From d00a0e85514bb31cae1291290c65840e899e6726 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 00:49:30 +0200
Subject: [PATCH 01/18] Update hstream.yml

 * Improved URL construction via sceneByFragment
 * Standardized output titles
 * Removed capture of tags related to resolution
 * added group construction in the sceneScraper
 * Added groupScraper support from URL
 * changed the search URL (with covers) to remove the post process change
 * Restored image "preview" for scenes
---
 scrapers/hstream.yml | 194 +++++++++++++++++++++++++++++++------------
 1 file changed, 139 insertions(+), 55 deletions(-)

diff --git a/scrapers/hstream.yml b/scrapers/hstream.yml
index f290cd934..a85f0ce5d 100644
--- a/scrapers/hstream.yml
+++ b/scrapers/hstream.yml
@@ -1,80 +1,164 @@
-name: hstream
-sceneByName:
-  action: scrapeXPath
-  queryURL: https://hstream.moe/search?search={}
-  scraper: sceneSearch 
-sceneByQueryFragment:
-  action: scrapeXPath
-  queryURL: "{url}"
-  scraper: sceneScraper     
+name: "hstream"
 
 sceneByFragment:
   action: scrapeXPath
   queryURL: https://hstream.moe/hentai/{filename}
   queryURLReplace:
     filename:
-      # Strip out everything after the first [
-      - regex: ([^[]+)\s.*
-        with: $1
-      # Remove non-word characters
-      - regex: \W+
-        with: "-"
-      # Remove leading zeroes
-      - regex: 0+(\d)
-        with: $1
+      # [HSUB] Anime_02_Title - sub eng - E05v2 Uncensored (HD) www.example.com [3bb935c6].mp4
+      # 1. Removes tags inside square brackets [xxx]
+      - regex: '\[[^\]]*\]'
+        with: ""
+      
+      # 2. Removes tags inside parentheses (xxx)
+      - regex: '\([^)]*\)'
+        with: ""
+      
+      # 3. Removes file extensions (.mp4, .avi, .mkv...)
+      - regex: '\.\w{2,4}$'
+        with: ""
+      
+      # 4. Removes known tags: sub eng, engsub, uncensored, www
+      - regex: '(?i)(sub[\s\-_]?eng|engsub|uncensored|censored|www\.[^\s]+)'
+        with: ""
+
+      # 5. Standardizes separators into hyphens
+      - regex: '[\s\._+]+'
+        with: '-'
+        
+      # 6. Removes extended prefixes for episodes and seasons (but keeps the number)
+      - regex: '(?i)(^|[\-])(?:ep|episode|episodio|act|vol|season|stagione)([\-]?\d{1,2})'
+        with: '$1$2'
+        
+      # 7. Converts short prefixes for seasons and episodes into numbers (e.g., S02E05 → 02-05)
+      - regex: '(?i)\b(e|s)(\d{1,2})((e|s)(\d{1,2}))?\b'
+        with: '$2-$5'
+
+      # 8. Removes version suffixes from numbers (v2, vFinal, vRev3)
+      - regex: '(?i)(\d{1,2})(?:-)?v(?:\d+|final|finale|rev\d*)\b'
+        with: '$1'
+
+      # 9. Converts any short number (max 2 digits) with a leading zero into -<number>
+      - regex: '(^|[^0-9])0?(\d{1,2})([^0-9]|$)'
+        with: '$1$2$3'
+      
+      # 10. Replaces invalid URL characters (but keeps hyphens)
+      - regex: '[^a-zA-Z0-9\-]+'
+        with: '-'
+      
+      # 11. Inserts a hyphen between letters and numbers (e.g., "abc2" → "abc-2")
+      - regex: '([a-zA-Z])(\d)'
+        with: '$1-$2'
+        
+      # 12. Removes everything after the last short number
+      - regex: '^(.*-\d{1,2})(?:-\d{1,2})*(?:-.*)?$'
+        with: '$1'
+        
+      # 13. Multiple hyphens → only one
+      - regex: '-+'
+        with: '-'
+      
+      # 14. Removes leading/trailing hyphens (with #12, trailing ones are already removed)
+      - regex: '^-+|-+$'
+        with: ""
   scraper: sceneScraper
+
 sceneByURL:
   - action: scrapeXPath
     url:
       - hstream.moe/hentai/
     scraper: sceneScraper
+
+sceneByName:
+  action: scrapeXPath
+  queryURL: https://hstream.moe/search?search={}&view=poster
+  scraper: sceneSearch
+
+sceneByQueryFragment:
+  action: scrapeXPath
+  queryURL: "{url}"
+  scraper: sceneScraper
+
+movieByURL:
+  - action: scrapeXPath
+    url:
+      - hstream.moe/hentai/
+    scraper: groupScraper
+
 xPathScrapers:
-  sceneSearch:              
-     scene:
-      URL:   //div[contains(@class,'relative')]/a/@href
-      Title:
-        selector: //div[contains(@class,'relative')]/a/img/@alt
-      Image:
-        selector: //div[contains(@class,'relative')]/a/img/@src
-        postProcess:
-          - replace:          
-              # 1) make relative paths absolute
-              - regex: '^/'                                     
-                with: https://hstream.moe/
-              # 2) turn “…/gallery‑…” into “…/cover‑…”
-              - regex: '/gallery-'
-                with: '/cover-'
-              # 3) drop the “‑thumbnail” tag
-              - regex: '-thumbnail'
-                with:
-              # 4) remove the extra frame index after the episode number
-              - regex: '(-ep-\d+)-\d+\.webp$'
-                with: $1.webp
   sceneScraper:
     scene:
-      Title: //h1
-      Date:
+      Title:
+        selector: //h1
+        postProcess:
+          - replace:
+              - regex: ' (\d{1})$'
+                with: ' 0$1'
+      Date: &date
         selector: //i[contains(@class, "fa-calendar")]/following-sibling::text()
         postProcess:
           - replace:
-              - regex: \s*(\d{4}-\d{2}-\d{2}).*
-                with: $1
+              - regex: '\s*(\d{4}-\d{2}-\d{2}).*'
+                with: '$1'
           - parseDate: 2006-01-02
-      Details: //p[contains(text(), "Description")]/following-sibling::p
+      Details: &details (//p[contains(text(), "Description")]/following-sibling::p)[1]
       Tags:
-        Name: //li[@class="inline-block p-1"]/a/text()
+        Name:
+          selector: //li[@class="inline-block p-1"]/a/text()
+          postProcess:
+            - map:
+                "48Fps": ""
+                "4K": ""
+                "4K 48Fps": ""
+                "Lq": ""
       Studio:
         Name: (//a[contains(@href, "studios")])[1]
-      Image: 
-        selector: //meta[@property="og:image"]/@content
+      Image: &image //meta[@property="og:image"]/@content
+      URL: //meta[@property="og:url"]/@content
+      Movies:
+        Name: //h1/a/text()
+        Aliases: //h2/text()
+        Date: *date
+        Synopsis: *details
+        URL: //h1/a/@href
+        FrontImage: &cover
+          selector: *image
+          postProcess:
+            - replace:
+                # 1) img gallery  ➜  1° cover
+                - regex: '/gallery-(ep-)\d+-\d+(\.[a-zA-Z0-9]+)$'
+                  with: '/cover-${1}1${2}'
+
+  sceneSearch:
+    scene:
+      Title: //div[contains(@class, "relative")]/a/img/@alt
+      URL: //div[contains(@class, "relative")]/a/@href
+      Image:
+        selector: //div[contains(@class, "relative")]/a/img/@src
         postProcess:
           - replace:
-                  # 1) gallery  ➜  cover
-                  - regex: gallery
-                    with: cover
-                  # 2) trim the trailing “-0” (or “-1”, etc.)
-                  - regex: (-ep-\d+)-\d+\.webp$
-                    with: $1.webp    
+              # 1) make relative paths absolute
+              - regex: '^/'                                     
+                with: https://hstream.moe/
 
