searxng/searx/engines/gigablast.py

91 lines
2.1 KiB
Python
Raw Normal View History

"""
Gigablast (Web)
2015-12-22 19:25:57 +00:00
@website https://gigablast.com
@provide-api yes (https://gigablast.com/api.html)
@using-api yes
@results XML
@stable yes
@parse url, title, content
"""
2015-02-08 13:12:14 +00:00
from urllib import urlencode
from cgi import escape
from lxml import etree
2015-10-16 10:05:50 +00:00
from random import randint
from time import time
2015-02-08 13:12:14 +00:00
# engine dependent config
categories = ['general']
paging = True
number_of_results = 10
language_support = True
safesearch = True
2015-02-08 13:12:14 +00:00
# search-url
2015-12-22 19:25:57 +00:00
base_url = 'https://gigablast.com/'
search_string = 'search?{query}'\
'&n={number_of_results}'\
'&s={offset}'\
'&format=xml'\
'&qh=0'\
'&rxiyd={rxiyd}'\
'&rand={rand}'\
'&qlang={lang}'\
'&ff={safesearch}'
2015-02-08 13:12:14 +00:00
# specific xpath variables
results_xpath = '//response//result'
url_xpath = './/url'
title_xpath = './/title'
content_xpath = './/sum'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * number_of_results
if params['language'] == 'all':
language = 'xx'
else:
language = params['language'][0:2]
if params['safesearch'] >= 1:
safesearch = 1
else:
safesearch = 0
search_path = search_string.format(query=urlencode({'q': query}),
offset=offset,
number_of_results=number_of_results,
rxiyd=randint(10000, 10000000),
rand=int(time()),
lang=language,
safesearch=safesearch)
2015-02-08 13:12:14 +00:00
params['url'] = base_url + search_path
return params
# get response from search-request
def response(resp):
results = []
dom = etree.fromstring(resp.content)
# parse results
for result in dom.xpath(results_xpath):
url = result.xpath(url_xpath)[0].text
title = result.xpath(title_xpath)[0].text
content = escape(result.xpath(content_xpath)[0].text)
# append result
results.append({'url': url,
'title': title,
'content': content})
# return results
return results