1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-09 14:40:11 +01:00
searxng/searx/engines/google_images.py

98 lines
2.8 KiB
Python
Raw Normal View History

"""
Google (Images)
@website https://www.google.com
@provide-api yes (https://developers.google.com/custom-search/)
2015-12-09 01:23:05 +01:00
@using-api no
@results HTML chunks with JSON inside
@stable no
@parse url, title, img_src
"""
2013-10-19 22:19:14 +02:00
from datetime import date, timedelta
from json import loads
from lxml import html
from searx.url_utils import urlencode
2014-09-01 15:10:05 +02:00
# engine dependent config
2013-10-19 22:19:31 +02:00
categories = ['images']
2014-09-01 15:10:05 +02:00
paging = True
2015-02-08 22:15:25 +01:00
safesearch = True
time_range_support = True
number_of_results = 100
2013-10-19 22:19:14 +02:00
search_url = 'https://www.google.com/search'\
'?{query}'\
'&tbm=isch'\
'&yv=2'\
'&{search_options}'
time_range_attr = "qdr:{range}"
time_range_custom_attr = "cdr:1,cd_min:{start},cd_max{end}"
time_range_dict = {'day': 'd',
'week': 'w',
'month': 'm'}
2013-10-19 22:19:14 +02:00
2016-07-19 10:14:11 +02:00
2014-09-01 15:10:05 +02:00
# do search-request
2013-10-19 22:19:14 +02:00
def request(query, params):
search_options = {
'ijn': params['pageno'] - 1,
'start': (params['pageno'] - 1) * number_of_results
}
2016-07-26 00:22:05 +02:00
if params['time_range'] in time_range_dict:
search_options['tbs'] = time_range_attr.format(range=time_range_dict[params['time_range']])
elif params['time_range'] == 'year':
now = date.today()
then = now - timedelta(days=365)
start = then.strftime('%m/%d/%Y')
end = now.strftime('%m/%d/%Y')
search_options['tbs'] = time_range_custom_attr.format(start=start, end=end)
2014-09-01 15:10:05 +02:00
if safesearch and params['safesearch']:
search_options['safe'] = 'on'
params['url'] = search_url.format(query=urlencode({'q': query}),
search_options=urlencode(search_options))
2013-10-19 22:19:14 +02:00
return params
2014-01-20 02:31:20 +01:00
2014-09-01 15:10:05 +02:00
# get response from search-request
2013-10-19 22:19:14 +02:00
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath('//div[contains(@class, "rg_meta")]/text()'):
try:
metadata = loads(result)
2019-08-27 06:54:01 +02:00
img_format = metadata.get('ity', '')
img_width = metadata.get('ow', '')
img_height = metadata.get('oh', '')
if img_width and img_height:
img_format += " {0}x{1}".format(img_width, img_height)
source = metadata.get('st', '')
source_url = metadata.get('isu', '')
if source_url:
source += " ({0})".format(source_url)
results.append({'url': metadata['ru'],
'title': metadata['pt'],
2019-08-27 06:54:01 +02:00
'content': metadata.get('s', ''),
'source': source,
'img_format': img_format,
'thumbnail_src': metadata['tu'],
'img_src': metadata['ou'],
'template': 'images.html'})
except:
continue
2013-10-19 22:19:14 +02:00
return results