-      URL: //meta[@property="og:url"]/@content
-# Last Updated May 29, 2025
\ No newline at end of file
+  groupScraper:
+    movie:
+      Name:
+        selector: //h1/text()
+        postProcess:
+          - replace:
+              - regex: '\s*\([^)]*\)'
+                with: ""
+      Aliases:
+        selector: //h1/text()
+        postProcess:
+          - replace:
+              - regex: '.*\(([^)]*)\)'
+                with: '$1'
+      Date: *date
+      Studio:
+        Name: //a[contains(@href, "studios")]/text()
+      Synopsis: *details
+      FrontImage: *cover
+
+# Last Updated June 15, 2025

From 23baf2a5046d7346ce0e1744031fd9683c735bb4 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 00:51:53 +0200
Subject: [PATCH 02/18] Update hanime.yml

 * Improved URL construction via sceneByFragment
 * Standardized output titles
 * Removed capture of tags related to resolution
 * Added group construction in the sceneScraper
 * Added scene URL construction from the cover URL
---
 scrapers/hanime.yml | 134 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 117 insertions(+), 17 deletions(-)

diff --git a/scrapers/hanime.yml b/scrapers/hanime.yml
index c9b89ea0f..d1302080c 100644
--- a/scrapers/hanime.yml
+++ b/scrapers/hanime.yml
@@ -1,30 +1,98 @@
-name: hanime
+name: "hanime"
+
 sceneByFragment:
   action: scrapeXPath
   queryURL: https://hanime.tv/videos/hentai/{filename}
   queryURLReplace:
     filename:
-      - regex: ^([a-z\-0-9]+?)(\-[0-9]{3,4}p)?\..+$
-        with: $1
+      # [HSUB] Anime_02_Title - sub eng - E05v2 Uncensored (HD) www.example.com [3bb935c6].mp4
+      # 1. Removes tags inside square brackets [xxx]
+      - regex: '\[[^\]]*\]'
+        with: ""
+      
+      # 2. Removes tags inside parentheses (xxx)
+      - regex: '\([^)]*\)'
+        with: ""
+      
+      # 3. Removes file extensions (.mp4, .avi, .mkv...)
+      - regex: '\.\w{2,4}$'
+        with: ""
+      
+      # 4. Removes known tags: sub eng, engsub, uncensored, www
+      - regex: '(?i)(sub[\s\-_]?eng|engsub|uncensored|censored|www\.[^\s]+)'
+        with: ""
+
+      # 5. Standardizes separators into hyphens
+      - regex: '[\s\._+]+'
+        with: '-'
+        
+      # 6. Removes extended prefixes for episodes and seasons (but keeps the number)
+      - regex: '(?i)(^|[\-])(?:ep|episode|episodio|act|vol|season|stagione)([\-]?\d{1,2})'
+        with: '$1$2'
+        
+      # 7. Converts short prefixes for seasons and episodes into numbers (e.g., S02E05 → 02-05)
+      - regex: '(?i)\b(e|s)(\d{1,2})((e|s)(\d{1,2}))?\b'
+        with: '$2-$5'
+
+      # 8. Removes version suffixes from numbers (v2, vFinal, vRev3)
+      - regex: '(?i)(\d{1,2})(?:-)?v(?:\d+|final|finale|rev\d*)\b'
+        with: '$1'
+
+      # 9. Converts any short number (max 2 digits) with a leading zero into -<number>
+      - regex: '(^|[^0-9])0?(\d{1,2})([^0-9]|$)'
+        with: '$1$2$3'
+      
+      # 10. Replaces invalid URL characters (but keeps hyphens)
+      - regex: '[^a-zA-Z0-9\-]+'
+        with: '-'
+      
+      # 11. Inserts a hyphen between letters and numbers (e.g., "abc2" → "abc-2")
+      - regex: '([a-zA-Z])(\d)'
+        with: '$1-$2'
+        
+      # 12. Removes everything after the last short number
+      - regex: '^(.*-\d{1,2})(?:-\d{1,2})*(?:-.*)?$'
+        with: '$1'
+        
+      # 13. Multiple hyphens → only one
+      - regex: '-+'
+        with: '-'
+      
+      # 14. Removes leading/trailing hyphens (with #12, trailing ones are already removed)
+      - regex: '^-+|-+$'
+        with: ""
   scraper: sceneScraper
+
 sceneByURL:
   - action: scrapeXPath
     url:
       - hanime.tv/
     scraper: sceneScraper
+
 xPathScrapers:
   sceneScraper:
     scene:
-      Title: //h1[@class="tv-title"]/text()
-      Date:
+      Title:
+        selector: //h1[@class="tv-title"]/text()
+        postProcess:
+          - replace:
+              - regex: '(\d+)$'
+                with: '- $1'
+              - regex: ' (\d{1})$'
+                with: ' 0$1'
+      Date: &date
         selector: //div[@class="hvpimbc-item"]/div[contains(.,"Release Date")]/../div[@class="hvpimbc-text grey--text"]/text()
         postProcess:
           - parseDate: January 2, 2006
-      Details:
+      Details: &details
         selector: //div[@class="mt-3 mb-0 hvpist-description"]//text()
         concat: "\n\n"
       Tags:
-        Name: //div[@class="hvpis-text grey--text text--lighten-1"]/a/div
+        Name:
+          selector: //div[@class="hvpis-text grey--text text--lighten-1"]/a/div
+          postProcess:
+            - map:
+                "hd": ""
       Studio:
         Name:
           selector: //div[@class="hvpimbc-item full"]/a[@class="hvpimbc-text"]/text()
@@ -32,14 +100,46 @@ xPathScrapers:
         selector: //script[contains(., "poster_url")]
         postProcess:
           - replace:
-              - regex: (.+?poster_url":")(.+?)(","cover_url".+)
-                with: $2
-              - regex: "u002F"
+              - regex: '(.+?poster_url":")(.+?)(","cover_url".+)'
+                with: '$2'
+              - regex: 'u002F'
                 with: ""
-              - regex: \\
-                with: /
-              - regex: "static-assets.highwinds-cdn.com"
-                with: "static-assets.droidbuzz.top"
-              - regex: "https://"
-                with: "https://i1.wp.com/"
-# Last Updated August 4, 2024
+              - regex: '\\'
+                with: '/'
+              - regex: 'static-assets.highwinds-cdn.com'
+                with: 'static-assets.droidbuzz.top'
+              - regex: 'https://'
+                with: 'https://i1.wp.com/'
+      # build the url from the cover:
+      URL:
+        selector: //img[@class="hvpi-cover"]/@src
+        postProcess:
+          - replace:
+              - regex: '^.*/([^/]+)\.[a-zA-Z0-9]+$'
+                with: '$1'
+              - regex: '(.+-\d+)(?:-[^-]+)?$'
+                with: 'https://hanime.tv/videos/hentai/$1'
+      Movies:
+        Name:
+          selector: //h1[@class="tv-title"]/text()
+          postProcess:
+            - replace:
+                - regex: ' (\d+)$'
+                  with: ""
+        Aliases: //h2/span[@class="mr-3 grey--text"]/text()
+        Date: *date
+        Synopsis: *details
+        FrontImage:
+          selector: //script[contains(., "cover_url")]
+          postProcess:
+            - replace:
+                - regex: '(.+?cover_url":")(.+?)(",".+)'
+                  with: '$2'
+                - regex: 'u002F'
+                  with: ""
+                - regex: '\\'
+                  with: '/'
+                - regex: '(.+-)(\d+)(-?[^-]+)$'
+                  with: '${1}1${3}'
+
+# Last Updated June 15, 2025

