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

Merge pull request #613 from return42/pylint-bing-images 

[pylint] Bing (Images) engine
This commit is contained in:
Alexandre Flament 2022-01-02 22:00:55 +01:00 committed by GitHub
parent c2e4b95e8d dc4f1f705d
commit d83aa2b0d2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 27 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
searx/engines/bing_images.py
View File

@ -1,11 +1,13 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Bing (Images)
# lint: pylint
"""Bing (Images)
"""
from urllib.parse import urlencode
from lxml import html
from json import loads
from urllib.parse import urlencode
from lxml import html
from searx.utils import match_language
from searx.engines.bing import language_aliases
@ -77,31 +79,28 @@ def response(resp):
# parse results
for result in dom.xpath('//div[@class="imgpt"]'):
try:
img_format = result.xpath('./div[contains(@class, "img_info")]/span/text()')[0]
# Microsoft seems to experiment with this code so don't make the path too specific,
# just catch the text section for the first anchor in img_info assuming this to be
# the originating site.
source = result.xpath('./div[contains(@class, "img_info")]//a/text()')[0]
img_format = result.xpath('./div[contains(@class, "img_info")]/span/text()')[0]
# Microsoft seems to experiment with this code so don't make the path too specific,
# just catch the text section for the first anchor in img_info assuming this to be
# the originating site.
source = result.xpath('./div[contains(@class, "img_info")]//a/text()')[0]
m = loads(result.xpath('./a/@m')[0])
m = loads(result.xpath('./a/@m')[0])
# strip 'Unicode private use area' highlighting, they render to Tux
# the Linux penguin and a standing diamond on my machine...
title = m.get('t', '').replace('\ue000', '').replace('\ue001', '')
results.append(
{
'template': 'images.html',
'url': m['purl'],
'thumbnail_src': m['turl'],
'img_src': m['murl'],
'content': '',
'title': title,
'source': source,
'img_format': img_format,
}
)
except:
continue
# strip 'Unicode private use area' highlighting, they render to Tux
# the Linux penguin and a standing diamond on my machine...
title = m.get('t', '').replace('\ue000', '').replace('\ue001', '')
results.append(
{
'template': 'images.html',
'url': m['purl'],
'thumbnail_src': m['turl'],
'img_src': m['murl'],
'content': '',
'title': title,
'source': source,
'img_format': img_format,
}
)
return results