Ponysearch/searx/engines/google_images.py

72 lines
1.8 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 urllib import urlencode
from urlparse import parse_qs
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
2013-10-19 22:19:14 +02:00
search_url = 'https://www.google.com/search'\
'?{query}'\
'&tbm=isch'\
'&ijn=1'\
'&start={offset}'
2014-01-20 02:31:20 +01:00
2013-10-19 22:19:14 +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):
offset = (params['pageno'] - 1) * 100
2015-02-08 22:15:25 +01:00
2014-01-30 01:21:33 +01:00
params['url'] = search_url.format(query=urlencode({'q': query}),
2015-02-08 22:15:25 +01:00
offset=offset,
safesearch=safesearch)
2014-09-01 15:10:05 +02:00
if safesearch and params['safesearch']:
params['url'] += '&' + urlencode({'safe': 'active'})
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
dom = html.fromstring(resp.text)
2014-09-01 15:10:05 +02:00
# parse results
for result in dom.xpath('//div[@data-ved]'):
data_url = result.xpath('./a/@href')[0]
data_query = {k: v[0] for k, v in parse_qs(data_url.split('?', 1)[1]).iteritems()}
metadata = loads(result.xpath('./div[@class="rg_meta"]/text()')[0])
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
results.append({'url': data_query['imgrefurl'],
'title': metadata['pt'],
'content': metadata['s'],
'thumbnail_src': metadata['tu'],
'img_src': data_query['imgurl'],
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