Icycoide/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng.git synced 2025-07-24 13:49:26 +02:00
Code Issues Projects Releases Packages Wiki Activity

[enh] use longest title and test get_ordered_results()

Browse source
This commit is contained in:
Allen 2024-10-17 04:57:21 +00:00 • committed by Markus Heiser
parent 94aafc83a6
commit 6948689d2a
2 changed files with 55 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

11
searx/results.py
View file

@ -12,7 +12,6 @@ from searx import logger
from searx.engines import engines
from searx.metrics import histogram_observe, counter_add, count_error
CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile(r'[,;:!?\./\\\\ ()-_]', re.M | re.U)
WHITESPACE_REGEX = re.compile('( |\t|\n)+', re.M | re.U)
@ -133,7 +132,7 @@ def result_score(result, priority):
weight = 1.0
for result_engine in result['engines']:
if hasattr(engines[result_engine], 'weight'):
if hasattr(engines.get(result_engine), 'weight'):
weight *= float(engines[result_engine].weight)
weight *= len(result['positions'])
@ -332,10 +331,14 @@ class ResultContainer:
return None
def __merge_duplicated_http_result(self, duplicated, result, position):
# using content with more text
# use content with more text
if result_content_len(result.get('content', '')) > result_content_len(duplicated.get('content', '')):
duplicated['content'] = result['content']
# use title with more text
if result_content_len(result.get('title', '')) > len(duplicated.get('title', '')):
duplicated['title'] = result['title']
# merge all result's parameters not found in duplicate
for key in result.keys():
if not duplicated.get(key):
@ -347,7 +350,7 @@ class ResultContainer:
# add engine to list of result-engines
duplicated['engines'].add(result['engine'])
# using https if possible
# use https if possible
if duplicated['parsed_url'].scheme != 'https' and result['parsed_url'].scheme == 'https':
duplicated['url'] = result['parsed_url'].geturl()
duplicated['parsed_url'] = result['parsed_url']