From 50acf2ac843932467cc71a640388cb0657404663 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sun, 17 Nov 2024 16:58:54 +0100
Subject: [PATCH] [danbooru] add 'artist-search' extractor (#5348)

---
 docs/supportedsites.md           |  8 +++---
 gallery_dl/extractor/danbooru.py | 45 ++++++++++++++++++++++++--------
 scripts/supportedsites.py        |  3 +++
 test/results/danbooru.py         | 36 +++++++++++++++++++++++++
 4 files changed, 77 insertions(+), 15 deletions(-)

diff --git a/docs/supportedsites.md b/docs/supportedsites.md
index 4f06028f..14f62e08 100644
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -1138,25 +1138,25 @@ Consider all listed sites to potentially be NSFW.
 <tr>
     <td>Danbooru</td>
     <td>https://danbooru.donmai.us/</td>
-    <td>Pools, Popular Images, Posts, Tag Searches</td>
+    <td>Artists, Artist Searches, Pools, Popular Images, Posts, Tag Searches</td>
     <td>Supported</td>
 </tr>
 <tr>
     <td>ATFBooru</td>
     <td>https://booru.allthefallen.moe/</td>
-    <td>Pools, Popular Images, Posts, Tag Searches</td>
+    <td>Artists, Artist Searches, Pools, Popular Images, Posts, Tag Searches</td>
     <td>Supported</td>
 </tr>
 <tr>
     <td>Aibooru</td>
     <td>https://aibooru.online/</td>
-    <td>Pools, Popular Images, Posts, Tag Searches</td>
+    <td>Artists, Artist Searches, Pools, Popular Images, Posts, Tag Searches</td>
     <td>Supported</td>
 </tr>
 <tr>
     <td>Booruvar</td>
     <td>https://booru.borvar.art/</td>
-    <td>Pools, Popular Images, Posts, Tag Searches</td>
+    <td>Artists, Artist Searches, Pools, Popular Images, Posts, Tag Searches</td>
     <td>Supported</td>
 </tr>
 
diff --git a/gallery_dl/extractor/danbooru.py b/gallery_dl/extractor/danbooru.py
index 815efbce..1f33f9fb 100644
--- a/gallery_dl/extractor/danbooru.py
+++ b/gallery_dl/extractor/danbooru.py
@@ -108,6 +108,13 @@ class DanbooruExtractor(BaseExtractor):
             yield Message.Directory, post
             yield Message.Url, url, post
 
+    def items_artists(self):
+        for artist in self.artists():
+            artist["_extractor"] = DanbooruTagExtractor
+            url = "{}/posts?tags={}".format(
+                self.root, text.quote(artist["name"]))
+            yield Message.Queue, url, artist
+
     def metadata(self):
         return ()
 
@@ -302,15 +309,31 @@ class DanbooruArtistExtractor(DanbooruExtractor):
     pattern = BASE_PATTERN + r"/artists/(\d+)"
     example = "https://danbooru.donmai.us/artists/12345"
 
-    def items(self):
-        url = "{}/artists/{}.json".format(self.root, self.groups[-1])
-        artist = self.request(url).json()
+    items = DanbooruExtractor.items_artists
 
-        url = "{}/posts?tags={}".format(
-            self.root, text.quote(artist["name"]))
-        data = {
-            "_extractor": DanbooruTagExtractor,
-            "artist"    : artist,
-        }
-        yield Message.Directory, data
-        yield Message.Queue, url, data
+    def artists(self):
+        url = "{}/artists/{}.json".format(self.root, self.groups[-1])
+        return (self.request(url).json(),)
+
+
+class DanbooruArtistSearchExtractor(DanbooruExtractor):
+    """Extractor for danbooru artist searches"""
+    subcategory = "artist-search"
+    pattern = BASE_PATTERN + r"/artists/?\?([^#]+)"
+    example = "https://danbooru.donmai.us/artists?QUERY"
+
+    items = DanbooruExtractor.items_artists
+
+    def artists(self):
+        url = self.root + "/artists.json"
+        params = text.parse_query(self.groups[-1])
+        params["page"] = text.parse_int(params.get("page"), 1)
+
+        while True:
+            artists = self.request(url, params=params).json()
+
+            yield from artists
+
+            if len(artists) < 20:
+                return
+            params["page"] += 1
diff --git a/scripts/supportedsites.py b/scripts/supportedsites.py
index 4ba5a763..357d7c39 100755
--- a/scripts/supportedsites.py
+++ b/scripts/supportedsites.py
@@ -217,6 +217,9 @@ SUBCATEGORY_MAP = {
         "discord-server": "",
         "posts"         : "",
     },
+    "Danbooru": {
+        "artist-search": "Artist Searches",
+    },
     "desktopography": {
         "site": "",
     },
diff --git a/test/results/danbooru.py b/test/results/danbooru.py
index bad66413..3a857dbb 100644
--- a/test/results/danbooru.py
+++ b/test/results/danbooru.py
@@ -231,4 +231,40 @@ __tests__ = (
     "#count"   : 120,
 },
 
+{
+    "#url"     : "https://danbooru.donmai.us/artists/288683",
+    "#category": ("Danbooru", "danbooru", "artist"),
+    "#class"   : danbooru.DanbooruArtistExtractor,
+    "#urls"    : "https://danbooru.donmai.us/posts?tags=kaori_%28vuoian_appxv%29",
+
+    "created_at" : "2022-05-12T16:00:40.852-04:00",
+    "updated_at" : "2022-05-12T22:10:51.917-04:00",
+    "group_name" : "",
+    "id"         : 288683,
+    "is_banned"  : False,
+    "is_deleted" : False,
+    "name"       : "kaori_(vuoian_appxv)",
+    "other_names": [
+        "香",
+        "vuoian_appxv",
+    ],
+},
+
+{
+    "#url"     : "https://danbooru.donmai.us/artists?commit=Search&search%5Bany_name_matches%5D=yu&search%5Border%5D=created_at",
+    "#category": ("Danbooru", "danbooru", "artist-search"),
+    "#class"   : danbooru.DanbooruArtistSearchExtractor,
+    "#pattern" : danbooru.DanbooruTagExtractor.pattern,
+    "#count"   : "> 50",
+
+    "created_at" : str,
+    "updated_at" : str,
+    "group_name" : str,
+    "id"         : int,
+    "is_banned"  : bool,
+    "is_deleted" : bool,
+    "name"       : str,
+    "other_names": list,
+},
+
 )