update engines_languages.json and languages.py

Also, fix fetch_languages.py so it can run on python3.

searx/engines/duckduckgo.py

@@ -134,4 +134,4 @@ def _fetch_supported_languages(resp):
     regions_json = loads(response_page)
     supported_languages = map((lambda x: x[3:] + '-' + x[:2].upper()), regions_json.keys())
 
-    return supported_languages
+    return list(supported_languages)

searx/engines/swisscows.py

@@ -118,7 +118,7 @@ def _fetch_supported_languages(resp):
     dom = fromstring(resp.text)
     options = dom.xpath('//div[@id="regions-popup"]//ul/li/a')
     for option in options:
-        code = option.xpath('./@data-val')[0]
+        code = option.xpath('./@data-search-language')[0]
         if code.startswith('nb-'):
             code = code.replace('nb', 'no', 1)
         supported_languages.append(code)

searx/languages.py

@@ -5,6 +5,11 @@
 language_codes = (
     (u"ar-SA", u"العربية", u"", u"Arabic"),
     (u"bg-BG", u"Български", u"", u"Bulgarian"),
+    (u"ca", u"Català", u"", u"Catalan"),
+    (u"ca-AD", u"Català", u"Andorra", u"Catalan"),
+    (u"ca-CT", u"Català", u"", u"Catalan"),
+    (u"ca-ES", u"Català", u"Espanya", u"Catalan"),
+    (u"ca-FR", u"Català", u"França", u"Catalan"),
     (u"cs-CZ", u"Čeština", u"", u"Czech"),
     (u"da-DK", u"Dansk", u"", u"Danish"),
     (u"de", u"Deutsch", u"", u"German"),
@@ -15,9 +20,7 @@ language_codes = (
     (u"en", u"English", u"", u"English"),
     (u"en-AU", u"English", u"Australia", u"English"),
     (u"en-CA", u"English", u"Canada", u"English"),
-    (u"en-CY", u"English", u"Cyprus", u"English"),
     (u"en-GB", u"English", u"United Kingdom", u"English"),
-    (u"en-GD", u"English", u"Grenada", u"English"),
     (u"en-ID", u"English", u"Indonesia", u"English"),
     (u"en-IE", u"English", u"Ireland", u"English"),
     (u"en-IN", u"English", u"India", u"English"),
@@ -28,6 +31,7 @@ language_codes = (
     (u"en-US", u"English", u"United States", u"English"),
     (u"en-ZA", u"English", u"South Africa", u"English"),
     (u"es", u"Español", u"", u"Spanish"),
+    (u"es-AD", u"Español", u"Andorra", u"Spanish"),
     (u"es-AR", u"Español", u"Argentina", u"Spanish"),
     (u"es-CL", u"Español", u"Chile", u"Spanish"),
     (u"es-CO", u"Español", u"Colombia", u"Spanish"),
@@ -38,38 +42,32 @@ language_codes = (
     (u"et-EE", u"Eesti", u"", u"Estonian"),
     (u"fi-FI", u"Suomi", u"", u"Finnish"),
     (u"fr", u"Français", u"", u"French"),
+    (u"fr-AD", u"Français", u"Andorre", u"French"),
     (u"fr-BE", u"Français", u"Belgique", u"French"),
     (u"fr-CA", u"Français", u"Canada", u"French"),
     (u"fr-CH", u"Français", u"Suisse", u"French"),
     (u"fr-FR", u"Français", u"France", u"French"),
     (u"he-IL", u"עברית", u"", u"Hebrew"),
-    (u"hr-HR", u"Hrvatski", u"", u"Croatian"),
     (u"hu-HU", u"Magyar", u"", u"Hungarian"),
-    (u"id-ID", u"Bahasa Indonesia", u"", u"Indonesian"),
     (u"it", u"Italiano", u"", u"Italian"),
     (u"it-CH", u"Italiano", u"Svizzera", u"Italian"),
     (u"it-IT", u"Italiano", u"Italia", u"Italian"),
     (u"ja-JP", u"日本語", u"", u"Japanese"),
     (u"ko-KR", u"한국어", u"", u"Korean"),
-    (u"lt-LT", u"Lietuvių", u"", u"Lithuanian"),
-    (u"lv-LV", u"Latviešu", u"", u"Latvian"),
-    (u"ms-MY", u"Bahasa Melayu", u"", u"Malay"),
     (u"nl", u"Nederlands", u"", u"Dutch"),
     (u"nl-BE", u"Nederlands", u"België", u"Dutch"),
     (u"nl-NL", u"Nederlands", u"Nederland", u"Dutch"),
     (u"no-NO", u"Norsk", u"", u"Norwegian"),
     (u"pl-PL", u"Polski", u"", u"Polish"),
     (u"pt", u"Português", u"", u"Portuguese"),
+    (u"pt-AD", u"Português", u"Andorra", u"Portuguese"),
     (u"pt-BR", u"Português", u"Brasil", u"Portuguese"),
     (u"pt-PT", u"Português", u"Portugal", u"Portuguese"),
     (u"ro-RO", u"Română", u"", u"Romanian"),
     (u"ru-RU", u"Русский", u"", u"Russian"),
-    (u"sk-SK", u"Slovenčina", u"", u"Slovak"),
-    (u"sl", u"Slovenščina", u"", u"Slovenian"),
     (u"sv-SE", u"Svenska", u"", u"Swedish"),
     (u"th-TH", u"ไทย", u"", u"Thai"),
     (u"tr-TR", u"Türkçe", u"", u"Turkish"),
-    (u"vi-VN", u"Tiếng Việt", u"", u"Vietnamese"),
     (u"zh", u"中文", u"", u"Chinese"),
     (u"zh-CN", u"中文", u"中国", u"Chinese"),
     (u"zh-HK", u"中文", u"香港", u"Chinese"),

