From ff84a1af35c04855ae6e5c2463b978111d8c9fb1 Mon Sep 17 00:00:00 2001 From: Alexandre Flament Date: Wed, 10 Feb 2021 16:40:03 +0100 Subject: [mod] json_engine: add content_html_to_text and title_html_to_text Some JSON API returns HTML in either in the HTML or the content. This commit adds two new parameters to the json_engine: content_html_to_text and title_html_to_text, False by default. If True, then the searx.utils.html_to_text removes the HTML tags. Update crossref, openairedatasets and openairepublications engines --- searx/settings.yml | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'searx/settings.yml') diff --git a/searx/settings.yml b/searx/settings.yml index 20b6c18c1..9c176b7c3 100644 --- a/searx/settings.yml +++ b/searx/settings.yml @@ -267,7 +267,9 @@ engines: search_url : https://search.crossref.org/dois?q={query}&page={pageno} url_query : doi title_query : title + title_html_to_text: True content_query : fullCitation + content_html_to_text: True categories : science shortcut : cr about: @@ -757,6 +759,7 @@ engines: url_query : metadata/oaf:entity/oaf:result/children/instance/webresource/url/$ title_query : metadata/oaf:entity/oaf:result/title/$ content_query : metadata/oaf:entity/oaf:result/description/$ + content_html_to_text: True categories : science shortcut : oad timeout: 5.0 @@ -776,6 +779,7 @@ engines: url_query : metadata/oaf:entity/oaf:result/children/instance/webresource/url/$ title_query : metadata/oaf:entity/oaf:result/title/$ content_query : metadata/oaf:entity/oaf:result/description/$ + content_html_to_text: True categories : science shortcut : oap timeout: 5.0 -- cgit v1.2.3