zaclys/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng synced 2024-01-01 19:24:07 +01:00
Code Issues Projects Releases Packages Wiki Activity

update comment

Browse source
This commit is contained in:
Dalf 2014-09-22 23:39:21 +02:00
parent 6b058962e1
commit e39d9fe542
1 changed files with 6 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
searx/search.py
View file

@ -106,8 +106,13 @@ def score_results(results):
res['host'] = res['host'].replace('www.', '', 1) res['host'] = res['host'].replace('www.', '', 1)
res['engines'] = [res['engine']] res['engines'] = [res['engine']]
weight = 1.0 weight = 1.0
# strip multiple spaces and cariage returns from content
if 'content' in res:
res['content'] = re.sub(' +', ' ', res['content'].strip().replace('\n', ''))
# get weight of this engine if possible # get weight of this engine if possible
if hasattr(engines[res['engine']], 'weight'): if hasattr(engines[res['engine']], 'weight'):
weight = float(engines[res['engine']].weight) weight = float(engines[res['engine']].weight)
@ -115,12 +120,8 @@ def score_results(results):
# calculate score for that engine # calculate score for that engine
score = int((flat_len - i) / engines_len) * weight + 1 score = int((flat_len - i) / engines_len) * weight + 1
duplicated = False
# check for duplicates # check for duplicates
if 'content' in res: duplicated = False
res['content'] = re.sub(' +', ' ', res['content'].strip().replace('\n', ''))
for new_res in results: for new_res in results:
# remove / from the end of the url if required # remove / from the end of the url if required
p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path # noqa p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path # noqa