mirror of
https://github.com/neon-mmd/websurfx.git
synced 2024-11-22 14:08:23 -05:00
✨ feat: rewrite code by implementing common engine trait SearchEngine
This commit is contained in:
parent
b72af01e0e
commit
f9b9e87a0e
@ -9,7 +9,7 @@ use scraper::{Html, Selector};
|
|||||||
|
|
||||||
use crate::search_results_handler::aggregation_models::RawSearchResult;
|
use crate::search_results_handler::aggregation_models::RawSearchResult;
|
||||||
|
|
||||||
use super::engine_models::EngineError;
|
use super::engine_models::{EngineError, SearchEngine};
|
||||||
|
|
||||||
use error_stack::{IntoReport, Report, Result, ResultExt};
|
use error_stack::{IntoReport, Report, Result, ResultExt};
|
||||||
|
|
||||||
@ -30,10 +30,16 @@ use error_stack::{IntoReport, Report, Result, ResultExt};
|
|||||||
/// reach the above `upstream search engine` page or if the `upstream search engine` is unable to
|
/// reach the above `upstream search engine` page or if the `upstream search engine` is unable to
|
||||||
/// provide results for the requested search query and also returns error if the scraping selector
|
/// provide results for the requested search query and also returns error if the scraping selector
|
||||||
/// or HeaderMap fails to initialize.
|
/// or HeaderMap fails to initialize.
|
||||||
pub async fn results(
|
|
||||||
query: &str,
|
pub struct DuckDuckGo;
|
||||||
|
|
||||||
|
#[async_trait::async_trait]
|
||||||
|
impl SearchEngine for DuckDuckGo {
|
||||||
|
async fn results(
|
||||||
|
&self,
|
||||||
|
query: String,
|
||||||
page: u32,
|
page: u32,
|
||||||
user_agent: &str,
|
user_agent: String,
|
||||||
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
||||||
// Page number can be missing or empty string and so appropriate handling is required
|
// Page number can be missing or empty string and so appropriate handling is required
|
||||||
// so that upstream server recieves valid page number.
|
// so that upstream server recieves valid page number.
|
||||||
@ -82,21 +88,9 @@ pub async fn results(
|
|||||||
.change_context(EngineError::UnexpectedError)?,
|
.change_context(EngineError::UnexpectedError)?,
|
||||||
);
|
);
|
||||||
|
|
||||||
// fetch the html from upstream duckduckgo engine
|
let document: Html = Html::parse_document(
|
||||||
let results: String = reqwest::Client::new()
|
&DuckDuckGo::fetch_html_from_upstream(&self, url, header_map).await?,
|
||||||
.get(url)
|
);
|
||||||
.timeout(Duration::from_secs(5))
|
|
||||||
.headers(header_map) // add spoofed headers to emulate human behaviour
|
|
||||||
.send()
|
|
||||||
.await
|
|
||||||
.into_report()
|
|
||||||
.change_context(EngineError::RequestError)?
|
|
||||||
.text()
|
|
||||||
.await
|
|
||||||
.into_report()
|
|
||||||
.change_context(EngineError::RequestError)?;
|
|
||||||
|
|
||||||
let document: Html = Html::parse_document(&results);
|
|
||||||
|
|
||||||
let no_result: Selector = Selector::parse(".no-results")
|
let no_result: Selector = Selector::parse(".no-results")
|
||||||
.map_err(|_| Report::new(EngineError::UnexpectedError))
|
.map_err(|_| Report::new(EngineError::UnexpectedError))
|
||||||
@ -153,3 +147,4 @@ pub async fn results(
|
|||||||
.map(|search_result| (search_result.visiting_url.clone(), search_result))
|
.map(|search_result| (search_result.visiting_url.clone(), search_result))
|
||||||
.collect())
|
.collect())
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
@ -8,7 +8,7 @@ use std::collections::HashMap;
|
|||||||
|
|
||||||
use crate::search_results_handler::aggregation_models::RawSearchResult;
|
use crate::search_results_handler::aggregation_models::RawSearchResult;
|
||||||
|
|
||||||
use super::engine_models::EngineError;
|
use super::engine_models::{EngineError, SearchEngine};
|
||||||
use error_stack::{IntoReport, Report, Result, ResultExt};
|
use error_stack::{IntoReport, Report, Result, ResultExt};
|
||||||
|
|
||||||
/// This function scrapes results from the upstream engine duckduckgo and puts all the scraped
|
/// This function scrapes results from the upstream engine duckduckgo and puts all the scraped
|
||||||
@ -28,10 +28,16 @@ use error_stack::{IntoReport, Report, Result, ResultExt};
|
|||||||
/// reach the above `upstream search engine` page or if the `upstream search engine` is unable to
|
/// reach the above `upstream search engine` page or if the `upstream search engine` is unable to
|
||||||
/// provide results for the requested search query and also returns error if the scraping selector
|
/// provide results for the requested search query and also returns error if the scraping selector
|
||||||
/// or HeaderMap fails to initialize.
