zaclys
/
searxng
mirror of https://github.com/searxng/searxng.git
1
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

[mod] results.py: code clean up (#2140)

This commit is contained in:
Alexandre Flament 2020-09-08 10:09:11 +02:00 committed by GitHub
parent f0ca1c3483
commit d0f9778c2a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 19 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
searx/results.py
View File

@ -3,6 +3,7 @@ import sys
from collections import defaultdict
from operator import itemgetter
from threading import RLock
from searx import logger
from searx.engines import engines
from searx.url_utils import urlparse, unquote
@ -127,9 +128,11 @@ def result_score(result):
class ResultContainer(object):
"""docstring for ResultContainer"""
__slots__ = '_merged_results', 'infoboxes', 'suggestions', 'answers', 'corrections', '_number_of_results',\
'_ordered', 'paging', 'unresponsive_engines', 'timings', 'redirect_url'
def __init__(self):
super(ResultContainer, self).__init__()
self.results = defaultdict(list)
self._merged_results = []
self.infoboxes = []
self.suggestions = set()
@ -143,51 +146,40 @@ class ResultContainer(object):
self.redirect_url = None
def extend(self, engine_name, results):
standard_result_count = 0
for result in list(results):
result['engine'] = engine_name
if 'suggestion' in result:
self.suggestions.add(result['suggestion'])
results.remove(result)
elif 'answer' in result:
self.answers[result['answer']] = result
results.remove(result)
elif 'correction' in result:
self.corrections.add(result['correction'])
results.remove(result)
elif 'infobox' in result:
self._merge_infobox(result)
results.remove(result)
elif 'number_of_results' in result:
self._number_of_results.append(result['number_of_results'])
results.remove(result)
else:
# standard result (url, title, content)
if 'url' in result and not isinstance(result['url'], basestring):
logger.debug('result: invalid URL: %s', str(result))
elif 'title' in result and not isinstance(result['title'], basestring):
logger.debug('result: invalid title: %s', str(result))
elif 'content' in result and not isinstance(result['content'], basestring):
logger.debug('result: invalid content: %s', str(result))
else:
self._merge_result(result, standard_result_count + 1)
standard_result_count += 1
if engine_name in engines:
with RLock():
engines[engine_name].stats['search_count'] += 1
engines[engine_name].stats['result_count'] += len(results)
engines[engine_name].stats['result_count'] += standard_result_count
if not results:
return
self.results[engine_name].extend(results)
if not self.paging and engine_name in engines and engines[engine_name].paging:
if not self.paging and standard_result_count > 0 and engine_name in engines\
and engines[engine_name].paging:
self.paging = True
for i, result in enumerate(results):
if 'url' in result and not isinstance(result['url'], basestring):
continue
try:
result['url'] = result['url'].decode('utf-8')
except:
pass
if 'title' in result and not isinstance(result['title'], basestring):
continue
if 'content' in result and not isinstance(result['content'], basestring):
continue
position = i + 1
self._merge_result(result, position)
def _merge_infobox(self, infobox):
add_infobox = True
infobox_id = infobox.get('id', None)