From 00fe308587ad30d30f9681b8d5e5f37527b8b823 Mon Sep 17 00:00:00 2001
From: jsouthgb <justin.southern@groundblock.dev>
Date: Wed, 25 Oct 2023 20:01:14 -0400
Subject: [PATCH 1/4] add support for erooups.com

---
 docs/supportedsites.md           |  6 ++++
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/erooups.py  | 52 ++++++++++++++++++++++++++++++++
 scripts/supportedsites.py        |  1 +
 4 files changed, 60 insertions(+)
 create mode 100644 gallery_dl/extractor/erooups.py

diff --git a/docs/supportedsites.md b/docs/supportedsites.md
index a15566df98..4ab897af9c 100644
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -181,6 +181,12 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Albums, Search Results, User Profiles</td>
     <td></td>
 </tr>
+<tr>
+    <td>Erooups</td>
+    <td>http://erooups.com/</td>
+    <td>Albums, Search Results, User Profiles</td>
+    <td></td>
+</tr>
 <tr>
     <td>ExHentai</td>
     <td>https://exhentai.org/</td>
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 22e4fe3412..b357fdcbc7 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -38,6 +38,7 @@
     "dynastyscans",
     "e621",
     "erome",
+    "erooups",
     "exhentai",
     "fallenangels",
     "fanbox",
diff --git a/gallery_dl/extractor/erooups.py b/gallery_dl/extractor/erooups.py
new file mode 100644
index 0000000000..e9a0ff1beb
--- /dev/null
+++ b/gallery_dl/extractor/erooups.py
@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+"""Extractors for http://erooups.com/"""
+
+from .common import Extractor, Message
+from .. import text
+
+
+class ErooupsExtractor(Extractor):
+    category = 'erooups'
+    directory_fmt = ('{category}', '{title}')
+    filename_fmt = '{filename}.{extension}'
+    archive_fmt = '{date}_{filename}'
+    subcategory = 'gallery'
+    pattern = r'(?:http?://)?(?:www\.)?erooups\.com'
+    root = 'http://erooups.com'
+
+    def items(self):
+        page = self.request(
+            text.ensure_http_scheme(self.url, scheme="http://")).text
+
+        data = self.metadata(page)
+        images = text.extract_iter(page, '</div><img src="', '?')
+
+        yield Message.Directory, data
+        for path in images:
+            if 'erooups' not in path:
+                path = self.root + path
+            image = text.nameext_from_url(path, {
+                'num': text.parse_int(path.split('_')[-1].split('.')[0]),
+                'date': data['date']
+            })
+            yield Message.Url, path, image
+
+    def metadata(self, page):
+        data = {}
+        data['pageurl'] = self.url
+        data['date'] = '-'.join(self.url.split('/')[3:6])
+        data['title'] = text.extr(
+            page, '<h1 class="title">', '</h1>')
+        data['tag'] = text.extr(
+            page, '"><strong>', '</strong></a>')
+        data['imagecount'] = text.extr(
+            page, '<div class="pics">', '</div>')
+
+        data = {k: text.unescape(data[k]) for k in data if data[k] != ""}
+
+        return data
diff --git a/scripts/supportedsites.py b/scripts/supportedsites.py
index 470b629d6d..4a5ac30194 100755
--- a/scripts/supportedsites.py
+++ b/scripts/supportedsites.py
@@ -43,6 +43,7 @@
     "e926"           : "e926",
     "e6ai"           : "e6AI",
     "erome"          : "EroMe",
+    "erooups"        : "erooups",
     "e-hentai"       : "E-Hentai",
     "exhentai"       : "ExHentai",
     "fallenangels"   : "Fallen Angels Scans",

From 16ef8958f2a89194b3183ec7d77e2dfdeebadd3a Mon Sep 17 00:00:00 2001
From: jsouthgb <justin.southern@groundblock.dev>
Date: Thu, 26 Oct 2023 11:13:40 -0400
Subject: [PATCH 2/4] Corrected extractor name for tests

---
 gallery_dl/extractor/erooups.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/gallery_dl/extractor/erooups.py b/gallery_dl/extractor/erooups.py
index e9a0ff1beb..e599b92fa0 100644
--- a/gallery_dl/extractor/erooups.py
+++ b/gallery_dl/extractor/erooups.py
@@ -10,7 +10,7 @@
 from .. import text
 
 
-class ErooupsExtractor(Extractor):
+class ErooupsGalleryExtractor(Extractor):
     category = 'erooups'
     directory_fmt = ('{category}', '{title}')
     filename_fmt = '{filename}.{extension}'
@@ -18,6 +18,7 @@ class ErooupsExtractor(Extractor):
     subcategory = 'gallery'
     pattern = r'(?:http?://)?(?:www\.)?erooups\.com'
     root = 'http://erooups.com'
+    example = 'http://erooups.com/2023/10/25/page-title-11-pics.html'
 
     def items(self):
         page = self.request(

From f7671e59790556a8f799b6f0e0a409a4bd1e748e Mon Sep 17 00:00:00 2001
From: jsouthgb <justin.southern@groundblock.dev>
Date: Wed, 29 Nov 2023 21:34:52 -0500
Subject: [PATCH 3/4] [erooups] rewrite for GalleryExtractor inheritance