From d0dfac8e60b25a5e2e26e5bcd4b690452a6cdc0c Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 00:52:39 +0200
Subject: [PATCH 03/18] Create Oppai.yml

---
 scrapers/Oppai.yml | 135 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 135 insertions(+)
 create mode 100644 scrapers/Oppai.yml

diff --git a/scrapers/Oppai.yml b/scrapers/Oppai.yml
new file mode 100644
index 000000000..165ef7283
--- /dev/null
+++ b/scrapers/Oppai.yml
@@ -0,0 +1,135 @@
+name: "Oppai"
+
+sceneByFragment:
+  action: scrapeXPath
+  queryURL: https://oppai.stream/watch?e={filename}
+  queryURLReplace:
+    filename:
+      # Oppai keeps symbols in the url, so you can't filter out the "wrong" ones from the name
+      # 1. Removes tags inside square brackets [xxx]
+      - regex: '\[[^\]]*\]'
+        with: ""
+      
+      # 2. Removes tags inside parentheses (xxx)
+      - regex: '\([^)]*\)'
+        with: ""
+      
+      # 3. Removes file extensions (.mp4, .avi, .mkv...)
+      - regex: '\.\w{2,4}$'
+        with: ""
+      
+      # 4. Removes known tags: sub eng, engsub, uncensored, www
+      - regex: '(?i)(sub[\s\-_]?eng|engsub|uncensored|censored|www\.[^\s]+)'
+        with: ""
+      
+      # 5. Replaces problematic URL characters (no problem with: !?:()♪♥★→←☆)
+      - regex: '\-'
+        with: '~'
+      - regex: '\+'
+        with: 'Ž'
+      - regex: '\&'
+        with: 'č'
+        
+      # 6. Standardizes separators into hyphens
+      - regex: '[\s\._+]+'
+        with: '-'
+        
+      # 7. Removes extended prefixes for episodes and seasons (but keeps the number)
+      - regex: '(?i)(^|[\-])(?:ep|episode|episodio|act|vol|season|stagione)([\-]?\d{1,2})'
+        with: '$1$2'
+        
+      # 8. Converts short prefixes for seasons and episodes into numbers (e.g., S02E05 → 02-05)
+      - regex: '(?i)\b(e|s)(\d{1,2})((e|s)(\d{1,2}))?\b'
+        with: '$2-$5'
+
+      # 9. Removes version suffixes from numbers (v2, vFinal, vRev3)
+      - regex: '(?i)(\d{1,2})(?:-)?v(?:\d+|final|finale|rev\d*)\b'
+        with: '$1'
+
+      # 10. Converts any short number (max 2 digits) with a leading zero into -<number>
+      - regex: '(^|[^0-9])0?(\d{1,2})([^0-9]|$)'
+        with: '$1$2$3'
+      
+      # 11. Inserts a hyphen between letters and numbers (e.g., "abc2" → "abc-2")
+      - regex: '([a-zA-Z])(\d)'
+        with: '$1-$2'
+        
+      # 12. Removes everything after the last short number
+      - regex: '^(.*-\d{1,2})(?:-\d{1,2})*(?:-.*)?$'
+        with: '$1'
+        
+      # 13. Multiple hyphens → only one
+      - regex: '-+'
+        with: '-'
+      
+      # 14. Removes leading/trailing hyphens (with #12, trailing ones are already removed)
+      - regex: '^-+|-+$'
+        with: ""
+  scraper: sceneScraper
+
+sceneByURL:
+  - action: scrapeXPath
+    url:
+      - oppai.stream/watch?e=
+    scraper: sceneScraper
+
+xPathScrapers:
+  sceneScraper:
+    scene:
+      Title:
+        selector: //h1[contains(@class, "line")]/text()
+        postProcess:
+          - replace:
+              - regex: '(?i)\s+Ep\s+'
+                with: ' - '
+              - regex: ' (\d{1})$'
+                with: ' 0$1'
+      Details: &details //div[@class="description"]/h5/text()[1]
+      Tags:
+        Name:
+          selector: //a[contains(@class, "tag")]/h5/text()
+          postProcess:
+            - map:
+                "4k": ""
+                "hd": ""
+      Studio:
+        Name: //h6/a[@class="red"]/text()
+      Image:
+        selector: //meta[@property="og:image"]/@content
+        postProcess:
+          - replace:
+              - regex: '\?v=\d+$'
+                with: ""
+      # build the url from the title:
+      URL:
+        selector: //h1[contains(@class, "line")]/text()
+        postProcess:
+          - replace:
+              - regex: '\-'
+                with: '~'
+              - regex: '\+'
+                with: 'Ž'
+              - regex: '\&'
+                with: 'č'
+              - regex: '(?i)\s+Ep\s+(\d+)$'
+                with: ' $1'
+              - regex: '\s+'
+                with: '-'
+              - regex: '(.+)'
+                with: 'https://oppai.stream/watch?e=$1'
+      Movies:
+        Name:
+          selector: //h1[contains(@class, "line")]/text()
+          postProcess:
+          - replace:
+              - regex: '(?i)\s+Ep\s+\d+$'
+                with: ""
+        Aliases:
+          selector: //div[@class="description"]/h5/text()[2]
+          postProcess:
+          - replace:
+              - regex: '[^(]*\(([^)]*)\)[^)]*'
+                with: '$1'
+        Synopsis: *details
+
+# Last Updated June 15, 2025