tests/unit/engines/test_swisscows.py

@@ -139,9 +139,9 @@ class TestSwisscowsEngine(SearxTestCase):
             <div id="regions-popup">
                 <div>
                     <ul>
-                        <li><a data-val="browser"></a></li>
+                        <li><a data-search-language="browser"></a></li>
-                        <li><a data-val="de-CH"></a></li>
+                        <li><a data-search-language="de-CH"></a></li>
-                        <li><a data-val="fr-CH"></a></li>
+                        <li><a data-search-language="fr-CH"></a></li>
                     </ul>
                 </div>
             </div>

utils/fetch_languages.py

@@ -8,13 +8,13 @@
 # are written in current directory to avoid overwriting in case something goes wrong.
 
 from requests import get
-from urllib import urlencode
 from lxml.html import fromstring
-from json import loads, dumps
+from json import loads, dump
 import io
 from sys import path
 path.append('../searx')  # noqa
 from searx import settings
+from searx.url_utils import urlencode
 from searx.engines import initialize_engines, engines
 
 # Geonames API for country names.
@@ -70,7 +70,7 @@ def get_country_name(locale):
     json = loads(response.text)
     content = json.get('geonames', None)
     if content is None or len(content) != 1:
-        print "No country name found for " + locale[0] + "-" + locale[1]
+        print("No country name found for " + locale[0] + "-" + locale[1])
         return ''
 
     return content[0].get('countryName', '')
@@ -84,11 +84,11 @@ def fetch_supported_languages():
             try:
                 engines_languages[engine_name] = engines[engine_name].fetch_supported_languages()
             except Exception as e:
-                print e
+                print(e)
 
     # write json file
     with io.open(engines_languages_file, "w", encoding="utf-8") as f:
-        f.write(unicode(dumps(engines_languages, ensure_ascii=False, encoding="utf-8")))
+        dump(engines_languages, f, ensure_ascii=False)
 
 
 # Join all language lists.
@@ -97,7 +97,7 @@ def join_language_lists():
     global languages
     # include wikipedia first for more accurate language names
     languages = {code: lang for code, lang
-                 in engines_languages['wikipedia'].iteritems()
+                 in engines_languages['wikipedia'].items()
                  if valid_code(code)}
 
     for engine_name in engines_languages:
@@ -121,7 +121,7 @@ def join_language_lists():
     # filter list to include only languages supported by most engines
     min_supported_engines = int(0.70 * len(engines_languages))
     languages = {code: lang for code, lang
-                 in languages.iteritems()
+                 in languages.items()
                  if len(lang.get('counter', [])) >= min_supported_engines or
                  len(languages.get(code.split('-')[0], {}).get('counter', [])) >= min_supported_engines}
 
@@ -165,7 +165,7 @@ def filter_single_country_languages():
 
 # Write languages.py.
 def write_languages_file():
-    new_file = open(languages_file, 'w')
+    new_file = open(languages_file, 'wb')
     file_content = '# -*- coding: utf-8 -*-\n'\
                    + '# list of language codes\n'\
                    + '# this file is generated automatically by utils/update_search_languages.py\n'\