fix: Extract prose from HTML text field for indexing

Co-authored-by: aider (gemini/gemini-2.5-pro) <aider@aider.chat>

apiserver/scripts/reindex.py

@@ -11,6 +11,7 @@ import sys
 import time
 import json
 import requests
+from bs4 import BeautifulSoup
 
 database.init()
 search.init()
@@ -45,6 +46,9 @@ if __name__ == '__main__':
             story = database.get_story(sid)
             print('Indexing {}/{} id: {} title: {}'.format(count, num_stories, sid[0], story.title))
             story_obj = json.loads(story.meta_json)
+            if 'text' in story_obj and story_obj['text']:
+                soup = BeautifulSoup(story_obj['text'], 'html.parser')
+                story_obj['text'] = soup.get_text()
             stories.append(story_obj)
             count += 1