From a8243b1c8b3e719c3f99705f5f2a5a4f40aee082 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 00:56:39 +0200
Subject: [PATCH 04/18] Create HentaiSubIta.yml

 * Italian plots
---
 scrapers/HentaiSubIta.yml | 194 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 194 insertions(+)
 create mode 100644 scrapers/HentaiSubIta.yml

diff --git a/scrapers/HentaiSubIta.yml b/scrapers/HentaiSubIta.yml
new file mode 100644
index 000000000..5983a94ed
--- /dev/null
+++ b/scrapers/HentaiSubIta.yml
@@ -0,0 +1,194 @@
+name: "Hentai Sub Ita"
+
+sceneByFragment:
+  action: scrapeXPath
+  queryURL: https://www.hentaisubita.net/{filename}/
+  queryURLReplace:
+    filename:
+      # [HSUB] Anime_02_Title - sub ita - E05v2 Uncensored (HD) www.example.com [3bb935c6].mp4
+      # 1. Rimuove tag tra parentesi quadre [xxx]
+      - regex: '\[[^\]]*\]'
+        with: ""
+      
+      # 2. Rimuove tag tra parentesi tonde (xxx)
+      - regex: '\([^)]*\)'
+        with: ""
+      
+      # 3. Rimuove estensione file (.mp4, .avi, .mkv...)
+      - regex: '\.\w{2,4}$'
+        with: ""
+      
+      # 4. Rimuove tag noti: sub ita, itasub, uncensored, www
+      - regex: '(?i)(sub[\s\-_]?ita|itasub|uncensored|censored|www\.[^\s]+)'
+        with: ""
+
+      # 5. Standardizza separatori in trattini
+      - regex: '[\s\._+]+'
+        with: '-'
+        
+      # 6. Rimuove prefissi estesi di episodi e stagioni (ma lascia il numero)
+      - regex: '(?i)(^|[\-])(?:ep|episode|episodio|act|vol|season|stagione)([\-]?\d{1,2})'
+        with: '$1$2'
+        
+      # 7. Converte prefissi brevi di stagione e episodio in numeri (es. S02E05 → 02-05)
+      - regex: '(?i)\b(e|s)(\d{1,2})((e|s)(\d{1,2}))?\b'
+        with: '$2-$5'
+
+      # 8. Rimuove suffissi di versione dai numeri (v2, vFinal, vRev3)
+      - regex: '(?i)(\d{1,2})(?:-)?v(?:\d+|final|finale|rev\d*)\b'
+        with: '$1'
+
+      # 9. Converte ogni numero breve (max 2 cifre) con zero iniziale in -<numero>
+      - regex: '(^|[^0-9])0?(\d{1,2})([^0-9]|$)'
+        with: '$1$2$3'
+      
+      # 10. Sostituisce caratteri non validi URL (ma lascia i trattini)
+      - regex: '[^a-zA-Z0-9\-]+'
+        with: '-'
+      
+      # 11. Inserisce trattino tra lettera e numero (es. "abc2" → "abc-2")
+      - regex: '([a-zA-Z])(\d)'
+        with: '$1-$2'
+        
+      # 12. Elimina tutto dopo l’ultimo numero breve
+      - regex: '^(.*-\d{1,2})(?:-\d{1,2})*(?:-.*)?$'
+        with: '$1'
+        
+      # 13. Trattini multipli → uno solo
+      - regex: '-+'
+        with: '-'
+      
+      # 14. Rimuove trattini iniziali/finali (con #12 i finali già non ci sono)
+      - regex: '^-+|-+$'
+        with: ""
+        
+      # 15. Aggiungi "episodio-" davanti all'ultimo numero
+      - regex: '(\d+)$'
+        with: 'episodio-$1'
+      
+      # 16. Se l'ultimo numero (episodio) è ad 1 cifra, aggiunge 0 davanti
+      - regex: '-(\d{1})$'
+        with: '-0$1'
+  scraper: sceneScraper
+
+sceneByURL:
+  - action: scrapeXPath
+    url:
+      - hentaisubita.net/
+    scraper: sceneScraper
+
+# scrape some information for the scene through the series
+sceneByName:
+  action: scrapeXPath
+  queryURL: https://www.hentaisubita.net/?s={}
+  scraper: sceneSearch
+
+sceneByQueryFragment:
+  action: scrapeXPath
+  queryURL: "{url}"
+  scraper: ScenefromSeriesScraper
+
+movieByURL:
+  - action: scrapeXPath
+    url:
+      - hentaisubita.net/anime/
+    scraper: groupScraper
+
+xPathScrapers:
+  commonXPaths:
+    scene:
+      Title: &title //h1[@class="entry-title"]/text()
+      Details: &details
+        selector: //div[contains(@class, 'desc') and contains(@class, 'mindes')]//text()
+        concat: "\n\n"
+      URL: &url //meta[@property="og:url"]/@content
+      # Date is approximate having only the year
+      Date: &date
+        selector: //span[@class="split"][b[text()="Anno:"]]/text()
+        postProcess:
+          - replace:
+              - regex: '\s*(\d{4})'
+                with: '$1'
+          - parseDate: 2006
+      # Site only have the covers (not thumbnails)
+      Image: &image //meta[@property="og:image"]/@content
+      Studio: &studio
+        Name: //div[@class="spe"]/span[b[text()="Studio:"]]/a/text()
+      Tags: &tags
+        Name:
+          selector: //div[@class="genxed"]/a[@rel="tag"]/text()
+          postProcess:
+            - map:
+                "Altro": ""
+                "Anime Bondage": "Bondage"
+                "HD": ""
+      Aliases: &aliases //span[@class="alter"]/text()
+      Synopsis: &synopsis
+        selector: //div[@class="entry-content"]/p//text()
+        concat: "\n\n"
+
+  sceneScraper:
+    scene:
+      Title:
+        selector: *title
+        postProcess:
+          - replace:
+              - regex: '(?i)\s+episodio\s+'
+                with: ' - '
+      Date: *date
+      Details: *details
+      Tags: *tags
+      Studio: *studio
+      Image: *image
+      URL: *url
+      Movies:
+        Name: //meta[@property="article:section"]/@content
+        Aliases: *aliases
+        Date: *date
+        Synopsis: *details
+        URL: (//li/a[@itemprop="item"])[2]/@href
+        FrontImage: *image
+        
+  sceneSearch:
+    scene:
+      Title: //article[@class="bs"]/div/a/div[@class="tt"]/text()
+      URL: //article[@class="bs"]/div/a[@class="tip"]/@href
+      Image: //article[@class="bs"]//img/@data-src
+
+  ScenefromSeriesScraper:
+    scene:
+      Title:
+        selector: *title
+        postProcess:
+          - replace:
+              - regex: '$'
+                with: ' - 00'
+      Date: *date
+      Details: *synopsis
+      Tags: *tags
+      Studio: *studio
+      Image: *image
+      URL: 
+        selector: *url
+        postProcess:
+          - replace:
+              - regex: '^(https://[^/]+)/anime/([^/]+)/'
+                with: '$1/$2-episodio-00/'
+      Movies:
+        Name: *title
+        Aliases: *aliases
+        Date: *date
+        Synopsis: *synopsis
+        URL: *url
+        FrontImage: *image
+
+  groupScraper:
+    movie:
+      Name: *title
+      Aliases: *aliases
+      Date: *date
+      Studio: *studio
+      Synopsis: *synopsis
+      FrontImage: *image
+
+# Last Updated June 15, 2025

