1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-19 10:50:09 +01:00
searxng/searx/search/processors/online_url_search.py
Markus Heiser 6e5f22e558 [mod] replace engines_languages.json by engines_traits.json
Implementations of the *traits* of the engines.

Engine's traits are fetched from the origin engine and stored in a JSON file in
the *data folder*.  Most often traits are languages and region codes and their
mapping from SearXNG's representation to the representation in the origin search
engine.

To load traits from the persistence::

    searx.enginelib.traits.EngineTraitsMap.from_data()

For new traits new properties can be added to the class::

    searx.enginelib.traits.EngineTraits

.. hint::

   Implementation is downward compatible to the deprecated *supported_languages
   method* from the vintage implementation.

   The vintage code is tagged as *deprecated* an can be removed when all engines
   has been ported to the *traits method*.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2023-03-24 10:37:42 +01:00

47 lines
1.2 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Processores for engine-type: ``online_url_search``
"""
import re
from .online import OnlineProcessor
re_search_urls = {
'http': re.compile(r'https?:\/\/[^ ]*'),
'ftp': re.compile(r'ftps?:\/\/[^ ]*'),
'data:image': re.compile('data:image/[^; ]*;base64,[^ ]*'),
}
class OnlineUrlSearchProcessor(OnlineProcessor):
"""Processor class used by ``online_url_search`` engines."""
engine_type = 'online_url_search'
def get_params(self, search_query, engine_category):
"""Returns a set of :ref:`request params <engine request online>` or ``None`` if
search query does not match to :py:obj:`re_search_urls`.
"""
params = super().get_params(search_query, engine_category)
if params is None:
return None
url_match = False
search_urls = {}
for k, v in re_search_urls.items():
m = v.search(search_query.query)
v = None
if m:
url_match = True
v = m[0]
search_urls[k] = v
if not url_match:
return None
params['search_urls'] = search_urls
return params