Ponysearch/searx/engines/google_images.py

96 lines
2.5 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 urllib import urlencode
2013-10-19 23:12:18 +02:00
from json import loads
from lxml import html
2013-10-19 22:19:14 +02:00
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}'\
'&asearch=ichunk'\
'&async=_id:rg_s,_pms:s'\
'&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 = []
2014-09-01 15:10:05 +02:00
g_result = loads(resp.text)
dom = html.fromstring(g_result[1][1])
2014-09-01 15:10:05 +02:00
# parse results
for result in dom.xpath('//div[@data-ved]'):
try:
metadata = loads(''.join(result.xpath('./div[@class="rg_meta"]/text()')))
except:
continue
thumbnail_src = metadata['tu']
2014-09-01 15:10:05 +02:00
# http to https
thumbnail_src = thumbnail_src.replace("http://", "https://")
2014-09-01 15:10:05 +02:00
# append result
2016-04-07 08:04:36 +02:00
results.append({'url': metadata['ru'],
'title': metadata['pt'],
'content': metadata['s'],
2016-04-07 08:04:36 +02:00
'thumbnail_src': thumbnail_src,
'img_src': metadata['ou'],
2014-01-20 02:31:20 +01:00
'template': 'images.html'})
2014-09-01 15:10:05 +02:00
# return results
2013-10-19 22:19:14 +02:00
return results