From 2bb849fd16b126e76c5039e153b9166797cca145 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 00:57:18 +0200
Subject: [PATCH 05/18] Create HentaiSaturn.yml

 * Italian plots
---
 scrapers/HentaiSaturn.yml | 232 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 232 insertions(+)
 create mode 100644 scrapers/HentaiSaturn.yml

diff --git a/scrapers/HentaiSaturn.yml b/scrapers/HentaiSaturn.yml
new file mode 100644
index 000000000..58d1fcda2
--- /dev/null
+++ b/scrapers/HentaiSaturn.yml
@@ -0,0 +1,232 @@
+name: "HentaiSaturn"
+
+sceneByFragment:
+  action: scrapeXPath
+  queryURL: https://www.hentaisaturn.tv/episode/{filename}
+  queryURLReplace:
+    filename:
+      # [HSUB] Anime_02_Title - sub ita - E05v2 Uncensored (HD) www.example.com [3bb935c6].mp4
+      # 1. Rimuove tag tra parentesi quadre [xxx]
+      - regex: '\[[^\]]*\]'
+        with: ""
+      
+      # 2. Rimuove tag tra parentesi tonde (xxx)
+      - regex: '\([^)]*\)'
+        with: ""
+      
+      # 3. Rimuove estensione file (.mp4, .avi, .mkv...)
+      - regex: '\.\w{2,4}$'
+        with: ""
+      
+      # 4. Rimuove tag noti: sub ita, itasub, uncensored, www
+      - regex: '(?i)(sub[\s\-_]?ita|itasub|uncensored|censored|www\.[^\s]+)'
+        with: ""
+
+      # 5. Standardizza separatori in trattini
+      - regex: '[\s\._+]+'
+        with: '-'
+        
+      # 6. Rimuove prefissi estesi di episodi e stagioni (ma lascia il numero)
+      - regex: '(?i)(^|[\-])(?:ep|episode|episodio|act|vol|season|stagione)([\-]?\d{1,2})'
+        with: '$1$2'
+        
+      # 7. Converte prefissi brevi di stagione e episodio in numeri (es. S02E05 → 02-05)
+      - regex: '(?i)\b(e|s)(\d{1,2})((e|s)(\d{1,2}))?\b'
+        with: '$2-$5'
+
+      # 8. Rimuove suffissi di versione dai numeri (v2, vFinal, vRev3)
+      - regex: '(?i)(\d{1,2})(?:-)?v(?:\d+|final|finale|rev\d*)\b'
+        with: '$1'
+
+      # 9. Converte ogni numero breve (max 2 cifre) con zero iniziale in -<numero>
+      - regex: '(^|[^0-9])0?(\d{1,2})([^0-9]|$)'
+        with: '$1$2$3'
+      
+      # 10. Sostituisce caratteri non validi URL (ma lascia i trattini)
+      - regex: '[^a-zA-Z0-9\-]+'
+        with: '-'
+      
+      # 11. Inserisce trattino tra lettera e numero (es. "abc2" → "abc-2")
+      - regex: '([a-zA-Z])(\d)'
+        with: '$1-$2'
+        
+      # 12. Elimina tutto dopo l’ultimo numero breve
+      - regex: '^(.*-\d{1,2})(?:-\d{1,2})*(?:-.*)?$'
+        with: '$1'
+        
+      # 13. Trattini multipli → uno solo
+      - regex: '-+'
+        with: '-'
+      
+      # 14. Rimuove trattini iniziali/finali (con #12 i finali già non ci sono)
+      - regex: '^-+|-+$'
+        with: ""
+        
+      # 15. Aggiungi "ep-" davanti all'ultimo numero
+      - regex: '(\d+)$'
+        with: 'ep-$1'
+  scraper: sceneScraper
+
+sceneByURL:
+  - action: scrapeXPath
+    url:
+      - hentaisaturn.tv/episode/
+    scraper: sceneScraper
+
+# scrape some information for the scene through the series
+sceneByName:
+  action: scrapeXPath
+  queryURL: https://www.hentaisaturn.tv/hentailist?search={}
+  scraper: sceneSearch
+
+sceneByQueryFragment:
+  action: scrapeXPath
+  queryURL: "{url}"
+  scraper: ScenefromSeriesScraper
+
+movieByURL:
+  - action: scrapeXPath
+    url:
+      - hentaisaturn.tv/hentai/
+    scraper: groupScraper
+
+xPathScrapers:
+  commonXPaths:
+    scene:
+      Title: &title (//title[contains(text(), "HentaiSaturn")])[1]/text()
+      Details: &details //div[@class="card-body"]/b[.="Trama:"]/following-sibling::text()[1]
+      # Site only have the covers (not thumbnails)
+      Image: &image //meta[@property="og:image"]/@content
+      Tags: &tags
+        Name:
+          selector: //div/a[@class="badge badge-light generi-as mb-1"]/text()
+          postProcess:
+            - map:
+                "HD": ""
+      # series url from scene page
+      URL: &urlSeries //div[@class="card-body"]/a[@class="btn btn-light w-100 mt-3 mb-3"]/@href
+      Date: &date
+        selector: //div/b[text()="Data di uscita:"]/following-sibling::text()[1]
+        postProcess:
+          - replace:
+              - regex: 'Gennaio'   
+                with: 'January'
+              - regex: 'Febbraio'  
+                with: 'February'
+              - regex: 'Marzo'     
+                with: 'March'
+              - regex: 'Aprile'    
+                with: 'April'
+              - regex: 'Maggio'    
+                with: 'May'
+              - regex: 'Giugno'    
+                with: 'June'
+              - regex: 'Luglio'    
+                with: 'July'
+              - regex: 'Agosto'    
+                with: 'August'
+              - regex: 'Settembre' 
+                with: 'September'
+              - regex: 'Ottobre'   
+                with: 'October'
+              - regex: 'Novembre'  
+                with: 'November'
+              - regex: 'Dicembre'  
+                with: 'December'
+          - parseDate: 2 January 2006
+      Studio: &studio
+        Name: //div/b[text()="Studio:"]/following-sibling::text()[1]
+      Aliases: &aliases //div[@class="container hentai-title-as mb-3 w-100"]/div[@class="box-trasparente-alternativo rounded"]/text()
+      Synopsis: &synopsis
+        selector: //div[@id="full-trama"]//text() | //div[@id="shown-trama"]//text()
+
+  sceneScraper:
+    scene:
+      Title:
+        selector: *title
+        postProcess:
+          - replace:
+              - regex: '(?i)^HentaiSaturn - | Streaming.*$'
+                with: ""
+              - regex: '(?i)\s+episodio\s+'
+                with: ' - '
+              - regex: ' (\d{1})$'
+                with: ' 0$1'
+      Details: *details
+      Tags: *tags
+      Image: *image
+      URL:
+        selector: *title
+        postProcess:
+          - replace:
+              - regex: '(?i)^HentaiSaturn - | Streaming.*$'
+                with: ""
+              - regex: '(?i)\s+episodio\s+'
+                with: ' ep '
+              - regex: '[\s\._+]+'
+                with: '-'
+              - regex: '^(.*)$'
+                with: 'https://www.hentaisaturn.tv/episode/$1'
+      Movies:
+        Name: //div/b[text()="Titolo:"]/following-sibling::text()[1]
+        Synopsis: *details
+        URL: *urlSeries
+        FrontImage: *image
+        
+  sceneSearch:
+    scene:
+      Title: //div[@class="info-archivio"]/h3/a/text()
+      URL: //div[@class="info-archivio"]/h3/a/@href
+      Image: //div[@class="item-archivio"]//img[contains(@class, "copertina-archivio")]/@src
+      Details: //div[@class="info-archivio"]/a[@class="thumb image-wrapper"]/p/text()
+      #Tags:
+      #  Name: //div[@class="info-archivio"]/a[@class="badge badge-light generi-as mb-1"]/text()
+
+  ScenefromSeriesScraper:
+    scene:
+      Title:
+        selector: *title
+        postProcess:
+          - replace:
+              - regex: '(?i)^HentaiSaturn - | Streaming.*$'
+                with: ""
+              - regex: '$'
+                with: ' - 00'
+      Date: *date
+      Details: *synopsis
+      Tags: *tags
+      Studio: *studio
+      Image: *image
+      URL: 
+        selector: //div[contains(@class, 'episodes-button')]/a/@href
+        postProcess:
+          - replace:
+              - regex: '-(\d+)$'
+                with: '-0'
+      Movies:
+        Name:
+          selector: *title
+          postProcess:
+            - replace:
+                - regex: '(?i)^HentaiSaturn - | Streaming.*$'
+                  with: ""
+        Aliases: *aliases
+        Date: *date
+        Synopsis: *synopsis
+        FrontImage: *image
+
+  groupScraper:
+    movie:
+      Name:
+        selector: *title
+        postProcess:
+          - replace:
+              - regex: '(?i)^HentaiSaturn - | Streaming.*$'
+                with: ""
+      Aliases: *aliases
+      Date: *date
+      Studio: *studio
+      Synopsis: *synopsis
+      FrontImage: *image
+
+# Last Updated June 15, 2025

