Merge pull request #1974 from return42/gigablast

Revise of the gigablast engine

Makefile

@@ -223,6 +223,7 @@ test.pylint: pyenvinstall
 	$(call cmd,pylint,\
 		searx/preferences.py \
 		searx/testing.py \
+		searx/engines/gigablast.py \
 	)
 endif
 
@@ -243,7 +244,7 @@ test.sh:
 
 test.pep8: pyenvinstall
 	@echo "TEST      pep8"
-	$(Q)$(PY_ENV_ACT); pep8 --exclude=searx/static --max-line-length=120 --ignore "E402,W503" searx tests
+	$(Q)$(PY_ENV_ACT); pep8 --exclude='searx/static, searx/engines/gigablast.py' --max-line-length=120 --ignore "E402,W503" searx tests
 
 test.unit: pyenvinstall
 	@echo "TEST      tests/unit"

searx/engines/gigablast.py

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
 """
  Gigablast (Web)
 
@@ -9,121 +10,117 @@
  @stable      yes
  @parse       url, title, content
 """
+# pylint: disable=missing-function-docstring, invalid-name
 
-import random
+import re
 from json import loads
-from time import time
-from lxml.html import fromstring
-from searx.poolrequests import get
+# from searx import logger
 from searx.url_utils import urlencode
-from searx.utils import eval_xpath
+from searx.poolrequests import get
 
 # engine dependent config
 categories = ['general']
-paging = True
-number_of_results = 10
+# gigablast's pagination is totally damaged, don't use it
+paging = False
 language_support = True
 safesearch = True
 
 # search-url
-base_url = 'https://gigablast.com/'
-search_string = 'search?{query}'\
-    '&n={number_of_results}'\
-    '&c=main'\
-    '&s={offset}'\
-    '&format=json'\
-    '&langcountry={lang}'\
-    '&ff={safesearch}'\
-    '&rand={rxikd}'
-# 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'
-
-extra_param = ''  # gigablast requires a random extra parameter
-# which can be extracted from the source code of the search page
+base_url = 'https://gigablast.com'
 
+# ugly hack: gigablast requires a random extra parameter which can be extracted
+# from the source code of the gigablast HTTP client
+extra_param = ''
+extra_param_path='/search?c=main&qlangcountry=en-us&q=south&s=10'
 
 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]
 
+    # example:
+    #
+    # var uxrl='/search?c=main&qlangcountry=en-us&q=south&s=10&rand=1590740241635&n';
+    # uxrl=uxrl+'sab=730863287';
+    #
+    # extra_param --> "rand=1590740241635&nsab=730863287"
 
-def init(engine_settings=None):
-    parse_extra_param(get('http://gigablast.com/search?c=main&qlangcountry=en-us&q=south&s=10').text)
+    global extra_param  # pylint: disable=global-statement
+    re_var= None
+    for line in text.splitlines():
+        if re_var is None and extra_param_path in line:
+            var = line.split("=")[0].split()[1]  # e.g. var --> 'uxrl'
+            re_var = re.compile(var + "\\s*=\\s*" + var + "\\s*\\+\\s*'" + "(.*)" + "'(.*)")
+            extra_param = line.split("'")[1][len(extra_param_path):]
+            continue
+        if re_var is not None and re_var.search(line):
+            extra_param += re_var.search(line).group(1)
+            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
-def request(query, params):
-    print("EXTRAPARAM:", extra_param)
-    offset = (params['pageno'] - 1) * number_of_results
+def request(query, params):  # pylint: disable=unused-argument
 
-    if params['language'] == 'all':
-        language = 'xx'
-    else:
-        language = params['language'].replace('-', '_').lower()
-        if language.split('-')[0] != 'zh':
-            language = language.split('-')[0]
+    # see API http://www.gigablast.com/api.html#/search
+    # Take into account, that the API has some quirks ..
+
+    query_args = dict(
+        c = 'main'
+        , format = 'json'
+        , q = query
+        , dr = 1
+        , showgoodimages = 0
+    )
+
+    if params['language'] and params['language'] != 'all':
+        query_args['qlangcountry'] = params['language']
+        query_args['qlang'] = params['language'].split('-')[0]
 
     if params['safesearch'] >= 1:
-        safesearch = 1
-    else:
-        safesearch = 0
+        query_args['ff'] = 1
 
-    # 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)
-
-    params['url'] = base_url + search_path + '&' + extra_param
+    search_url = '/search?' + urlencode(query_args)
+    params['url'] = base_url + search_url + extra_param
 
     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')
+    response_json = loads(resp.text)
+
+    # logger.debug('gigablast returns %s results', len(response_json['results']))
 
     for result in response_json['results']:
-        # append result
-        results.append({'url': result['url'],
-                        'title': result['title'],
-                        'content': result['sum']})
+        # see "Example JSON Output (&format=json)"
+        # at http://www.gigablast.com/api.html#/search
+
+        # sort out meaningless result
+
+        title = result.get('title')
+        if len(title) < 2:
+            continue
+
+        url = result.get('url')
+        if len(url) < 9:
+            continue
+
+        content = result.get('sum')
+        if len(content) < 5:
+            continue
+
+        # extend fields
+
+        subtitle = result.get('title')
+        if len(subtitle) > 3 and subtitle != title:
+            title += " - " + subtitle
+
+        results.append(dict(
+            url = url
+            , title = title
+            , content = content
+        ))
 
-    # 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

utils/fetch_languages.py

@@ -28,10 +28,10 @@ def fetch_supported_languages():
     names.sort()
 
     for engine_name in names:
-        print("fetching languages of engine %s" % engine_name)
-
         if hasattr(engines[engine_name], 'fetch_supported_languages'):
             engines_languages[engine_name] = engines[engine_name].fetch_supported_languages()
+            print("fetched %s languages from engine %s" % (
+                len(engines_languages[engine_name]), engine_name))
             if type(engines_languages[engine_name]) == list:
                 engines_languages[engine_name] = sorted(engines_languages[engine_name])