2021-01-13 10:31:25 +00:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
2024-03-11 06:45:08 +00:00
|
|
|
"""The JSON engine is a *generic* engine with which it is possible to configure
|
|
|
|
engines in the settings.
|
|
|
|
|
|
|
|
.. todo::
|
|
|
|
|
|
|
|
- The JSON engine needs documentation!!
|
|
|
|
|
|
|
|
- The parameters of the JSON engine should be adapted to those of the XPath
|
|
|
|
engine.
|
|
|
|
|
|
|
|
"""
|
2021-01-13 10:31:25 +00:00
|
|
|
|
2020-10-05 10:52:08 +00:00
|
|
|
from collections.abc import Iterable
|
2016-11-30 17:43:03 +00:00
|
|
|
from json import loads
|
2020-08-06 15:42:46 +00:00
|
|
|
from urllib.parse import urlencode
|
2021-02-10 15:40:03 +00:00
|
|
|
from searx.utils import to_string, html_to_text
|
2016-11-30 17:43:03 +00:00
|
|
|
|
2013-11-19 14:49:52 +00:00
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
search_url = None
|
|
|
|
url_query = None
|
2023-10-20 09:26:28 +00:00
|
|
|
url_prefix = ""
|
2013-11-19 14:49:52 +00:00
|
|
|
content_query = None
|
2014-01-20 01:31:20 +00:00
|
|
|
title_query = None
|
2021-02-10 15:40:03 +00:00
|
|
|
content_html_to_text = False
|
|
|
|
title_html_to_text = False
|
2016-11-30 17:43:03 +00:00
|
|
|
paging = False
|
2016-08-12 10:15:27 +00:00
|
|
|
suggestion_query = ''
|
|
|
|
results_query = ''
|
2013-11-19 14:49:52 +00:00
|
|
|
|
2022-06-10 21:26:55 +00:00
|
|
|
cookies = {}
|
|
|
|
headers = {}
|
|
|
|
'''Some engines might offer different result based on cookies or headers.
|
|
|
|
Possible use-case: To set safesearch cookie or header to moderate.'''
|
|
|
|
|
2016-07-16 09:26:29 +00:00
|
|
|
# parameters for engines with paging support
|
|
|
|
#
|
|
|
|
# number of results on each page
|
|
|
|
# (only needed if the site requires not a page number, but an offset)
|
|
|
|
page_size = 1
|
|
|
|
# number of the first page (usually 0 or 1)
|
|
|
|
first_page_num = 1
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
|
2013-11-19 14:49:52 +00:00
|
|
|
def iterate(iterable):
|
2024-03-11 06:45:08 +00:00
|
|
|
if isinstance(iterable, dict):
|
|
|
|
items = iterable.items()
|
2013-11-19 14:49:52 +00:00
|
|
|
|
|
|
|
else:
|
2024-03-11 06:45:08 +00:00
|
|
|
items = enumerate(iterable)
|
|
|
|
for index, value in items:
|
2013-11-19 14:49:52 +00:00
|
|
|
yield str(index), value
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
|
2013-11-19 14:49:52 +00:00
|
|
|
def is_iterable(obj):
|
2024-03-11 06:45:08 +00:00
|
|
|
if isinstance(obj, str):
|
2014-01-20 01:31:20 +00:00
|
|
|
return False
|
2013-11-19 14:49:52 +00:00
|
|
|
return isinstance(obj, Iterable)
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
|
2024-03-11 06:45:08 +00:00
|
|
|
def parse(query): # pylint: disable=redefined-outer-name
|
|
|
|
q = [] # pylint: disable=invalid-name
|
2013-11-19 14:49:52 +00:00
|
|
|
for part in query.split('/'):
|
|
|
|
if part == '':
|
|
|
|
continue
|
2024-03-11 06:45:08 +00:00
|
|
|
q.append(part)
|
2013-11-19 14:49:52 +00:00
|
|
|
return q
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
|
2024-03-11 06:45:08 +00:00
|
|
|
def do_query(data, q): # pylint: disable=invalid-name
|
2013-11-19 14:49:52 +00:00
|
|
|
ret = []
|
2014-02-11 12:13:51 +00:00
|
|
|
if not q:
|
2013-11-19 14:49:52 +00:00
|
|
|
return ret
|
|
|
|
|
|
|
|
qkey = q[0]
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
for key, value in iterate(data):
|
2013-11-19 14:49:52 +00:00
|
|
|
|
|
|
|
if len(q) == 1:
|
|
|
|
if key == qkey:
|
|
|
|