From 259dd29cf2476d872f6dfee200b723376b86c80b Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 15:39:54 +0200
Subject: [PATCH 06/18] Update HentaiSaturn.yml

fixed commonXPaths movies fields
---
 scrapers/HentaiSaturn.yml | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/scrapers/HentaiSaturn.yml b/scrapers/HentaiSaturn.yml
index 58d1fcda2..f3ea26088 100644
--- a/scrapers/HentaiSaturn.yml
+++ b/scrapers/HentaiSaturn.yml
@@ -136,9 +136,10 @@ xPathScrapers:
           - parseDate: 2 January 2006
       Studio: &studio
         Name: //div/b[text()="Studio:"]/following-sibling::text()[1]
-      Aliases: &aliases //div[@class="container hentai-title-as mb-3 w-100"]/div[@class="box-trasparente-alternativo rounded"]/text()
-      Synopsis: &synopsis
-        selector: //div[@id="full-trama"]//text() | //div[@id="shown-trama"]//text()
+      Movies:
+        Aliases: &aliases //div[@class="container hentai-title-as mb-3 w-100"]/div[@class="box-trasparente-alternativo rounded"]/text()
+        Synopsis: &synopsis
+          selector: //div[@id="full-trama"]//text() | //div[@id="shown-trama"]//text()
 
   sceneScraper:
     scene:

From 747de503584e34dbbdbdf3664d056208cd4db41d Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 15:41:33 +0200
Subject: [PATCH 07/18] Update HentaiSubIta.yml

fixed commonXPaths movies fields
---
 scrapers/HentaiSubIta.yml | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/scrapers/HentaiSubIta.yml b/scrapers/HentaiSubIta.yml
index 5983a94ed..fbbb90993 100644
--- a/scrapers/HentaiSubIta.yml
+++ b/scrapers/HentaiSubIta.yml
@@ -122,10 +122,11 @@ xPathScrapers:
                 "Altro": ""
                 "Anime Bondage": "Bondage"
                 "HD": ""
-      Aliases: &aliases //span[@class="alter"]/text()
-      Synopsis: &synopsis
-        selector: //div[@class="entry-content"]/p//text()
-        concat: "\n\n"
+      Movies:
+        Aliases: &aliases //span[@class="alter"]/text()
+        Synopsis: &synopsis
+          selector: //div[@class="entry-content"]/p//text()
+          concat: "\n\n"
 
   sceneScraper:
     scene:

From 349c80407bf153f4541d90808525b19a6e345968 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 17:14:51 +0200
Subject: [PATCH 08/18] Update HentaiSubIta.yml

---
 scrapers/HentaiSubIta.yml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scrapers/HentaiSubIta.yml b/scrapers/HentaiSubIta.yml
index fbbb90993..4196b6962 100644
--- a/scrapers/HentaiSubIta.yml
+++ b/scrapers/HentaiSubIta.yml
@@ -123,6 +123,7 @@ xPathScrapers:
                 "Anime Bondage": "Bondage"
                 "HD": ""
       Movies:
+        Name: &name //meta[@property="article:section"]/@content
         Aliases: &aliases //span[@class="alter"]/text()
         Synopsis: &synopsis
           selector: //div[@class="entry-content"]/p//text()
@@ -143,7 +144,7 @@ xPathScrapers:
       Image: *image
       URL: *url
       Movies:
-        Name: //meta[@property="article:section"]/@content
+        Name: *name
         Aliases: *aliases
         Date: *date
         Synopsis: *details

From 956cb2ecac0c7f1dd5b621bb8a163323e6158292 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Sun, 15 Jun 2025 17:15:42 +0200
Subject: [PATCH 09/18] Update HentaiSaturn.yml

