mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-03-12 23:42:40 +00:00
Code Issues Projects Releases Wiki Activity

[fix] presearch engine: domain sometimes included in beginning of titles

Browse source
This commit is contained in:
Aadniz 2025-03-07 23:28:28 +01:00 committed by Bnyro
parent 73d50f5748
commit a88b4d7036
1 changed files with 24 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
searx/engines/presearch.py
View file

@ -64,7 +64,7 @@ Implementations
""" """
from urllib.parse import urlencode from urllib.parse import urlencode, urlparse
from searx import locales from searx import locales
from searx.network import get from searx.network import get
from searx.utils import gen_useragent, html_to_text from searx.utils import gen_useragent, html_to_text
@ -155,13 +155,34 @@ def _strip_leading_strings(text):
return text.strip() return text.strip()
def _fix_title(title, url):
"""
Titles from Presearch shows domain + title without spacing, and HTML
This function removes these 2 issues.
Transforming "translate.google.co.in<em>Google</em> Translate" into "Google Translate"
"""
parsed_url = urlparse(url)
domain = parsed_url.netloc
title = html_to_text(title)
# Fixes issue where domain would show up in the title
# translate.google.co.inGoogle Translate -> Google Translate
if (
title.startswith(domain)
and len(title) > len(domain)
and not title.startswith(domain + "/")
and not title.startswith(domain + " ")
):
title = title.removeprefix(domain)
return title
def parse_search_query(json_results): def parse_search_query(json_results):
results = [] results = []
for item in json_results.get('specialSections', {}).get('topStoriesCompact', {}).get('data', []): for item in json_results.get('specialSections', {}).get('topStoriesCompact', {}).get('data', []):
result = { result = {
'url': item['link'], 'url': item['link'],
'title': html_to_text(item['title']), 'title': _fix_title(item['title'], item['link']),
'thumbnail': item['image'], 'thumbnail': item['image'],
'content': '', 'content': '',
'metadata': item.get('source'), 'metadata': item.get('source'),
@ -171,7 +192,7 @@ def parse_search_query(json_results):
for item in json_results.get('standardResults', []): for item in json_results.get('standardResults', []):
result = { result = {
'url': item['link'], 'url': item['link'],
'title': html_to_text(item['title']), 'title': _fix_title(item['title'], item['link']),
'content': html_to_text(item['description']), 'content': html_to_text(item['description']),
} }
results.append(result) results.append(result)