From a552fb5bcd6c6a1ff24b153072b6605356a5cd54 Mon Sep 17 00:00:00 2001
From: Allen <64094914+allendema@users.noreply.github.com>
Date: Thu, 29 Aug 2024 21:31:15 +0200
Subject: [PATCH] [generic] better directory formatting/md

---
 gallery_dl/extractor/generic.py |  8 ++++++--
 test/results/generic.py         | 16 ++++++++--------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/gallery_dl/extractor/generic.py b/gallery_dl/extractor/generic.py
index 16d4340c..a6c1d5ae 100644
--- a/gallery_dl/extractor/generic.py
+++ b/gallery_dl/extractor/generic.py
@@ -15,7 +15,7 @@ import re
 class GenericExtractor(Extractor):
     """Extractor for images in a generic web page."""
     category = "generic"
-    directory_fmt = ("{category}", "{pageurl}")
+    directory_fmt = ("{category}", "{subcategory}", "{path}")
     archive_fmt = "{imageurl}"
 
     # By default, the generic extractor is disabled
@@ -52,7 +52,10 @@ class GenericExtractor(Extractor):
             self.scheme = match.group('scheme')
         else:
             self.scheme = 'https://'
-            self.url = self.scheme + self.url
+            self.url = text.ensure_http_scheme(self.url, self.scheme)
+
+        self.subcategory = match.group('domain')
+        self.path = match.group('path')
 
         # Used to resolve relative image urls
         self.root = self.scheme + match.group('domain')
@@ -87,6 +90,7 @@ class GenericExtractor(Extractor):
     def metadata(self, page):
         """Extract generic webpage metadata, return them in a dict."""
         data = {}
+        data['path'] = self.path.replace("/", "")
         data['pageurl'] = self.url
         data['title'] = text.extr(page, '<title>', "</title>")
         data['description'] = text.extr(
diff --git a/test/results/generic.py b/test/results/generic.py
index 5ec0400e..4d940afe 100644
--- a/test/results/generic.py
+++ b/test/results/generic.py
@@ -10,7 +10,7 @@ from gallery_dl.extractor import generic
 __tests__ = (
 {
     "#url"     : "generic:https://www.nongnu.org/lzip/",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "www.nongnu.org"),
     "#class"   : generic.GenericExtractor,
     "#count"       : 1,
     "#sha1_content": "40be5c77773d3e91db6e1c5df720ee30afb62368",
@@ -23,7 +23,7 @@ __tests__ = (
 
 {
     "#url"     : "generic:https://räksmörgås.josefsson.org/",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "räksmörgås.josefsson.org"),
     "#class"   : generic.GenericExtractor,
     "#pattern" : "^https://räksmörgås.josefsson.org/",
     "#count"   : 2,
@@ -31,37 +31,37 @@ __tests__ = (
 
 {
     "#url"     : "generic:https://en.wikipedia.org/Main_Page",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "en.wikipedia.org"),
     "#class"   : generic.GenericExtractor,
 },
 
 {
     "#url"     : "generic:https://example.org/path/to/file?que=1?&ry=2/#fragment",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "example.org"),
     "#class"   : generic.GenericExtractor,
 },
 
 {
     "#url"     : "generic:https://example.org/%27%3C%23/%23%3E%27.htm?key=%3C%26%3E",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "example.org"),
     "#class"   : generic.GenericExtractor,
 },
 
 {
     "#url"     : "generic:https://en.wikipedia.org/Main_Page",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "en.wikipedia.org"),
     "#class"   : generic.GenericExtractor,
 },
 
 {
     "#url"     : "generic:https://example.org/path/to/file?que=1?&ry=2/#fragment",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "example.org"),
     "#class"   : generic.GenericExtractor,
 },
 
 {
     "#url"     : "generic:https://example.org/%27%3C%23/%23%3E%27.htm?key=%3C%26%3E",
-    "#category": ("", "generic", ""),
+    "#category": ("", "generic", "example.org"),
     "#class"   : generic.GenericExtractor,
 },