iarv/meshing-around
1
0
Fork 1
mirror of https://github.com/SpudGunMan/meshing-around.git synced 2026-03-28 17:32:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update wiki.py

Browse Source
This commit is contained in:
SpudGunMan
2025-10-23 12:45:12 -07:00
parent 5225998c92
commit 74a744c77e
1 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
modules/wiki.py
View File

@@ -6,9 +6,8 @@ import wikipedia # pip install wikipedia
# Kiwix support for local wiki
if use_kiwix_server:
import requests
from bs4 import BeautifulSoup
import bs4 as bs
from urllib.parse import quote
from bs4.element import Comment
# Kiwix helper functions (only loaded if use_kiwix_server is True)
if wikipedia_enabled and use_kiwix_server:
@@ -16,13 +15,13 @@ if wikipedia_enabled and use_kiwix_server:
"""Filter visible text from HTML elements for Kiwix"""
if element.parent.name in ['style', 'script', 'head', 'title', 'meta', '[document]']:
return False
if isinstance(element, Comment):
if isinstance(element, bs.element.Comment):
return False
return True
def text_from_html(body):
"""Extract visible text from HTML content"""
soup = BeautifulSoup(body, 'html.parser')
soup = bs.BeautifulSoup(body, 'html.parser')
texts = soup.find_all(string=True)
visible_texts = filter(tag_visible, texts)
return " ".join(t.strip() for t in visible_texts if t.strip())