searxng/searx/engines/gigablast.py

130 lines
3.5 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
2017-08-31 14:11:04 +00:00
import random
from json import loads
2015-10-16 10:05:50 +00:00
from time import time
from lxml.html import fromstring
from searx.poolrequests import get
2016-11-30 17:43:03 +00:00
from searx.url_utils import urlencode
from searx.utils import eval_xpath
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}'\
'&c=main'\
'&s={offset}'\
'&format=json'\
'&langcountry={lang}'\
2016-06-11 22:06:31 +00:00
'&ff={safesearch}'\
'&rand={rxikd}'
2015-02-08 13:12:14 +00:00
# specific xpath variables
results_xpath = '//response//result'
url_xpath = './/url'
title_xpath = './/title'
content_xpath = './/sum'
supported_languages_url = 'https://gigablast.com/search?&rxikd=1'
2016-08-07 03:19:21 +00:00
2019-12-21 20:13:43 +00:00
extra_param = '' # gigablast requires a random extra parameter
# which can be extracted from the source code of the search page
def parse_extra_param(text):
global extra_param
param_lines = [x for x in text.splitlines() if x.startswith('var url=') or x.startswith('url=url+')]
extra_param = ''
for l in param_lines:
extra_param += l.split("'")[1]
extra_param = extra_param.split('&')[-1]
def init(engine_settings=None):
parse_extra_param(get('http://gigablast.com/search?c=main&qlangcountry=en-us&q=south&s=10').text)
2015-02-08 13:12:14 +00:00
# do search-request
def request(query, params):
print("EXTRAPARAM:", extra_param)
2015-02-08 13:12:14 +00:00
offset = (params['pageno'] - 1) * number_of_results
if params['language'] == 'all':
language = 'xx'
else:
language = params['language'].replace('-', '_').lower()
if language.split('-')[0] != 'zh':
language = language.split('-')[0]
if params['safesearch'] >= 1:
safesearch = 1
else:
safesearch = 0
2017-08-31 14:11:04 +00:00
# rxieu is some kind of hash from the search query, but accepts random atm
search_path = search_string.format(query=urlencode({'q': query}),
offset=offset,
number_of_results=number_of_results,
lang=language,
rxikd=int(time() * 1000),
safesearch=safesearch)
2015-02-08 13:12:14 +00:00
params['url'] = base_url + search_path + '&' + extra_param
2015-02-08 13:12:14 +00:00
return params
# get response from search-request
def response(resp):
results = []
# parse results
try:
response_json = loads(resp.text)
except:
parse_extra_param(resp.text)
raise Exception('extra param expired, please reload')
2015-02-08 13:12:14 +00:00
for result in response_json['results']:
2015-02-08 13:12:14 +00:00
# append result
results.append({'url': result['url'],
'title': result['title'],
'content': result['sum']})
2015-02-08 13:12:14 +00:00
# return results
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
supported_languages = []
dom = fromstring(resp.text)
links = eval_xpath(dom, '//span[@id="menu2"]/a')
for link in links:
href = eval_xpath(link, './@href')[0].split('lang%3A')
if len(href) == 2:
code = href[1].split('_')
if len(code) == 2:
code = code[0] + '-' + code[1].upper()
else:
code = code[0]
supported_languages.append(code)
return supported_languages