From 9aeaf98cf14f529a084a06f3a40bbbe7dc5f65a7 Mon Sep 17 00:00:00 2001
From: Maista6969 <glad.beach5807@fastmail.com>
Date: Mon, 8 Apr 2024 03:17:53 +0200
Subject: [PATCH] Add new scrapers to TugPass

Several of these sites are better served with a secondary scraper, and Tease POV is
unique enough to warrant a separate scraper entirely
---
 scrapers/TugPass.yml | 87 +++++++++++++++++++++++++++++++-------------
 1 file changed, 62 insertions(+), 25 deletions(-)

diff --git a/scrapers/TugPass.yml b/scrapers/TugPass.yml
index 97c29e1f..7e959d7f 100644
--- a/scrapers/TugPass.yml
+++ b/scrapers/TugPass.yml
@@ -3,49 +3,53 @@ sceneByURL:
   - action: scrapeXPath
     url:
       - tugpass.com/videos
-    scraper: sceneScraper_network
+    scraper: network
   - action: scrapeXPath
-    url: 
-      - breedme.com/videos
+    url:
       - cumblastcity.com/videos
       - clubtug.com/videos
-      - ebonytugs.com/videos
-      - edgequeens.com/videos
       - familylust.com/videos
       - finishhim.com/videos
-      - jawbreakerz.com/videos
       - meanmassage.com/videos
-      - milfaf.com/videos
-      - mylked.com/videos
       - nookies.com/video
       - over40handjobs.com/videos
       - petite18.com/videos
       - seemomsuck.com/videos
+      - teentugs.com/videos
+    scraper: primary
+  - action: scrapeXPath
+    url:
+      - breedme.com/videos
+      - edgequeens.com/videos
+      - jawbreakerz.com/videos
+      - milfaf.com/videos
+      - mylked.com/videos
       - shadyspa.com/videos
       - shereacts.com/videos
+    scraper: secondary
+  - action: scrapeXPath
+    url:
       - teasepov.com/videos
-      - teentugs.com/videos
-    scraper: sceneScraper_sites
+    scraper: teasepov
+
 xPathScrapers:
-  sceneScraper_network:
+  network:
     scene:
       Details: &details //meta[@name="description"]/@content
       Performers: &performers
-        Name: //div[@class="featuringWrapper"]/a
+        Name: //div[@class="featuringWrapper"]/a | //div[@class="video-box"]//a[contains(@href, "/model/")]
       Title: &title
-          selector: //title/text()
-          postProcess:
-            - replace:
-                - regex: \s\|.+$
-                  with:
-                - regex: \s\-.+$
-                  with:
+        selector: //title/text()
+        postProcess:
+          - replace:
+              - regex: \s[|-].+$
+                with:
       # Scrape sanitized URL
       URL: &url //link[@rel="canonical"]/@href
       Image:
         selector: //div[@class="player"]/img/@src
         postProcess:
-           - replace:
+          - replace:
               - regex: ^
                 with: https://www.tugpass.com/
       Studio:
@@ -55,7 +59,7 @@ xPathScrapers:
             - replace:
                 - regex: ^\/[A-Za-z_-]+\/([A-Za-z0-9-]+)\/.+
                   with: $1
-  sceneScraper_sites:
+  primary:
     scene:
       Details: *details
       Performers: *performers
@@ -78,7 +82,7 @@ xPathScrapers:
                 with: $1
               - regex: ^(https?:.+(\.com)).+__SEP__(.+)
                 with: $1$3
-      Studio:
+      Studio: &studio
         Name:
           selector: //meta[@name="copyright"]/@content
           postProcess:
@@ -86,6 +90,39 @@ xPathScrapers:
                 - regex: Copyright\s(.+)\s\d{4}
                   with: $1
             - map:
-                "breedme": Breed Me
-                "milfaf": MILFAF
-# Last Updated March 27, 2024
+                breedme: Breed Me
+                milfaf: MILFAF
+  secondary:
+    scene:
+      Title: >-
+        //h3[@class="top-title"] |
+        //div[@class="title-top"]//h5
+      Details: //div[contains(@class, "video-detail") or contains(@class, "title-bottom")]/p
+      Date:
+        selector: //div[@class="title-top"]//span/text()
+        postProcess:
+          - replace:
+              - regex: ^\W+
+                with: ""
+          - parseDate: January 2, 2006
+      Image: //video/@poster
+      Performers:
+        Name: //div[contains(@class, "player") or contains(@class, "title-top")]//a[contains(@href, "models")]
+      URL: *url
+      Studio: *studio
+  # This one site is different enough that it gets its own scraper
+  teasepov:
+    scene:
+      Title: //div[@class="slideTitle"]
+      Details: //div[@class="videoDescription"]
+      Image: //div[@id="player"]/img/@src
+      Date:
+        selector: //div[@class="slideDate"]
+        postProcess:
+          - replace:
+              - regex: ^\W+
+                with: ""
+          - parseDate: January 2, 2006
+      URL: *url
+      Studio: *studio
+# Last Updated April 08, 2024