||
| Date: | ||
| selector: ($details//h5[contains(text(), "Details")]/text())[1] | ||
| postProcess: | ||
| - replace: | ||
| # https://regex101.com/r/rsjbb6/1 | ||
| - regex: ^Details:\s+(\w{3}\s*\d{1,2},\s*\d{4}).*?$ | ||
| with: $1 | ||
| - parseDate: Jan 2,2006 | ||
| Image: | ||
| selector: //meta[@property="og:image"]/@content | ||
| Tags: | ||
| Name: $details//h5[contains(., "Categories")]/a/text() | ||
| # Last Updated September 08, 2023 |