feat: provide the functionality to use the new config option

This commit is contained in:
neon_arch 2023-07-30 10:53:48 +03:00
parent 6d3396b6f9
commit 2d47e8d730
5 changed files with 18 additions and 8 deletions

View file

@ -41,6 +41,7 @@ impl SearchEngine for DuckDuckGo {
query: String,
page: u32,
user_agent: String,
request_timeout: u8,
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
// Page number can be missing or empty string and so appropriate handling is required
// so that upstream server recieves valid page number.
@ -90,7 +91,7 @@ impl SearchEngine for DuckDuckGo {
);
let document: Html = Html::parse_document(
&DuckDuckGo::fetch_html_from_upstream(self, url, header_map).await?,
&DuckDuckGo::fetch_html_from_upstream(self, url, header_map, request_timeout).await?,
);
let no_result: Selector = Selector::parse(".no-results")

View file

@ -50,11 +50,12 @@ pub trait SearchEngine {
&self,
url: String,
header_map: reqwest::header::HeaderMap,
request_timeout: u8,
) -> Result<String, EngineError> {
// fetch the html from upstream search engine
Ok(reqwest::Client::new()
.get(url)
.timeout(Duration::from_secs(30)) // Add timeout to request to avoid DDOSing the server
.timeout(Duration::from_secs(request_timeout as u64)) // Add timeout to request to avoid DDOSing the server
.headers(header_map) // add spoofed headers to emulate human behaviour
.send()
.await
@ -71,5 +72,6 @@ pub trait SearchEngine {
query: String,
page: u32,
user_agent: String,
request_timeout: u8,
) -> Result<HashMap<String, RawSearchResult>, EngineError>;
}

View file

@ -4,7 +4,7 @@
use reqwest::header::{HeaderMap, CONTENT_TYPE, COOKIE, REFERER, USER_AGENT};
use scraper::{Html, Selector};
use std::collections::HashMap;
use std::{collections::HashMap};
use crate::results::aggregation_models::RawSearchResult;
@ -40,6 +40,7 @@ impl SearchEngine for Searx {
query: String,
page: u32,
user_agent: String,
request_timeout: u8,
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
// Page number can be missing or empty string and so appropriate handling is required
// so that upstream server recieves valid page number.
@ -70,8 +71,9 @@ impl SearchEngine for Searx {
);
header_map.insert(COOKIE, "categories=general; language=auto; locale=en; autocomplete=duckduckgo; image_proxy=1; method=POST; safesearch=2; theme=simple; results_on_new_tab=1; doi_resolver=oadoi.org; simple_style=auto; center_alignment=1; query_in_title=1; infinite_scroll=0; disabled_engines=; enabled_engines=\"archive is__general\\054yep__general\\054curlie__general\\054currency__general\\054ddg definitions__general\\054wikidata__general\\054duckduckgo__general\\054tineye__general\\054lingva__general\\054startpage__general\\054yahoo__general\\054wiby__general\\054marginalia__general\\054alexandria__general\\054wikibooks__general\\054wikiquote__general\\054wikisource__general\\054wikiversity__general\\054wikivoyage__general\\054dictzone__general\\054seznam__general\\054mojeek__general\\054naver__general\\054wikimini__general\\054brave__general\\054petalsearch__general\\054goo__general\"; disabled_plugins=; enabled_plugins=\"searx.plugins.hostname_replace\\054searx.plugins.oa_doi_rewrite\\054searx.plugins.vim_hotkeys\"; tokens=; maintab=on; enginetab=on".parse().into_report().change_context(EngineError::UnexpectedError)?);
let document: Html =
Html::parse_document(&Searx::fetch_html_from_upstream(self, url, header_map).await?);
let document: Html = Html::parse_document(
&Searx::fetch_html_from_upstream(self, url, header_map, request_timeout).await?,
);
let no_result: Selector = Selector::parse("#urls>.dialog-error>p")
.map_err(|_| Report::new(EngineError::UnexpectedError))