Update epilog cause it didnt offend anyone

Co-authored-by: ErrorNoInternet <errornointernet@envs.net>

.gitignore

@@ -1 +1,2 @@
 /target
+/Cargo.lock

Cargo.toml

@@ -6,4 +6,5 @@ edition = "2021"
 [dependencies]
 regex = "1.11.0"
 reqwest = { version = "0.12.8", features = ["blocking"] }
+taap = "0.1.4"
 tokio = { version = "1", features = ["full"] }

README.md

@@ -5,3 +5,6 @@ a scraper that well scrapes r34
 ## note 
 
 this thing is still not completed, it only gathers links, it doesnt download things yet
+
+## example usage image
+![example image](./image.png)

rust-toolchain.toml

@@ -0,0 +1,2 @@
+[toolchain]
+channel = "nightly"

src/main.rs

@@ -2,21 +2,34 @@
 use regex::Regex;
 use reqwest::Client;
 use std::process::ExitCode;
+use taap::Argument;
 use tokio::time::{sleep, Duration};
 
 const USER_AGENT: &str = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36";
 
 #[tokio::main]
 async fn main() -> ExitCode {
-    println!("which tags do you want to scrape? ex: 1girls+1boys+yomama");
+    // Taap setup
-    let tags = std::io::stdin()
+    let mut arguments = Argument::new(
-        .lines()
+        "r34-scrape",
-        .next()
+        "A scraper for r34.xxx",
-        .unwrap()
+        "Users love this tool! Hear our reviews down below:\n\"It has never been easier to find what I love!\" - penguinlover\n\"This has made my life way easier!\" - FurryUser69\n\"Best tool I've ever used\" - Sean Combs\n",
-        .unwrap()
+        "Danmax and authors 2024",
-        .trim()
+    );
-        .to_string();
     
+    arguments.add_arg("TAGS", "+", Some("the tags you want to search for"));
+    let parsed_arguments = arguments.parse_args(None);
+    
+    let tags = parsed_arguments.get("TAGS").unwrap();
+    
+    // End of taap setup
+    // Check if empty and warn
+    // Can't use tags.0 because taap is not buggy at all :3
+    if tags.1.is_empty() {
+        println!("[warning] No tags were used, use --help for help")
+    }
+    
+    let mut thread_counter = 0;
     let client = Client::builder().user_agent(USER_AGENT).build().unwrap();
     let mut page = 0;
 
@@ -27,7 +40,12 @@ async fn main() -> ExitCode {
             extract_urls(
                 &client
                     .get(format!(
-                        "https://rule34.xxx/index.php?page=post&s=list&tags={tags}&pid={}",
+                        "https://rule34.xxx/index.php?page=post&s=list{}&pid={}",
+                        if tags.0 {
+                            format!("&tags={}", tags.1.join("+"))
+                        } else {
+                            "".to_owned()
+                        },
                         page * 42
                     ))
                     .send()
@@ -65,12 +83,46 @@ async fn main() -> ExitCode {
         }
 
         for url in urls {
-            let img_url =
+            tokio::spawn(async move {
-                extract_img_url(&client.get(url).send().await.unwrap().text().await.unwrap());
+                let thread_id = format!("[{thread_counter: >4}]");
-            if img_url.is_empty() {
+                loop {
-                println!("image url not found");
+                    let client = Client::builder().user_agent(USER_AGENT).build().unwrap();
-            } else {
+                    match extract_img_url(
-                println!("found image url: {img_url}");
+                        &client
+                            .get(url.clone())
+                            .send()
+                            .await
+                            .unwrap()
+                            .text()
+                            .await
+                            .unwrap(),
+                    ) {
+                        Ok(img_url) => {
+                            if img_url.is_empty() {
+                                println!("{thread_id} image url not found");
+                            } else {
+                                println!("{thread_id} found image url: {img_url}");
+                            }
+                        }
+                        Err(_) => {
+                            println!("{thread_id} ratelimited, retrying after 1 second");
+                            std::thread::sleep(std::time::Duration::from_millis(1000));
+                            continue;
+                        }
+                    }
+                    break;
+                }
+            });
+            thread_counter += 1;
+            if thread_counter > 9999 {
+                thread_counter = 0;
+            }
+            while tokio::runtime::Handle::current()
+                .metrics()
+                .num_alive_tasks()
+                > 4
+            {
+                std::thread::sleep(std::time::Duration::from_millis(100));
             }
         }
 
@@ -86,14 +138,18 @@ fn extract_urls(html: &str) -> Vec<String> {
         .collect()
 }
 
-fn extract_img_url(html: &str) -> String {
+fn extract_img_url(html: &str) -> Result<String, &'static str> {
     if let Some(img_url) =
         Regex::new(r"https://us\.rule34\.xxx/images/([A-Za-z0-9]+(/[A-Za-z0-9]+)+)\.[A-Za-z0-9]+")
             .unwrap()
             .find(html)
     {
-        img_url.as_str().to_string()
+        Ok(img_url.as_str().to_string())
     } else {
-        String::new()
+        if html.contains("503 Rate limiting") {
+            Err("ratelimited")
+        } else {
+            Ok(String::new())
+        }
     }
 }