From bddcec49f1f58523e865322bff8c76ee04e4b238 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Tue, 1 Mar 2022 02:56:51 +0100
Subject: [PATCH] implement 'text.root_from_url()'

use domain from input URL for kemono
---
 gallery_dl/extractor/common.py      |  3 +--
 gallery_dl/extractor/kemonoparty.py |  2 +-
 gallery_dl/text.py                  |  7 +++++++
 test/test_text.py                   | 12 ++++++++++++
 4 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/gallery_dl/extractor/common.py b/gallery_dl/extractor/common.py
index 1cf00f14..026034cb 100644
--- a/gallery_dl/extractor/common.py
+++ b/gallery_dl/extractor/common.py
@@ -621,8 +621,7 @@ class BaseExtractor(Extractor):
                     if index:
                         self.category, self.root = self.instances[index-1]
                         if not self.root:
-                            url = text.ensure_http_scheme(match.group(0))
-                            self.root = url[:url.index("/", 8)]
+                            self.root = text.root_from_url(match.group(0))
                     else:
                         self.root = group
                         self.category = group.partition("://")[2]
diff --git a/gallery_dl/extractor/kemonoparty.py b/gallery_dl/extractor/kemonoparty.py
index 9b85fcbe..25484f0f 100644
--- a/gallery_dl/extractor/kemonoparty.py
+++ b/gallery_dl/extractor/kemonoparty.py
@@ -30,8 +30,8 @@ class KemonopartyExtractor(Extractor):
     def __init__(self, match):
         if match.group(1) == "coomer":
             self.category = "coomerparty"
-            self.root = "https://coomer.party"
             self.cookiedomain = ".coomer.party"
+        self.root = text.root_from_url(match.group(0))
         Extractor.__init__(self, match)
 
     def items(self):
diff --git a/gallery_dl/text.py b/gallery_dl/text.py
index ac4bbcbd..97ef3acb 100644
--- a/gallery_dl/text.py
+++ b/gallery_dl/text.py
@@ -46,6 +46,13 @@ def ensure_http_scheme(url, scheme="https://"):
     return url
 
 
+def root_from_url(url, scheme="https://"):
+    """Extract scheme and domain from a URL"""
+    if not url.startswith(("https://", "http://")):
+        return scheme + url[:url.index("/")]
+    return url[:url.index("/", 8)]
+
+
 def filename_from_url(url):
     """Extract the last part of an URL to use as a filename"""
     try:
diff --git a/test/test_text.py b/test/test_text.py
index 3ab9e73c..ffed7267 100644
--- a/test/test_text.py
+++ b/test/test_text.py
@@ -102,6 +102,18 @@ class TestText(unittest.TestCase):
         for value in INVALID_ALT:
             self.assertEqual(f(value), value)
 
+    def test_root_from_url(self, f=text.root_from_url):
+        result = "https://example.org"
+        self.assertEqual(f("https://example.org/")    , result)
+        self.assertEqual(f("https://example.org/path"), result)
+        self.assertEqual(f("example.org/")            , result)
+        self.assertEqual(f("example.org/path/")       , result)
+
+        result = "http://example.org"
+        self.assertEqual(f("http://example.org/")     , result)
+        self.assertEqual(f("http://example.org/path/"), result)
+        self.assertEqual(f("example.org/", "http://") , result)
+
     def test_filename_from_url(self, f=text.filename_from_url):
         result = "filename.ext"