0
0
mirror of https://github.com/neon-mmd/websurfx.git synced 2024-11-21 21:48:21 -05:00

Merge pull request #13 from neon-mmd/optimise-code-for-server-use

optimise code for large scale server use and closes #7
This commit is contained in:
neon_arch 2023-05-08 08:04:39 +00:00 committed by GitHub
commit ab7348ba3d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 22 additions and 22 deletions

View File

@ -2,9 +2,8 @@
//! by querying the upstream duckduckgo search engine with user provided query and with a page //! by querying the upstream duckduckgo search engine with user provided query and with a page
//! number if provided. //! number if provided.
use std::{collections::HashMap, time::Duration}; use std::collections::HashMap;
use rand::Rng;
use reqwest::header::{HeaderMap, CONTENT_TYPE, REFERER, USER_AGENT}; use reqwest::header::{HeaderMap, CONTENT_TYPE, REFERER, USER_AGENT};
use scraper::{Html, Selector}; use scraper::{Html, Selector};
@ -47,11 +46,6 @@ pub async fn results(
} }
}; };
// Add a random delay before making the request.
let mut rng = rand::thread_rng();
let delay_secs = rng.gen_range(1, 10);
std::thread::sleep(Duration::from_secs(delay_secs));
// initializing HeaderMap and adding appropriate headers. // initializing HeaderMap and adding appropriate headers.
let mut header_map = HeaderMap::new(); let mut header_map = HeaderMap::new();
header_map.insert(USER_AGENT, user_agent.parse()?); header_map.insert(USER_AGENT, user_agent.parse()?);

View File

@ -2,10 +2,9 @@
//! by querying the upstream searx search engine instance with user provided query and with a page //! by querying the upstream searx search engine instance with user provided query and with a page
//! number if provided. //! number if provided.
use rand::Rng;
use reqwest::header::{HeaderMap, CONTENT_TYPE, REFERER, USER_AGENT}; use reqwest::header::{HeaderMap, CONTENT_TYPE, REFERER, USER_AGENT};
use scraper::{Html, Selector}; use scraper::{Html, Selector};
use std::{collections::HashMap, time::Duration}; use std::collections::HashMap;
use crate::search_results_handler::aggregation_models::RawSearchResult; use crate::search_results_handler::aggregation_models::RawSearchResult;
@ -34,11 +33,6 @@ pub async fn results(
// so that upstream server recieves valid page number. // so that upstream server recieves valid page number.
let url: String = format!("https://searx.work/search?q={query}&pageno={page}"); let url: String = format!("https://searx.work/search?q={query}&pageno={page}");
// Add random delay before making the request.
let mut rng = rand::thread_rng();
let delay_secs = rng.gen_range(1, 10);
std::thread::sleep(Duration::from_secs(delay_secs));
// initializing headers and adding appropriate headers. // initializing headers and adding appropriate headers.
let mut header_map = HeaderMap::new(); let mut header_map = HeaderMap::new();
header_map.insert(USER_AGENT, user_agent.parse()?); header_map.insert(USER_AGENT, user_agent.parse()?);

View File

@ -1,7 +1,10 @@
//! This module provides the functionality to scrape and gathers all the results from the upstream //! This module provides the functionality to scrape and gathers all the results from the upstream
//! search engines and then removes duplicate results. //! search engines and then removes duplicate results.
use std::collections::HashMap; use std::{collections::HashMap, time::Duration};
use rand::Rng;
use tokio::join;
use super::{ use super::{
aggregation_models::{RawSearchResult, SearchResult, SearchResults}, aggregation_models::{RawSearchResult, SearchResult, SearchResults},
@ -14,14 +17,14 @@ use crate::engines::{duckduckgo, searx};
/// then removes duplicate results and if two results are found to be from two or more engines /// then removes duplicate results and if two results are found to be from two or more engines
/// then puts their names together to show the results are fetched from these upstream engines /// then puts their names together to show the results are fetched from these upstream engines
/// and then removes all data from the HashMap and puts into a struct of all results aggregated /// and then removes all data from the HashMap and puts into a struct of all results aggregated
/// into a vector and also adds the query used into the struct this is neccessory because /// into a vector and also adds the query used into the struct this is neccessory because
/// otherwise the search bar in search remains empty if searched from the query url /// otherwise the search bar in search remains empty if searched from the query url
/// ///
/// # Example: /// # Example:
/// ///
/// If you search from the url like `https://127.0.0.1/search?q=huston` then the search bar should /// If you search from the url like `https://127.0.0.1/search?q=huston` then the search bar should
/// contain the word huston and not remain empty. /// contain the word huston and not remain empty.
/// ///
/// # Arguments /// # Arguments
/// ///
/// * `query` - Accepts a string to query with the above upstream search engines. /// * `query` - Accepts a string to query with the above upstream search engines.
@ -29,7 +32,7 @@ use crate::engines::{duckduckgo, searx};
/// ///
/// # Error /// # Error
/// ///
/// Returns an error a reqwest and scraping selector errors if any error occurs in the results /// Returns an error a reqwest and scraping selector errors if any error occurs in the results
/// function in either `searx` or `duckduckgo` or both otherwise returns a `SearchResults struct` /// function in either `searx` or `duckduckgo` or both otherwise returns a `SearchResults struct`
/// containing appropriate values. /// containing appropriate values.
pub async fn aggregate( pub async fn aggregate(
@ -39,10 +42,19 @@ pub async fn aggregate(
let user_agent: String = random_user_agent(); let user_agent: String = random_user_agent();
let mut result_map: HashMap<String, RawSearchResult> = HashMap::new(); let mut result_map: HashMap<String, RawSearchResult> = HashMap::new();
let ddg_map_results: HashMap<String, RawSearchResult> = // Add a random delay before making the request.
duckduckgo::results(query, page, &user_agent).await?; let mut rng = rand::thread_rng();
let searx_map_results: HashMap<String, RawSearchResult> = let delay_secs = rng.gen_range(1, 10);
searx::results(query, page, &user_agent).await?; std::thread::sleep(Duration::from_secs(delay_secs));
// fetch results from upstream search engines simultaneously/concurrently.
let (ddg_map_results, searx_map_results) = join!(
duckduckgo::results(query, page, &user_agent),
searx::results(query, page, &user_agent)
);
let ddg_map_results: HashMap<String, RawSearchResult> = ddg_map_results?;
let searx_map_results: HashMap<String, RawSearchResult> = searx_map_results?;
result_map.extend(ddg_map_results); result_map.extend(ddg_map_results);