searxng/searx/engines/__init__.py

174 lines
5.9 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
# pylint: disable=missing-function-docstring
"""
Engine loader:
call load_engines(settings['engines])
to initialiaze categories, engines, engine_shortcuts
"""
2013-10-16 22:32:32 +00:00
2014-02-05 19:24:31 +00:00
import sys
import copy
from os.path import realpath, dirname
from babel.localedata import locale_identifiers
from searx import logger, settings
from searx.data import ENGINES_LANGUAGES
from searx.network import get
from searx.utils import load_module, match_language, gen_useragent
2015-01-09 03:13:05 +00:00
logger = logger.getChild('engines')
ENGINE_DIR = dirname(realpath(__file__))
BABEL_LANGS = [lang_parts[0] + '-' + lang_parts[-1] if len(lang_parts) > 1 else lang_parts[0]
for lang_parts in (lang_code.split('_') for lang_code in locale_identifiers())]
ENGINE_DEFAULT_ARGS = {
"engine_type": "online",
"inactive": False,
"disabled": False,
"timeout": settings["outgoing"]["request_timeout"],
"shortcut": "-",
"categories": ["general"],
"supported_languages": [],
"language_aliases": {},
"paging": False,
"safesearch": False,
"time_range_support": False,
"enable_http": False,
"display_error_messages": True,
"tokens": [],
}
categories = {'general': []}
engines = {}
engine_shortcuts = {}
2014-12-13 18:26:40 +00:00
def load_engine(engine_data):
engine_name = engine_data['name']
if '_' in engine_name:
logger.error('Engine name contains underscore: "{}"'.format(engine_name))
sys.exit(1)
if engine_name.lower() != engine_name:
logger.warn('Engine name is not lowercase: "{}", converting to lowercase'.format(engine_name))
engine_name = engine_name.lower()
engine_data['name'] = engine_name
# load_module
engine_module = engine_data['engine']
try:
engine = load_module(engine_module + '.py', ENGINE_DIR)
except (SyntaxError, KeyboardInterrupt, SystemExit, SystemError, ImportError, RuntimeError):
logger.exception('Fatal exception in engine "{}"'.format(engine_module))
sys.exit(1)
except BaseException:
logger.exception('Cannot load engine "{}"'.format(engine_module))
return None
2014-01-31 03:35:23 +00:00
update_engine_attributes(engine, engine_data)
set_language_attributes(engine)
update_attributes_for_tor(engine)
if is_missing_required_attributes(engine):
sys.exit(1)
if not is_engine_active(engine):
return None
return engine
def update_engine_attributes(engine, engine_data):
# set engine attributes from engine_data
for param_name, param_value in engine_data.items():
if param_name == 'categories':
if isinstance(param_value, str):
param_value = list(map(str.strip, param_value.split(',')))
engine.categories = param_value
elif param_name != 'engine':
setattr(engine, param_name, param_value)
# set default attributes
for arg_name, arg_value in ENGINE_DEFAULT_ARGS.items():
2016-02-19 14:13:01 +00:00
if not hasattr(engine, arg_name):
setattr(engine, arg_name, copy.deepcopy(arg_value))
def set_language_attributes(engine):
# pylint: disable=protected-access
# assign supported languages from json file
if engine.name in ENGINES_LANGUAGES:
engine.supported_languages = ENGINES_LANGUAGES[engine.name]
# find custom aliases for non standard language codes
for engine_lang in engine.supported_languages:
iso_lang = match_language(engine_lang, BABEL_LANGS, fallback=None)
if iso_lang and iso_lang != engine_lang and not engine_lang.startswith(iso_lang) and \
iso_lang not in engine.supported_languages:
engine.language_aliases[iso_lang] = engine_lang
# language_support
engine.language_support = len(engine.supported_languages) > 0
# assign language fetching method if auxiliary method exists
if hasattr(engine, '_fetch_supported_languages'):
headers = {
'User-Agent': gen_useragent(),
'Accept-Language': 'ja-JP,ja;q=0.8,en-US;q=0.5,en;q=0.3', # bing needs a non-English language
}
engine.fetch_supported_languages =\
lambda: engine._fetch_supported_languages(get(engine.supported_languages_url, headers=headers))
def update_attributes_for_tor(engine):
if settings['outgoing'].get('using_tor_proxy') and hasattr(engine, 'onion_url'):
engine.search_url = engine.onion_url + getattr(engine, 'search_path', '')
engine.timeout += settings['outgoing'].get('extra_proxy_timeout', 0)
def is_missing_required_attributes(engine):
"""an attribute is required when its name doesn't start with '_'.
Required attributes must not be None
"""
missing = False
for engine_attr in dir(engine):
if not engine_attr.startswith('_') and getattr(engine, engine_attr) is None:
logger.error('Missing engine config attribute: "{0}.{1}"'
.format(engine.name, engine_attr))
missing = True
return missing
def is_engine_active(engine):
# check if engine is inactive
if engine.inactive is True:
return False
# exclude onion engines if not using tor
if 'onions' in engine.categories and not settings['outgoing'].get('using_tor_proxy'):
return False
return True
2016-02-19 14:13:01 +00:00
def register_engine(engine):
engines[engine.name] = engine
2016-02-19 14:13:01 +00:00
if engine.shortcut in engine_shortcuts:
logger.error('Engine config error: ambigious shortcut: {0}'.format(engine.shortcut))
sys.exit(1)
engine_shortcuts[engine.shortcut] = engine.name
for category_name in engine.categories:
categories.setdefault(category_name, []).append(engine)
def load_engines(engine_list):
"""Use case: engine_list = settings['engines']
"""
engines.clear()
engine_shortcuts.clear()
categories.clear()
categories['general'] = []
2016-12-27 16:25:19 +00:00
for engine_data in engine_list:
engine = load_engine(engine_data)
if engine:
register_engine(engine)
return engines