ret.append(value)
|
|
|
|
elif is_iterable(value):
|
|
|
|
ret.extend(do_query(value, q))
|
|
|
|
else:
|
|
|
|
if not is_iterable(value):
|
|
|
|
continue
|
|
|
|
if key == qkey:
|
|
|
|
ret.extend(do_query(value, q[1:]))
|
|
|
|
else:
|
|
|
|
ret.extend(do_query(value, q))
|
|
|
|
return ret
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
|
2013-11-19 14:49:52 +00:00
|
|
|
def query(data, query_string):
|
|
|
|
q = parse(query_string)
|
|
|
|
|
|
|
|
return do_query(data, q)
|
|
|
|
|
2014-01-20 01:31:20 +00:00
|
|
|
|
2024-03-11 06:45:08 +00:00
|
|
|
def request(query, params): # pylint: disable=redefined-outer-name
|
2013-11-19 14:49:52 +00:00
|
|
|
query = urlencode({'q': query})[2:]
|
2016-07-16 09:26:29 +00:00
|
|
|
|
2024-03-11 06:45:08 +00:00
|
|
|
fp = {'query': query} # pylint: disable=invalid-name
|
2016-07-16 09:26:29 +00:00
|
|
|
if paging and search_url.find('{pageno}') >= 0:
|
2016-08-14 11:46:54 +00:00
|
|
|
fp['pageno'] = (params['pageno'] - 1) * page_size + first_page_num
|
2016-07-16 09:26:29 +00:00
|
|
|
|
2022-06-10 21:26:55 +00:00
|
|
|
params['cookies'].update(cookies)
|
|
|
|
params['headers'].update(headers)
|
|
|
|
|
2016-07-16 09:26:29 +00:00
|
|
|
params['url'] = search_url.format(**fp)
|
2013-11-19 14:49:52 +00:00
|
|
|
params['query'] = query
|
2016-07-16 09:26:29 +00:00
|
|
|
|
2013-11-19 14:49:52 +00:00
|
|
|
return params
|
|
|
|
|
|
|
|
|
2021-02-10 15:40:03 +00:00
|
|
|
def identity(arg):
|
|
|
|
return arg
|
|
|
|
|
|
|
|
|
2013-11-19 14:49:52 +00:00
|
|
|
def response(resp):
|
|
|
|
results = []
|
|
|
|
json = loads(resp.text)
|
2021-02-10 15:40:03 +00:00
|
|
|
|
|
|
|
title_filter = html_to_text if title_html_to_text else identity
|
|
|
|
content_filter = html_to_text if content_html_to_text else identity
|
|
|
|
|
2016-08-12 10:15:27 +00:00
|
|
|
if results_query:
|
2024-03-11 06:45:08 +00:00
|
|
|
rs = query(json, results_query) # pylint: disable=invalid-name
|
|
|
|
if not rs:
|
2017-11-01 23:43:29 +00:00
|
|
|
return results
|
|
|
|
for result in rs[0]:
|
2017-11-02 00:08:15 +00:00
|
|
|
try:
|
|
|
|
url = query(result, url_query)[0]
|
|
|
|
title = query(result, title_query)[0]
|
2024-03-11 06:45:08 +00:00
|
|
|
except: # pylint: disable=bare-except
|
2017-11-02 00:08:15 +00:00
|
|
|
continue
|
2017-11-01 23:43:29 +00:00
|
|
|
try:
|
|
|
|
content = query(result, content_query)[0]
|
2024-03-11 06:45:08 +00:00
|
|
|
except: # pylint: disable=bare-except
|
2017-11-01 23:43:29 +00:00
|
|
|
content = ""
|
2021-12-27 08:26:22 +00:00
|
|
|
results.append(
|
|
|
|
{
|
2023-10-20 09:26:28 +00:00
|
|
|
'url': url_prefix + to_string(url),
|
2021-12-27 08:26:22 +00:00
|
|
|
'title': title_filter(to_string(title)),
|
|
|
|
'content': content_filter(to_string(content)),
|
|
|
|
}
|
|
|
|
)
|
2016-08-12 10:15:27 +00:00
|
|
|
else:
|
2021-12-27 08:26:22 +00:00
|
|
|
for url, title, content in zip(query(json, url_query), query(json, title_query), query(json, content_query)):
|
|
|
|
results.append(
|
|
|
|
{
|
2023-10-20 09:26:28 +00:00
|
|
|
'url': url_prefix + to_string(url),
|
2021-12-27 08:26:22 +00:00
|
|
|
'title': title_filter(to_string(title)),
|
|
|
|
'content': content_filter(to_string(content)),
|
|
|
|
}
|
|
|
|
)
|
2016-08-12 10:15:27 +00:00
|
|
|
|
|
|
|
if not suggestion_query:
|
|
|
|
return results
|
|
|
|
for suggestion in query(json, suggestion_query):
|
|
|
|
results.append({'suggestion': suggestion})
|
2013-11-19 14:49:52 +00:00
|
|
|
return results
|