From 4fd3c893fab3388031efc457f5a811b85ad975f6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Fri, 4 Nov 2022 15:04:34 +0100
Subject: [PATCH] [booru] adjust/match '_tags' and '_notes' code

---
 gallery_dl/extractor/gelbooru_v02.py | 23 ++++++++++++-----------
 gallery_dl/extractor/moebooru.py     | 26 ++++++++++++++------------
 2 files changed, 26 insertions(+), 23 deletions(-)

diff --git a/gallery_dl/extractor/gelbooru_v02.py b/gallery_dl/extractor/gelbooru_v02.py
index 47df0f27..9bf367be 100644
--- a/gallery_dl/extractor/gelbooru_v02.py
+++ b/gallery_dl/extractor/gelbooru_v02.py
@@ -98,17 +98,18 @@ class GelbooruV02Extractor(booru.BooruExtractor):
             self.root, post["id"])).text
 
     def _tags(self, post, page):
-        html = text.extract(page, '<ul id="tag-', '</ul>')[0]
-        if not html:
-            html = text.extract(page, '<ul class="tag-', '</ul>')[0]
-        if html:
-            tags = collections.defaultdict(list)
-            pattern = re.compile(
-                r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'&]+)", re.S)
-            for tag_type, tag_name in pattern.findall(html):
-                tags[tag_type].append(text.unquote(tag_name))
-            for key, value in tags.items():
-                post["tags_" + key] = " ".join(value)
+        tag_container = (text.extract(page, '<ul id="tag-', '</ul>')[0] or
+                         text.extract(page, '<ul class="tag-', '</ul>')[0])
+        if not tag_container:
+            return
+
+        tags = collections.defaultdict(list)
+        pattern = re.compile(
+            r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'&]+)", re.S)
+        for tag_type, tag_name in pattern.findall(tag_container):
+            tags[tag_type].append(text.unquote(tag_name))
+        for key, value in tags.items():
+            post["tags_" + key] = " ".join(value)
 
     def _notes(self, post, page):
         note_container = text.extract(page, 'id="note-container"', "<img ")[0]
diff --git a/gallery_dl/extractor/moebooru.py b/gallery_dl/extractor/moebooru.py
index e3179c75..459f30f2 100644
--- a/gallery_dl/extractor/moebooru.py
+++ b/gallery_dl/extractor/moebooru.py
@@ -31,22 +31,24 @@ class MoebooruExtractor(BooruExtractor):
             self.root, post["id"])).text
 
     def _tags(self, post, page):
-        html = text.extract(page, '<ul id="tag-', '</ul>')[0]
-        if html:
-            tags = collections.defaultdict(list)
-            pattern = re.compile(r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'+]+)")
-            for tag_type, tag_name in pattern.findall(html):
-                tags[tag_type].append(text.unquote(tag_name))
-            for key, value in tags.items():
-                post["tags_" + key] = " ".join(value)
+        tag_container = text.extract(page, '<ul id="tag-', '</ul>')[0]
+        if not tag_container:
+            return
+
+        tags = collections.defaultdict(list)
+        pattern = re.compile(r"tag-type-([^\"' ]+).*?[?;]tags=([^\"'+]+)")
+        for tag_type, tag_name in pattern.findall(tag_container):
+            tags[tag_type].append(text.unquote(tag_name))
+        for key, value in tags.items():
+            post["tags_" + key] = " ".join(value)
 
     def _notes(self, post, page):
-        notes_container = text.extract(page, 'id="note-container"', "<img ")[0]
-        if not notes_container:
+        note_container = text.extract(page, 'id="note-container"', "<img ")[0]
+        if not note_container:
             return
 
         post["notes"] = notes = []
-        for note in notes_container.split('class="note-box"')[1:]:
+        for note in note_container.split('class="note-box"')[1:]:
             extr = text.extract_from(note)
             notes.append({
                 "width" : int(extr("width:", "p")),
@@ -54,7 +56,7 @@ class MoebooruExtractor(BooruExtractor):
                 "y"     : int(extr("top:", "p")),
                 "x"     : int(extr("left:", "p")),
                 "id"    : int(extr('id="note-body-', '"')),
-                "body"  : text.remove_html(extr(">", "</div>")),
+                "body"  : text.unescape(text.remove_html(extr(">", "</div>"))),
             })
 
     def _pagination(self, url, params):