mirror of
https://github.com/searxng/searxng.git
synced 2024-07-04 04:45:50 +00:00
b973081134
It seems like Google image is doing a double urlencode on the url of the images. So we need to unquote once before sending to the browser the urls. It solves the 404 we could see with some image with specials chars in url. Exemple https://searx.laquadrature.net/?q=etes&pageno=1&category_images (there are two of those in the list)
60 lines
1.5 KiB
Python
60 lines
1.5 KiB
Python
## Google (Images)
|
|
#
|
|
# @website https://www.google.com
|
|
# @provide-api yes (https://developers.google.com/web-search/docs/),
|
|
# deprecated!
|
|
#
|
|
# @using-api yes
|
|
# @results JSON
|
|
# @stable yes (but deprecated)
|
|
# @parse url, title, img_src
|
|
|
|
from urllib import urlencode,unquote
|
|
from json import loads
|
|
|
|
# engine dependent config
|
|
categories = ['images']
|
|
paging = True
|
|
|
|
# search-url
|
|
url = 'https://ajax.googleapis.com/'
|
|
search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe=off&filter=off&{query}' # noqa
|
|
|
|
|
|
# do search-request
|
|
def request(query, params):
|
|
offset = (params['pageno'] - 1) * 8
|
|
|
|
params['url'] = search_url.format(query=urlencode({'q': query}),
|
|
offset=offset)
|
|
|
|
return params
|
|
|
|
|
|
# get response from search-request
|
|
def response(resp):
|
|
results = []
|
|
|
|
search_res = loads(resp.text)
|
|
|
|
# return empty array if there are no results
|
|
if not search_res.get('responseData', {}).get('results'):
|
|
return []
|
|
|
|
# parse results
|
|
for result in search_res['responseData']['results']:
|
|
href = result['originalContextUrl']
|
|
title = result['title']
|
|
if not result['url']:
|
|
continue
|
|
|
|
# append result
|
|
results.append({'url': href,
|
|
'title': title,
|
|
'content': '',
|
|
'img_src': unquote(result['url']),
|
|
'template': 'images.html'})
|
|
|
|
# return results
|
|
return results
|