[koharu] cleanup

- update BASE_PATTERN formatting
- fix groups indices
- add tests for new domains
- update docs/supportedsites

docs/supportedsites.md

@@ -511,12 +511,6 @@ Consider all listed sites to potentially be NSFW.
     <td>Soundtracks</td>
     <td></td>
 </tr>
-<tr>
-    <td>Koharu</td>
-    <td>https://koharu.to/</td>
-    <td>Favorites, Galleries, Search Results</td>
-    <td></td>
-</tr>
 <tr>
     <td>Komikcast</td>
     <td>https://komikcast.cz/</td>
@@ -829,6 +823,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Articles, Tag Searches</td>
     <td></td>
 </tr>
+<tr>
+    <td>SchaleNetwork</td>
+    <td>https://niyaniya.moe/</td>
+    <td>Favorites, Galleries, Search Results</td>
+    <td></td>
+</tr>
 <tr>
     <td>Scrolller</td>
     <td>https://scrolller.com/</td>

gallery_dl/extractor/koharu.py

@@ -6,13 +6,19 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-"""Extractors for https://koharu.to/"""
+"""Extractors for https://niyaniya.moe/"""
 
 from .common import GalleryExtractor, Extractor, Message
 from .. import text, exception
 from ..cache import cache
 
-BASE_PATTERN = r"(?i)(?:https?://)?((?:anchira|seia)\.to|(?:niyaniya|shupogaki)\.moe|hoshino\.one)"
+BASE_PATTERN = (
+    r"(?i)(?:https?://)?("
+    r"(?:niyaniya|shupogaki)\.moe|"
+    r"(?:koharu|anchira|seia)\.to|"
+    r"(?:hoshino)\.one"
+    r")"
+)
 
 
 class KoharuExtractor(Extractor):
@@ -179,11 +185,11 @@ class KoharuGalleryExtractor(KoharuExtractor, GalleryExtractor):
                     break
             except KeyError:
                 self.log.debug("%s: Format %s is not available",
-                               self.groups[0], fmtid)
+                               self.groups[1], fmtid)
         else:
             raise exception.NotFoundError("format")
 
-        self.log.debug("%s: Selected format %s", self.groups[0], fmtid)
+        self.log.debug("%s: Selected format %s", self.groups[1], fmtid)
         fmt["w"] = fmtid
         return fmt
 
@@ -195,7 +201,7 @@ class KoharuSearchExtractor(KoharuExtractor):
     example = "https://niyaniya.moe/?s=QUERY"
 
     def items(self):
-        params = text.parse_query(self.groups[0])
+        params = text.parse_query(self.groups[1])
         params["page"] = text.parse_int(params.get("page"), 1)
         return self._pagination("/books", params)
 
@@ -209,7 +215,7 @@ class KoharuFavoriteExtractor(KoharuExtractor):
     def items(self):
         self.login()
 
-        params = text.parse_query(self.groups[0])
+        params = text.parse_query(self.groups[1])
         params["page"] = text.parse_int(params.get("page"), 1)
         return self._pagination("/favorites", params)
 

scripts/supportedsites.py

@@ -84,6 +84,7 @@ CATEGORY_MAP = {
     "jpgfish"        : "JPG Fish",
     "kabeuchi"       : "かべうち",
     "kemonoparty"    : "Kemono",
+    "koharu"         : "SchaleNetwork",
     "livedoor"       : "livedoor Blog",
     "ohpolly"        : "Oh Polly",
     "omgmiamiswimwear": "Omg Miami Swimwear",

test/results/koharu.py

@@ -66,9 +66,24 @@ __tests__ = (
 },
 
 {
-    "#url"     : "https://anchira.to/g/14216/6c67076fdd45",
+    "#url"  : "https://koharu.to/g/14216/6c67076fdd45",
-    "#category": ("", "koharu", "gallery"),
+    "#class": koharu.KoharuGalleryExtractor,
-    "#class"   : koharu.KoharuGalleryExtractor,
+},
+{
+    "#url"  : "https://anchira.to/g/14216/6c67076fdd45",
+    "#class": koharu.KoharuGalleryExtractor,
+},
+{
+    "#url"  : "https://seia.to/g/14216/6c67076fdd45",
+    "#class": koharu.KoharuGalleryExtractor,
+},
+{
+    "#url"  : "https://shupogaki.moe/g/14216/6c67076fdd45",
+    "#class": koharu.KoharuGalleryExtractor,
+},
+{
+    "#url"  : "https://hoshino.one/g/14216/6c67076fdd45",
+    "#class": koharu.KoharuGalleryExtractor,
 },
 
 {