Fix google image search

- Because there is not full image url in the dom, we replace "image_url" with the same url as the "url" (url of source).
  See example HTML https://gist.github.com/Nachtalb/2dea8a4d2c723c49226ad9645838121f
- Remove unused import
- Fix google image search title
- Keep google image safe value up to date
This commit is contained in:
Nick Espig 2019-04-12 23:12:56 +02:00
parent 34d85c8c3c
commit 1c6ab79b9f
No known key found for this signature in database
GPG key ID: E48DF13C07055D92

View file

@ -11,7 +11,6 @@
""" """
from datetime import date, timedelta from datetime import date, timedelta
from json import loads
from lxml import html from lxml import html
from searx.url_utils import urlencode, urlparse, parse_qs from searx.url_utils import urlencode, urlparse, parse_qs
@ -39,7 +38,6 @@ time_range_dict = {'day': 'd',
# do search-request # do search-request
def request(query, params): def request(query, params):
search_options = { search_options = {
'ijn': params['pageno'] - 1,
'start': (params['pageno'] - 1) * number_of_results 'start': (params['pageno'] - 1) * number_of_results
} }
@ -53,7 +51,7 @@ def request(query, params):
search_options['tbs'] = time_range_custom_attr.format(start=start, end=end) search_options['tbs'] = time_range_custom_attr.format(start=start, end=end)
if safesearch and params['safesearch']: if safesearch and params['safesearch']:
search_options['safe'] = 'on' search_options['safe'] = 'active'
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}),
search_options=urlencode(search_options)) search_options=urlencode(search_options))
@ -63,24 +61,30 @@ def request(query, params):
# get response from search-request # get response from search-request
def response(resp): def response(resp):
results = []
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
# parse results results = []
for img in dom.xpath('//a'): for element in dom.xpath('//div[@id="search"] //td'):
r = { link = element.xpath('./a')[0]
'title': u' '.join(img.xpath('.//div[class="rg_ilmbg"]//text()')),
google_url = urlparse(link.xpath('.//@href')[0])
query = parse_qs(google_url.query)
source_url = next(iter(query.get('q', [])), None)
title_parts = element.xpath('./cite//following-sibling::*/text()')
title_parts.extend(element.xpath('./cite//following-sibling::text()')[:-1])
result = {
'title': ''.join(title_parts),
'content': '', 'content': '',
'template': 'images.html', 'template': 'images.html',
'url': source_url,
'img_src': source_url,
'thumbnail_src': next(iter(link.xpath('.//img //@src')), None)
} }
url = urlparse(img.xpath('.//@href')[0])
query = parse_qs(url.query)
r['url'] = query['imgrefurl'][0]
r['img_src'] = query['imgurl'][0]
r['thumbnail_src'] = r['img_src']
# append result
results.append(r)
# return results if not source_url or not result['thumbnail_src']:
continue
results.append(result)
return results return results