|
/// or HeaderMap fails to initialize.
|
||||||
pub async fn results(
|
|
||||||
query: &str,
|
pub struct Searx;
|
||||||
|
|
||||||
|
#[async_trait::async_trait]
|
||||||
|
impl SearchEngine for Searx {
|
||||||
|
async fn results(
|
||||||
|
&self,
|
||||||
|
query: String,
|
||||||
page: u32,
|
page: u32,
|
||||||
user_agent: &str,
|
user_agent: String,
|
||||||
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
) -> Result<HashMap<String, RawSearchResult>, EngineError> {
|
||||||
// Page number can be missing or empty string and so appropriate handling is required
|
// Page number can be missing or empty string and so appropriate handling is required
|
||||||
// so that upstream server recieves valid page number.
|
// so that upstream server recieves valid page number.
|
||||||
@ -62,24 +68,14 @@ pub async fn results(
|
|||||||
);
|
);
|
||||||
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)?);
|
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)?);
|
||||||
|
|
||||||
// fetch the html from upstream searx instance engine
|
let document: Html =
|
||||||
let results: String = reqwest::Client::new()
|
Html::parse_document(&Searx::fetch_html_from_upstream(&self, url, header_map).await?);
|
||||||
.get(url)
|
|
||||||
.headers(header_map) // add spoofed headers to emulate human behaviours.
|
|
||||||
.send()
|
|
||||||
.await
|
|
||||||
.into_report()
|
|
||||||
.change_context(EngineError::RequestError)?
|
|
||||||
.text()
|
|
||||||
.await
|
|
||||||
.into_report()
|
|
||||||
.change_context(EngineError::RequestError)?;
|
|
||||||
|
|
||||||
let document: Html = Html::parse_document(&results);
|
|
||||||
|
|
||||||
let no_result: Selector = Selector::parse("#urls>.dialog-error>p")
|
let no_result: Selector = Selector::parse("#urls>.dialog-error>p")
|
||||||
.map_err(|_| Report::new(EngineError::UnexpectedError))
|
.map_err(|_| Report::new(EngineError::UnexpectedError))
|
||||||
.attach_printable_lazy(|| format!("invalid CSS selector: {}", "#urls>.dialog-error>p"))?;
|
.attach_printable_lazy(|| {
|
||||||
|
format!("invalid CSS selector: {}", "#urls>.dialog-error>p")
|
||||||
|
})?;
|
||||||
|
|
||||||
if let Some(no_result_msg) = document.select(&no_result).nth(1) {
|
if let Some(no_result_msg) = document.select(&no_result).nth(1) {
|
||||||
if no_result_msg.inner_html()
|
if no_result_msg.inner_html()
|
||||||
@ -136,3 +132,4 @@ pub async fn results(
|
|||||||
.map(|search_result| (search_result.visiting_url.clone(), search_result))
|
.map(|search_result| (search_result.visiting_url.clone(), search_result))
|
||||||
.collect())
|
.collect())
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user