Icycoide/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng.git synced 2025-08-03 10:32:21 +02:00
Code Issues Projects Releases Packages Wiki Activity

[fix] bing images

Browse source
This commit is contained in:
marc 2017-05-13 02:22:27 -05:00 • committed by Adam Tauber
parent c0bb89fd46
commit 9ee8e552da
2 changed files with 48 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

21
searx/engines/bing_images.py
View file

@ -31,7 +31,6 @@ time_range_support = True
base_url = 'https://www.bing.com/'
search_string = 'images/search?{query}&count=10&first={offset}'
time_range_string = '&qft=+filterui:age-lt{interval}'
thumb_url = "https://www.bing.com/th?id={ihk}"
time_range_dict = {'day': '1440',
'week': '10080',
'month': '43200',
@ -78,30 +77,32 @@ def response(resp):
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath('//div[@class="dg_u"]/div'):
for result in dom.xpath('//div[@id="mmComponent_images_1"]/ul/li/div/div[@class="imgpt"]'):
link = result.xpath('./a')[0]
# TODO find actual title
title = link.xpath('.//img/@alt')[0]
# parse json-data (it is required to add a space, to make it parsable)
json_data = loads(_quote_keys_regex.sub(r'\1"\2": \3', link.attrib.get('m')))
title = link.attrib.get('t1')
ihk = link.attrib.get('ihk')
url = json_data.get('purl')
img_src = json_data.get('murl')
# url = 'http://' + link.attrib.get('t3')
url = json_data.get('surl')
img_src = json_data.get('imgurl')
thumb_json_data = loads(_quote_keys_regex.sub(r'\1"\2": \3', link.attrib.get('mad')))
thumbnail = thumb_json_data.get('turl')
# append result
results.append({'template': 'images.html',
'url': url,
'title': title,
'content': '',
'thumbnail_src': thumb_url.format(ihk=ihk),
'thumbnail_src': thumbnail,
'img_src': img_src})
# TODO stop parsing if 10 images are found
if len(results) >= 10:
break
# if len(results) >= 10:
# break
# return results
return results