[fix] gigablast engine

fetch extra params after 3000 seconds
This commit is contained in:
Alexandre Flament 2021-12-06 22:55:15 +01:00
parent e4a2d354aa
commit 1a6207574e
2 changed files with 22 additions and 15 deletions

View file

@ -6,6 +6,7 @@
# pylint: disable=invalid-name # pylint: disable=invalid-name
import re import re
from time import time
from json import loads from json import loads
from urllib.parse import urlencode from urllib.parse import urlencode
from searx.network import get from searx.network import get
@ -28,13 +29,18 @@ safesearch = True
# search-url # search-url
base_url = 'https://gigablast.com' base_url = 'https://gigablast.com'
search_path = '/search?'
# ugly hack: gigablast requires a random extra parameter which can be extracted # ugly hack: gigablast requires a random extra parameter which can be extracted
# from the source code of the gigablast HTTP client # from the source code of the gigablast HTTP client
extra_param = '' extra_param = ''
extra_param_path='/search?c=main&qlangcountry=en-us&q=south&s=10' # timestamp of the last fetch of extra_param
extra_param_ts = 0
# after how many seconds extra_param expire
extra_param_expiration_delay = 3000
def parse_extra_param(text):
def fetch_extra_param(query_args, headers):
# example: # example:
# #
@ -43,7 +49,12 @@ def parse_extra_param(text):
# #
# extra_param --> "rand=1590740241635&nsab=730863287" # extra_param --> "rand=1590740241635&nsab=730863287"
global extra_param # pylint: disable=global-statement global extra_param, extra_param_ts # pylint: disable=global-statement
extra_param_ts = time()
extra_param_path = search_path + urlencode(query_args)
text = get(base_url + extra_param_path, headers=headers).text
re_var= None re_var= None
for line in text.splitlines(): for line in text.splitlines():
if re_var is None and extra_param_path in line: if re_var is None and extra_param_path in line:
@ -54,21 +65,12 @@ def parse_extra_param(text):
if re_var is not None and re_var.search(line): if re_var is not None and re_var.search(line):
extra_param += re_var.search(line).group(1) extra_param += re_var.search(line).group(1)
break break
# logger.debug('gigablast extra_param="%s"', extra_param)
def init(engine_settings=None): # pylint: disable=unused-argument
parse_extra_param(get(base_url + extra_param_path).text)
# do search-request # do search-request
def request(query, params): # pylint: disable=unused-argument def request(query, params): # pylint: disable=unused-argument
# see API http://www.gigablast.com/api.html#/search
# Take into account, that the API has some quirks ..
query_args = dict( query_args = dict(
c = 'main' c = 'main'
, format = 'json'
, q = query , q = query
, dr = 1 , dr = 1
, showgoodimages = 0 , showgoodimages = 0
@ -81,8 +83,13 @@ def request(query, params): # pylint: disable=unused-argument
if params['safesearch'] >= 1: if params['safesearch'] >= 1:
query_args['ff'] = 1 query_args['ff'] = 1
search_url = '/search?' + urlencode(query_args) # see API http://www.gigablast.com/api.html#/search
params['url'] = base_url + search_url + extra_param # Take into account, that the API has some quirks ..
if time() > (extra_param_ts + extra_param_expiration_delay):
fetch_extra_param(query_args, params['headers'])
query_args['format'] = 'json'
params['url'] = base_url + search_path + urlencode(query_args) + extra_param
return params return params

View file

@ -558,7 +558,7 @@ engines:
- name: gigablast - name: gigablast
engine: gigablast engine: gigablast
shortcut: gb shortcut: gb
timeout: 3.0 timeout: 4.0
disabled: true disabled: true
additional_tests: additional_tests:
rosebud: *test_rosebud rosebud: *test_rosebud