added -b/break-when-found flag

Author: QpxDesign

Cargo.lock

@@ -1,7 +1,7 @@
 
 [package]
 name = "webgrep"
-version = "0.3.3"
+version = "0.3.4"
 edition = "2021"
 license = "MIT"
 description = "grep the web: a full-browser-spec search-focused ultra-simple way to read the web without having to leave the terminal"

Cargo.toml

@@ -13,6 +13,7 @@ to use headless-chrome with webgrep, either use the `-c/--chrome` flag, or set t
 - `-o/--samehost` OPTIONAL, only explore webpages on the same host (ie same domain)
 - `-c/--chrome` OPTIONAL, use chrome instead of just basic http request (needed for sites with js)
 - `-i/--insensitive` OPTIONAL, search case-insensitivly
+- `-b/--break_when_found` OPTIONAL, stop recursion when search nets result
 
 ### Examples:
 recursively search through a college course catalog for a keyword (case insensitive):

README.md

@@ -24,4 +24,7 @@ pub struct ArgParser {
 
     #[arg(short = 'c', long = "chrome", action=ArgAction::SetTrue)]
     pub use_chrome: Option<bool>,
+
+    #[arg(short, long, action=ArgAction::SetTrue)]
+    pub break_when_found: Option<bool>,
 }

src/structs/Args.rs

@@ -7,6 +7,7 @@ use crate::utils::request_handler;
 use async_recursion::async_recursion;
 use clap::Parser;
 use lazy_static::lazy_static;
+use regex::Regex;
 use reqwest::Client;
 use std::collections::HashMap;
 use std::sync::Mutex;
@@ -47,7 +48,7 @@ pub async fn recurse(
             let link_selector = Selector::parse("a").unwrap();
             let mut phtml = Html::new_document();
             if use_chrome.is_some() && use_chrome.unwrap() {
-                phtml = request_handler::browse_for_html_from_url(specific_url).await;
+                phtml = request_handler::browse_for_html_from_url(specific_url.clone()).await;
             } else {
                 phtml = request_handler::get_html_from_url(&specific_url).await;
             }
@@ -65,6 +66,26 @@ pub async fn recurse(
                     if Url::parse(&href) == Err(url::ParseError::RelativeUrlWithoutBase) {
                         href = parsed_url.join(&href).unwrap().as_str().to_string();
                     }
+                    if args.break_when_found.is_some() && args.break_when_found.unwrap() {
+                        let mut re = Regex::new("").unwrap();
+                        if args.search.clone().is_some() {
+                            if args.insensitive.is_some() && args.insensitive.unwrap() == true {
+                                re = Regex::new(
+                                    &("(?i)".to_owned() + &args.search.clone().unwrap()),
+                                )
+                                .unwrap();
+                            } else {
+                                re = Regex::new(&args.search.clone().unwrap()).unwrap();
+                            }
+                        }
+                        for t in CACHE.lock().unwrap().values_mut() {
+                            for a in t {
+                                if re.is_match(a) {
+                                    return get_links(links, depth - 1, use_chrome).await;
+                                }
+                            }
+                        }
+                    }
                     if !CACHE.lock().unwrap().contains_key(&href) && !Url::parse(&href).is_err() {
                         let mut file_type = "html";
                         if crate::utils::determine_file_type::determine_file_type(&href) == "pdf" {

src/utils/recurse.rs

@@ -63,3 +63,9 @@ name = "Search/Insensitive"
 run_type = "lines_count"
 cmd = "../target/release/webgrep https://google.com dark -i"
 expect = "3"
+
+[[test_cases]]
+name = "Recursive/BreakWhenFound"
+run_type = "lines_count"
+cmd = "../target/debug/webgrep https://quinnpatwardhan.com/ frisb -r 1 -b -c"
+expect = "5"