0
0
mirror of https://github.com/neon-mmd/websurfx.git synced 2024-10-18 06:22:53 -04:00

LibreX for the search engine (#429)

*  feat(engine): provide librex search engine (#318)

*  feat(engine): provide librex search engine (#318)

*  feat(engine): provide librex search engine (#318)

* 🔖 chore(release): bump the app version (#318)

* 🔖 chore(release): bump the app version (#318)

*  feat(engine): provide librex search engine (#318)

*  feat(engine): provide librex search engine (#429)

Co-authored-by: neon_arch <mustafadhuleb53@gmail.com>

*  feat(engine): provide librex search engine (#429)

Co-authored-by: neon_arch <mustafadhuleb53@gmail.com>

*  feat(engine): provide librex search engine (#429)

Co-authored-by: neon_arch <mustafadhuleb53@gmail.com>

*  feat(engine): provide librex search engine (#429)

*  feat(engine): provide librex search engine (#429)

*  feat(engine): provide librex search engine (#429)

*  feat(engine): provide librex search engine (#429)

Co-authored-by: neon_arch <mustafadhuleb53@gmail.com>

---------

Co-authored-by: neon_arch <mustafadhuleb53@gmail.com>
This commit is contained in:
alamin655 2023-12-09 16:55:28 +05:30 committed by GitHub
parent 1143846ca6
commit c02006c297
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 119 additions and 2 deletions

2
Cargo.lock generated
View File

@ -4066,7 +4066,7 @@ checksum = "1778a42e8b3b90bff8d0f5032bf22250792889a5cdc752aa0020c84abe3aaf10"
[[package]] [[package]]
name = "websurfx" name = "websurfx"
version = "1.4.2" version = "1.5.0"
dependencies = [ dependencies = [
"actix-cors", "actix-cors",
"actix-files", "actix-files",

View File

@ -1,6 +1,6 @@
[package] [package]
name = "websurfx" name = "websurfx"
version = "1.4.2" version = "1.5.0"
edition = "2021" edition = "2021"
description = "An open-source alternative to Searx that provides clean, ad-free, and organic results with incredible speed while keeping privacy and security in mind." description = "An open-source alternative to Searx that provides clean, ad-free, and organic results with incredible speed while keeping privacy and security in mind."
repository = "https://github.com/neon-mmd/websurfx" repository = "https://github.com/neon-mmd/websurfx"

111
src/engines/librex.rs Normal file
View File

@ -0,0 +1,111 @@
//! The `librex` module contains the implementation of a search engine for LibreX using the reqwest and scraper libraries.
//! It includes a `SearchEngine` trait implementation for interacting with the search engine and retrieving search results.
use std::collections::HashMap;
use reqwest::header::HeaderMap;
use reqwest::Client;
use scraper::Html;
use crate::models::aggregation_models::SearchResult;
use crate::models::engine_models::{EngineError, SearchEngine};
use error_stack::{Report, Result, ResultExt};
use super::search_result_parser::SearchResultParser;
/// Represents the LibreX search engine.
pub struct LibreX {
/// The parser used to extract search results from HTML documents.
parser: SearchResultParser,
}
impl LibreX {
/// Creates a new instance of LibreX with a default configuration.
///
/// # Returns
///
/// Returns a `Result` containing `LibreX` if successful, otherwise an `EngineError`.
pub fn new() -> Result<Self, EngineError> {
Ok(Self {
parser: SearchResultParser::new(
".text-result-container>p",
".text-result-container",
".text-result-wrapper>a>h2",
".text-result-wrapper>a",
".text-result-wrapper>span",
)?,
})
}
}
#[async_trait::async_trait]
impl SearchEngine for LibreX {
/// Retrieves search results from LibreX based on the provided query, page, user agent, and client.
///
/// # Arguments
///
/// * `query` - The search query.
/// * `page` - The page number for pagination.
/// * `user_agent` - The user agent string.
/// * `client` - The reqwest client for making HTTP requests.
/// * `_safe_search` - A parameter for safe search (not currently used).
///
/// # Returns
///
/// Returns a `Result` containing a `HashMap` of search results if successful, otherwise an `EngineError`.
/// The `Err` variant is explicit for better documentation.
async fn results(
&self,
query: &str,
page: u32,
user_agent: &str,
client: &Client,
_safe_search: u8,
) -> Result<HashMap<String, SearchResult>, EngineError> {
// Page number can be missing or empty string and so appropriate handling is required
// so that upstream server recieves valid page number.
let url: String = match page {
1 | 0 => {
format!("https://search.ahwx.org/search.php?q={query}&p=0&t=10")
}
_ => {
format!(
"https://search.ahwx.org/search.php?q={query}&p={}&t=10",
page * 10,
)
}
};
// initializing HeaderMap and adding appropriate headers.
let header_map = HeaderMap::try_from(&HashMap::from([
("USER_AGENT".to_string(), user_agent.to_string()),
("REFERER".to_string(), "https://google.com/".to_string()),
("CONTENT_TYPE".to_string(), "application/x-www-form-urlencoded".to_string()),
(
"COOKIE".to_string(),
"theme=amoled; disable_special=on; disable_frontends=on; language=en; number_of_results=10; safe_search=on; save=1".to_string(),
),
]))
.change_context(EngineError::UnexpectedError)?;
let document: Html = Html::parse_document(
&LibreX::fetch_html_from_upstream(self, &url, header_map, client).await?,
);
if self.parser.parse_for_no_results(&document).next().is_some() {
return Err(Report::new(EngineError::EmptyResultSet));
}
// scrape all the results from the html
self.parser
.parse_for_results(&document, |title, url, desc| {
Some(SearchResult::new(
title.inner_html().trim(),
url.inner_html().trim(),
desc.inner_html().trim(),
&["librex"],
))
})
}
}

View File

@ -5,6 +5,7 @@
pub mod brave; pub mod brave;
pub mod duckduckgo; pub mod duckduckgo;
pub mod librex;
pub mod search_result_parser; pub mod search_result_parser;
pub mod searx; pub mod searx;
pub mod startpage; pub mod startpage;

View File

@ -158,6 +158,10 @@ impl EngineHandler {
let engine = crate::engines::startpage::Startpage::new()?; let engine = crate::engines::startpage::Startpage::new()?;
("startpage", Box::new(engine)) ("startpage", Box::new(engine))
} }
"librex" => {
let engine = crate::engines::librex::LibreX::new()?;
("librex", Box::new(engine))
}
_ => { _ => {
return Err(Report::from(EngineError::NoSuchEngineFound( return Err(Report::from(EngineError::NoSuchEngineFound(
engine_name.to_string(), engine_name.to_string(),

View File

@ -54,4 +54,5 @@ upstream_search_engines = {
Searx = false, Searx = false,
Brave = false, Brave = false,
Startpage = false, Startpage = false,
LibreX = false,
} -- select the upstream search engines from which the results should be fetched. } -- select the upstream search engines from which the results should be fetched.