add neeva web engine

Neeva is "the world's first ad-free, private search engine" and uses data from Apple, Bing, Yelp and "others".
They claim to crawl "hundreds of millions" of URLs a day (https://twitter.com/Neeva/status/1536447373903335426).
This commit is contained in:
ta 2022-08-13 06:04:31 +07:00
parent 2bfb269f0a
commit d6dfada1a9

View file

@ -960,6 +960,30 @@ engines:
# collection: 'reviews' # name of the db collection # collection: 'reviews' # name of the db collection
# key: 'name' # key in the collection to search for # key: 'name' # key in the collection to search for
- name: neeva
engine: xpath
shortcut: nv
search_url: https://neeva.com/search?q={query}&c=All&src=Pagination&page={pageno}{time_range}
results_xpath: //div[@class="web-index__component-2rKiM"] | //li[@class="web-rich-deep-links__deepLink-SIbD4"]
url_xpath: .//a[@class="lib-doc-title__link-1b9rC"]/@href | ./h2/a/@href
title_xpath: .//a[@class="lib-doc-title__link-1b9rC"] | ./h2/a
content_xpath: >
.//div[@class="lib-doc-snippet__component-3ewW6"]/text() |
.//div[@class="lib-doc-snippet__component-3ewW6"]/*[not(self::a)] |
./p
content_html_to_text: true
suggestion_xpath: //span[@class="result-related-searches__link-2ho_u"]
paging: true
disabled: true
categories: [general, web]
timeout: 5.0
about:
website: https://neeva.com
official_api_documentation:
use_official_api: false
require_api_key: false
results: HTML
- name: npm - name: npm
engine: json_engine engine: json_engine
paging: true paging: true