mirror of
https://github.com/searxng/searxng.git
synced 2026-05-26 21:00:13 +02:00
Markus Heiser
efc305b7f9
[mod] normalize variable name for the max number of results per request In the past, we have used different names for the variable that specifies the maximum number of hits in the outgoing request. - ``page_size`` - ``number_of_results`` - ``nb_per_page`` Since *page_size* is the most accurate term and is also used in the XPath engines, all other engines are adjusted accordingly within this patch .. documentation adjusted accordingly. Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
77 lines
2.0 KiB
Python
77 lines
2.0 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""metacpan"""
|
|
|
|
from urllib.parse import urlunparse
|
|
|
|
# about
|
|
about = {
|
|
"website": 'https://metacpan.org/',
|
|
"wikidata_id": 'Q841507',
|
|
"official_api_documentation": 'https://github.com/metacpan/metacpan-api/blob/master/docs/API-docs.md',
|
|
"use_official_api": True,
|
|
"require_api_key": False,
|
|
"results": 'JSON',
|
|
}
|
|
|
|
# engine dependent config
|
|
page_size = 20 # Don't put this over 5000
|
|
categories = ["it", "packages"]
|
|
disabled = True
|
|
shortcut = "cpan"
|
|
paging = True
|
|
|
|
query_data_template = {
|
|
'query': {
|
|
'multi_match': {
|
|
'type': 'most_fields',
|
|
'fields': ['documentation', 'documentation.*'],
|
|
'analyzer': 'camelcase',
|
|
}
|
|
},
|
|
'filter': {
|
|
'bool': {
|
|
'must': [
|
|
{'exists': {'field': 'documentation'}},
|
|
{'term': {'status': 'latest'}},
|
|
{'term': {'indexed': 1}},
|
|
{'term': {'authorized': 1}},
|
|
]
|
|
}
|
|
},
|
|
"sort": [
|
|
{"_score": {"order": "desc"}},
|
|
{"date": {"order": "desc"}},
|
|
],
|
|
'_source': ['documentation', "abstract"],
|
|
'size': page_size,
|
|
}
|
|
search_url = urlunparse(["https", "fastapi.metacpan.org", "/v1/file/_search", "", "", ""])
|
|
|
|
|
|
def request(query, params):
|
|
params["url"] = search_url
|
|
params["method"] = "POST"
|
|
query_data = query_data_template
|
|
query_data["query"]["multi_match"]["query"] = query
|
|
query_data["from"] = (params["pageno"] - 1) * page_size
|
|
params["json"] = query_data
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
|
|
search_results = resp.json()["hits"]["hits"]
|
|
for result in search_results:
|
|
fields = result["_source"]
|
|
module = fields["documentation"]
|
|
results.append(
|
|
{
|
|
"url": "https://metacpan.org/pod/" + module,
|
|
"title": module,
|
|
"content": fields.get("abstract", ""),
|
|
}
|
|
)
|
|
|
|
return results
|