---
 scrapers/HentaiSaturn.yml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scrapers/HentaiSaturn.yml b/scrapers/HentaiSaturn.yml
index f3ea26088..be0b8c91a 100644
--- a/scrapers/HentaiSaturn.yml
+++ b/scrapers/HentaiSaturn.yml
@@ -137,6 +137,7 @@ xPathScrapers:
       Studio: &studio
         Name: //div/b[text()="Studio:"]/following-sibling::text()[1]
       Movies:
+        Name: &name //div/b[text()="Titolo:"]/following-sibling::text()[1]
         Aliases: &aliases //div[@class="container hentai-title-as mb-3 w-100"]/div[@class="box-trasparente-alternativo rounded"]/text()
         Synopsis: &synopsis
           selector: //div[@id="full-trama"]//text() | //div[@id="shown-trama"]//text()
@@ -169,7 +170,7 @@ xPathScrapers:
               - regex: '^(.*)$'
                 with: 'https://www.hentaisaturn.tv/episode/$1'
       Movies:
-        Name: //div/b[text()="Titolo:"]/following-sibling::text()[1]
+        Name: *name
         Synopsis: *details
         URL: *urlSeries
         FrontImage: *image

From a73dd39cf8fc899aa38def8cfa427d647a42f318 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:30:58 +0200
Subject: [PATCH 10/18] Update hstream.yml

 * updated title template: Name ep02
---
 scrapers/hstream.yml | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/scrapers/hstream.yml b/scrapers/hstream.yml
index a85f0ce5d..642c67dc6 100644
--- a/scrapers/hstream.yml
+++ b/scrapers/hstream.yml
@@ -92,8 +92,10 @@ xPathScrapers:
         selector: //h1
         postProcess:
           - replace:
-              - regex: ' (\d{1})$'
-                with: ' 0$1'
+              - regex: '\s+-\s+(\d+)$'
+                with: ' ep$1'
+              - regex: ' ep(\d{1})$'
+                with: ' ep0$1'
       Date: &date
         selector: //i[contains(@class, "fa-calendar")]/following-sibling::text()
         postProcess:
@@ -161,4 +163,4 @@ xPathScrapers:
       Synopsis: *details
       FrontImage: *cover
 
-# Last Updated June 15, 2025
+# Last Updated June 24, 2025

From ae7996c5dc703c5d061e9978ea86c38172b3b5bc Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:31:43 +0200
Subject: [PATCH 11/18] Update Oppai.yml

 * updated title template: Name ep02
---
 scrapers/Oppai.yml | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/scrapers/Oppai.yml b/scrapers/Oppai.yml
index 165ef7283..680c70423 100644
--- a/scrapers/Oppai.yml
+++ b/scrapers/Oppai.yml
@@ -80,10 +80,10 @@ xPathScrapers:
         selector: //h1[contains(@class, "line")]/text()
         postProcess:
           - replace:
-              - regex: '(?i)\s+Ep\s+'
-                with: ' - '
-              - regex: ' (\d{1})$'
-                with: ' 0$1'
+              - regex: '(?i)\s+Ep\s+(\d+)$'
+                with: ' ep$1'
+              - regex: ' ep(\d{1})$'
+                with: ' ep0$1'
       Details: &details //div[@class="description"]/h5/text()[1]
       Tags:
         Name:
@@ -132,4 +132,4 @@ xPathScrapers:
                 with: '$1'
         Synopsis: *details
 
-# Last Updated June 15, 2025
+# Last Updated June 24, 2025

From 40dfeed4b8c76201520468ea24a1f4fa95ba8382 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:32:35 +0200
Subject: [PATCH 12/18] Update HentaiSubIta.yml

 * updated title template: Name ep02
---
 scrapers/HentaiSubIta.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/scrapers/HentaiSubIta.yml b/scrapers/HentaiSubIta.yml
index 4196b6962..8806f4c8f 100644
--- a/scrapers/HentaiSubIta.yml
+++ b/scrapers/HentaiSubIta.yml
@@ -135,8 +135,8 @@ xPathScrapers:
         selector: *title
         postProcess:
           - replace:
-              - regex: '(?i)\s+episodio\s+'
-                with: ' - '
+              - regex: '(?i)\s+episodio\s+(\d+)$'
+                with: ' ep$1'
       Date: *date
       Details: *details
       Tags: *tags
@@ -164,7 +164,7 @@ xPathScrapers:
         postProcess:
           - replace:
               - regex: '$'
-                with: ' - 00'
+                with: ' ep00'
       Date: *date
       Details: *synopsis
       Tags: *tags
@@ -193,4 +193,4 @@ xPathScrapers:
       Synopsis: *synopsis
       FrontImage: *image
 
-# Last Updated June 15, 2025
+# Last Updated June 24, 2025

From 289dd72cdc97dd920045dc43f3622c84fbdd9b09 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:33:00 +0200
Subject: [PATCH 13/18] Update HentaiSaturn.yml

 * updated title template: Name ep02
---
 scrapers/HentaiSaturn.yml | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/scrapers/HentaiSaturn.yml b/scrapers/HentaiSaturn.yml
index be0b8c91a..85277e295 100644
--- a/scrapers/HentaiSaturn.yml
+++ b/scrapers/HentaiSaturn.yml
@@ -150,10 +150,10 @@ xPathScrapers:
           - replace:
               - regex: '(?i)^HentaiSaturn - | Streaming.*$'
                 with: ""
-              - regex: '(?i)\s+episodio\s+'
-                with: ' - '
-              - regex: ' (\d{1})$'
-                with: ' 0$1'
+              - regex: '(?i)\s+episodio\s+(\d+)$'
+                with: ' ep$1'
+              - regex: ' ep(\d{1})$'
+                with: ' ep0$1'
       Details: *details
       Tags: *tags
       Image: *image
@@ -193,7 +193,7 @@ xPathScrapers:
               - regex: '(?i)^HentaiSaturn - | Streaming.*$'
                 with: ""
               - regex: '$'
-                with: ' - 00'
+                with: ' ep00'
       Date: *date
       Details: *synopsis
       Tags: *tags
@@ -231,4 +231,4 @@ xPathScrapers:
       Synopsis: *synopsis
       FrontImage: *image
 
-# Last Updated June 15, 2025
+# Last Updated June 24, 2025

From 3700f6c2b8fab65d6d347daea5a3e569188211b6 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:37:59 +0200
Subject: [PATCH 14/18] Update hanime.yml

 * updated title template: Name ep02
 * updated title with more cases
 * updated sceneByURL
 * added sceneByName/sceneByQueryFragment via python
---
 scrapers/hanime.yml | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/scrapers/hanime.yml b/scrapers/hanime.yml
index d1302080c..6eba46450 100644
--- a/scrapers/hanime.yml
+++ b/scrapers/hanime.yml
@@ -66,9 +66,21 @@ sceneByFragment:
 sceneByURL:
   - action: scrapeXPath
     url:
-      - hanime.tv/
+      - hanime.tv/videos/hentai/
     scraper: sceneScraper
 