---
 gallery_dl/extractor/erooups.py | 78 ++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 40 deletions(-)

diff --git a/gallery_dl/extractor/erooups.py b/gallery_dl/extractor/erooups.py
index e599b92fa0..919bdd149a 100644
--- a/gallery_dl/extractor/erooups.py
+++ b/gallery_dl/extractor/erooups.py
@@ -6,48 +6,46 @@
 
 """Extractors for http://erooups.com/"""
 
-from .common import Extractor, Message
+from .common import GalleryExtractor
 from .. import text
 
 
-class ErooupsGalleryExtractor(Extractor):
-    category = 'erooups'
-    directory_fmt = ('{category}', '{title}')
-    filename_fmt = '{filename}.{extension}'
-    archive_fmt = '{date}_{filename}'
-    subcategory = 'gallery'
-    pattern = r'(?:http?://)?(?:www\.)?erooups\.com'
-    root = 'http://erooups.com'
-    example = 'http://erooups.com/2023/10/25/page-title-11-pics.html'
-
-    def items(self):
-        page = self.request(
-            text.ensure_http_scheme(self.url, scheme="http://")).text
-
-        data = self.metadata(page)
-        images = text.extract_iter(page, '</div><img src="', '?')
-
-        yield Message.Directory, data
-        for path in images:
-            if 'erooups' not in path:
-                path = self.root + path
-            image = text.nameext_from_url(path, {
-                'num': text.parse_int(path.split('_')[-1].split('.')[0]),
-                'date': data['date']
-            })
-            yield Message.Url, path, image
+class ErooupsGalleryExtractor(GalleryExtractor):
+    category = "erooups"
+    directory_fmt = ("{category}", "{title}")
+    archive_fmt = "{date}_{filename}"
+    subcategory = "gallery"
+    pattern = (r"(?:http?://)?(?:www\.)?erooups\.com"
+               r"/(\d+)/(\d+)/(\d+)/([^/?#]+)")
+    root = "http://erooups.com"
+    example = "http://erooups.com/2023/10/25/page-title-11-pics.html"
+
+    def __init__(self, match):
+        self.year = match.group(1)
+        self.month = match.group(2)
+        self.day = match.group(3)
+        self.slug = match.group(4)
+        url = "{}/{}/{}/{}/{}".format(
+            self.root, self.year, self.month, self.day, self.slug)
+        GalleryExtractor.__init__(self, match, url)
+
+    def images(self, page):
+        fmt = "http://content.erooups.com/{}".format
+        extr = text.extr(page, 'class="imgs"', "</section>")
+        return [
+            (fmt(i), None) for i in text.extract_iter(
+                extr, 'src="http://content.erooups.com', '"')
+        ]
 
     def metadata(self, page):
-        data = {}
-        data['pageurl'] = self.url
-        data['date'] = '-'.join(self.url.split('/')[3:6])
-        data['title'] = text.extr(
-            page, '<h1 class="title">', '</h1>')
-        data['tag'] = text.extr(
-            page, '"><strong>', '</strong></a>')
-        data['imagecount'] = text.extr(
-            page, '<div class="pics">', '</div>')
-
-        data = {k: text.unescape(data[k]) for k in data if data[k] != ""}
-
-        return data
+        return {
+            "pageurl": self.url,
+            "date": text.parse_datetime(
+                "{}-{}-{}".format(self.year, self.month, self.day)),
+            "title": text.extr(
+                page, '<h1 class="title">', "</h1>"),
+            "tag": text.extr(
+                page, '"><strong>', "</strong></a>"),
+            "count": text.parse_int(text.extr(
+                page, '<div class="pics">', "</div>")),
+        }

From ae8ba88925c06cd81fe3405975d29724178a6f0b Mon Sep 17 00:00:00 2001
From: jsouthgb <justin.southern@groundblock.dev>
Date: Thu, 30 Nov 2023 22:21:19 -0500
Subject: [PATCH 4/4] [erooups] accommodate older albums using different "img
 src"

---
 gallery_dl/extractor/erooups.py | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/gallery_dl/extractor/erooups.py b/gallery_dl/extractor/erooups.py
index 919bdd149a..7a4c47de59 100644
--- a/gallery_dl/extractor/erooups.py
+++ b/gallery_dl/extractor/erooups.py
@@ -14,7 +14,6 @@ class ErooupsGalleryExtractor(GalleryExtractor):
     category = "erooups"
     directory_fmt = ("{category}", "{title}")
     archive_fmt = "{date}_{filename}"
-    subcategory = "gallery"
     pattern = (r"(?:http?://)?(?:www\.)?erooups\.com"
                r"/(\d+)/(\d+)/(\d+)/([^/?#]+)")
     root = "http://erooups.com"
@@ -30,11 +29,10 @@ def __init__(self, match):
         GalleryExtractor.__init__(self, match, url)
 
     def images(self, page):
-        fmt = "http://content.erooups.com/{}".format
-        extr = text.extr(page, 'class="imgs"', "</section>")
+        extr = text.extr(page, 'class="imgs">', "</section>")
         return [
-            (fmt(i), None) for i in text.extract_iter(
-                extr, 'src="http://content.erooups.com', '"')
+            (self.root + i if "erooups" not in i else i, None) for i in
+            text.extract_iter(extr, 'img src="', '"')
         ]
 
     def metadata(self, page):