searxng/searx/engines/google_news.py
Noémi Ványi c59c76e6ee add year to time range to engines which support "Last year"
Engines:
 * Bing images
 * Flickr (noapi)
 * Google
 * Google Images
 * Google News
2016-12-11 16:58:31 +01:00

81 lines
2.0 KiB
Python

"""
Google (News)
@website https://news.google.com
@provide-api no
@using-api no
@results HTML
@stable no
@parse url, title, content, publishedDate
"""
from lxml import html
from urllib import urlencode
# search-url
categories = ['news']
paging = True
language_support = True
safesearch = True
time_range_support = True
number_of_results = 10
search_url = 'https://www.google.com/search'\
'?{query}'\
'&tbm=nws'\
'&gws_rd=cr'\
'&{search_options}'
time_range_attr = "qdr:{range}"
time_range_dict = {'day': 'd',
'week': 'w',
'month': 'm',
'year': 'y'}
# do search-request
def request(query, params):
search_options = {
'start': (params['pageno'] - 1) * number_of_results
}
if params['time_range'] in time_range_dict:
search_options['tbs'] = time_range_attr.format(range=time_range_dict[params['time_range']])
if safesearch and params['safesearch']:
search_options['safe'] = 'on'
params['url'] = search_url.format(query=urlencode({'q': query}),
search_options=urlencode(search_options))
if params['language'] != 'all':
language_array = params['language'].lower().split('_')
params['url'] += '&lr=lang_' + language_array[0]
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath('//div[@class="g"]|//div[@class="g _cy"]'):
r = {
'url': result.xpath('.//div[@class="_cnc"]//a/@href')[0],
'title': ''.join(result.xpath('.//div[@class="_cnc"]//h3//text()')),
'content': ''.join(result.xpath('.//div[@class="st"]//text()')),
}
img = result.xpath('.//img/@src')[0]
if img and not img.startswith('data'):
r['img_src'] = img
results.append(r)
# return results
return results