jason/qotnews
1
0
Fork 0
forked from tanner/qotnews
Code Issues Pull Requests Releases Wiki Activity

fix: Extract prose from HTML text field for indexing

Browse Source 
Co-authored-by: aider (gemini/gemini-2.5-pro) <aider@aider.chat>
This commit is contained in:
Tanner Collin
2025-12-12 16:14:36 -07:00
parent 5bcca8e201
commit a10f120fed
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apiserver/scripts/reindex.py
+4
View File
@@ -11,6 +11,7 @@ import sys
import time import time
import json import json
import requests import requests
from bs4 import BeautifulSoup
database.init() database.init()
search.init() search.init()
@@ -45,6 +46,9 @@ if __name__ == '__main__':
story = database.get_story(sid) story = database.get_story(sid)
print('Indexing {}/{} id: {} title: {}'.format(count, num_stories, sid[0], story.title)) print('Indexing {}/{} id: {} title: {}'.format(count, num_stories, sid[0], story.title))
story_obj = json.loads(story.meta_json) 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) stories.append(story_obj)
count += 1 count += 1