+sceneByName:
+  action: script
+  script:
+    - python
+    - hanime.py
+
+sceneByQueryFragment:
+  action: script
+  script:
+    - python
+    - hanime.py
+
 xPathScrapers:
   sceneScraper:
     scene:
@@ -76,10 +88,10 @@ xPathScrapers:
         selector: //h1[@class="tv-title"]/text()
         postProcess:
           - replace:
-              - regex: '(\d+)$'
-                with: '- $1'
-              - regex: ' (\d{1})$'
-                with: ' 0$1'
+              - regex: '(?i)\s+(?:ep\.?|(?:- )?episode)?\s*(\d+)$'
+                with: ' ep$1'
+              - regex: ' ep(\d{1})$'
+                with: ' ep0$1'
       Date: &date
         selector: //div[@class="hvpimbc-item"]/div[contains(.,"Release Date")]/../div[@class="hvpimbc-text grey--text"]/text()
         postProcess:
@@ -124,7 +136,7 @@ xPathScrapers:
           selector: //h1[@class="tv-title"]/text()
           postProcess:
             - replace:
-                - regex: ' (\d+)$'
+                - regex: '(?i)\s+(?:ep\.?|(?:- )?episode)?\s*(\d+)$'
                   with: ""
         Aliases: //h2/span[@class="mr-3 grey--text"]/text()
         Date: *date
@@ -142,4 +154,4 @@ xPathScrapers:
                 - regex: '(.+-)(\d+)(-?[^-]+)$'
                   with: '${1}1${3}'
 
-# Last Updated June 15, 2025
+# Last Updated June 24, 2025

From 6e589371ba07f6be31f8981bbc7d9dcc971a97c2 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:42:59 +0200
Subject: [PATCH 15/18] Rename scrapers/hanime.yml to
 scrapers/hanime/hanime.yml

---
 scrapers/{ => hanime}/hanime.yml | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename scrapers/{ => hanime}/hanime.yml (100%)

diff --git a/scrapers/hanime.yml b/scrapers/hanime/hanime.yml
similarity index 100%
rename from scrapers/hanime.yml
rename to scrapers/hanime/hanime.yml

From f71e6b6719cb9b51c38ff7e18ac2c5cc9d489564 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 03:43:52 +0200
Subject: [PATCH 16/18] add python

---
 scrapers/hanime/hanime.py        | 70 ++++++++++++++++++++++++++++++++
 scrapers/hanime/requirements.txt |  1 +
 2 files changed, 71 insertions(+)
 create mode 100644 scrapers/hanime/hanime.py
 create mode 100644 scrapers/hanime/requirements.txt

diff --git a/scrapers/hanime/hanime.py b/scrapers/hanime/hanime.py
new file mode 100644
index 000000000..9b4a611cf
--- /dev/null
+++ b/scrapers/hanime/hanime.py
@@ -0,0 +1,70 @@
+import sys
+import json
+import requests
+import io
+sys.stdin = io.TextIOWrapper(sys.stdin.buffer, encoding='utf-8')
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
+
+
+HANIME_SEARCH_URL = "https://search.htv-services.com/"
+
+def search_hanime(query):
+    params = {
+        "search_text": query,
+        "tags": [],
+        "tags_mode": "AND",
+        "brands": [],
+        "blacklist": [],
+        "order_by": "views",
+        "ordering": "desc",
+        "page": 0
+    }
+
+    try:
+        response = requests.post(HANIME_SEARCH_URL, json=params)
+        data = response.json()
+        hits = json.loads(data.get("hits", "[]"))
+    except Exception as e:
+        print("Failed to fetch or parse JSON response", e, file=sys.stderr)
+        return []
+
+    return [
+        {
+            "Title": hit["name"],
+            "URL": f'https://hanime.tv/videos/hentai/{hit["slug"]}',
+            "Image": hit.get("cover_url", "")
+        }
+        for hit in hits
+    ]
+
+def main():
+    try:
+        raw_input = sys.stdin.read()
+        if not raw_input.strip():
+            print("No input from stdin", file=sys.stderr)
+            sys.exit(1)
+
+        raw = json.loads(raw_input)
+    except Exception as e:
+        print("Invalid JSON input:", e, file=sys.stderr)
+        sys.exit(1)
+
+    # CASE 1: Search mode (scene-by-name)
+    if "name" in raw:
+        results = search_hanime(raw["name"])
+        print(json.dumps(results, ensure_ascii=False))
+        return
+    # CASE 2: User selected a result – return URL and Title
+    else:
+        print(json.dumps({
+            "URL": raw["url"],
+            "Title": raw.get("title", "")
+        }, ensure_ascii=False))
+        return
+
+    # DEFAULT: Invalid input
+    print("Missing 'name' or 'url' in input", file=sys.stderr)
+    sys.exit(1)
+
+if __name__ == "__main__":
+    main()
diff --git a/scrapers/hanime/requirements.txt b/scrapers/hanime/requirements.txt
new file mode 100644
index 000000000..663bd1f6a
--- /dev/null
+++ b/scrapers/hanime/requirements.txt
@@ -0,0 +1 @@
+requests
\ No newline at end of file

From aa020082f1e37c0457966a508e3906fd320ac014 Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 14:58:47 +0200
Subject: [PATCH 17/18] Update HentaiSubIta.yml

 * removed incorrect parseDate
---
 scrapers/HentaiSubIta.yml | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/scrapers/HentaiSubIta.yml b/scrapers/HentaiSubIta.yml
index 8806f4c8f..61312b269 100644
--- a/scrapers/HentaiSubIta.yml
+++ b/scrapers/HentaiSubIta.yml
@@ -108,8 +108,7 @@ xPathScrapers:
         postProcess:
           - replace:
               - regex: '\s*(\d{4})'
-                with: '$1'
-          - parseDate: 2006
+                with: '${1}-01-01'
       # Site only have the covers (not thumbnails)
       Image: &image //meta[@property="og:image"]/@content
       Studio: &studio
@@ -193,4 +192,4 @@ xPathScrapers:
       Synopsis: *synopsis
       FrontImage: *image
 
-# Last Updated June 24, 2025
+# Last Updated June 25, 2025

From 7ba6bcae09389dd1757dfc25d9bcc2470762fc1f Mon Sep 17 00:00:00 2001
From: Lc4B <149880036+Lc4B@users.noreply.github.com>
Date: Wed, 25 Jun 2025 15:19:34 +0200
Subject: [PATCH 18/18] Update hanime.py

 * changed the search for ascending title
---
 scrapers/hanime/hanime.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scrapers/hanime/hanime.py b/scrapers/hanime/hanime.py
index 9b4a611cf..eadaaf13a 100644
--- a/scrapers/hanime/hanime.py
+++ b/scrapers/hanime/hanime.py
@@ -15,8 +15,8 @@ def search_hanime(query):
         "tags_mode": "AND",
         "brands": [],
         "blacklist": [],
-        "order_by": "views",
-        "ordering": "desc",
+        "order_by": "title_sortable",
+        "ordering": "asc",
         "page": 0
     }