From 5ce292d1c262057cc9ebc43d7126b16ab660e64b Mon Sep 17 00:00:00 2001
From: javalsai <jvssxxi@gmail.com>
Date: Fri, 18 Oct 2024 19:26:11 +0200
Subject: [PATCH] chore: modularity & good code

---
 src/args/mod.rs | 16 +++++++++++++++
 src/main.rs     | 53 ++++++++++++++++++++++++-------------------------
 2 files changed, 42 insertions(+), 27 deletions(-)
 create mode 100644 src/args/mod.rs

diff --git a/src/args/mod.rs b/src/args/mod.rs
new file mode 100644
index 0000000..f982d82
--- /dev/null
+++ b/src/args/mod.rs
@@ -0,0 +1,16 @@
+use clap::Parser;
+
+#[derive(Parser)]
+#[command(version)]
+pub struct Args {
+    /// User Agent to use for requests
+    #[arg(
+        short,
+        default_value = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
+    )]
+    pub user_agent: String,
+
+    // Tags to search for
+    #[arg(short, long)]
+    pub tags: Option<Vec<String>>,
+}
diff --git a/src/main.rs b/src/main.rs
index 769b9ee..037909e 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -1,45 +1,44 @@
-#![feature(async_closure)]
+#![feature(async_closure, iter_intersperse)]
+pub mod args;
+
 use clap::Parser;
 use regex::Regex;
 use reqwest::Client;
 use std::process::ExitCode;
 use tokio::time::{sleep, Duration};
 
-#[derive(Parser)]
-#[command(version)]
-struct Args {
-    /// User Agent to use for requests
-    #[arg(
-        short,
-        default_value = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
-    )]
-    user_agent: String,
-}
-
 #[tokio::main]
 async fn main() -> ExitCode {
-    let args = Args::parse();
+    let args = args::Args::parse();
 
-    println!("which tags do you want to scrape? ex: 1girls+1boys+yomama");
-    let tags = std::io::stdin()
-        .lines()
-        .next()
-        .unwrap()
-        .unwrap()
-        .trim()
-        .to_string();
+    let tags = args.tags.unwrap_or_else(|| {
+        println!("which tags do you want to scrape? ex: 1girls 1boys yomama");
+        let tags_binding = std::io::stdin().lines().next().unwrap().unwrap();
+        tags_binding
+            .split(' ')
+            .filter(|item| !item.is_empty())
+            .map(|item| item.to_owned())
+            .collect()
+    });
+    let uri_tags: String = tags.into_iter().intersperse(String::from("+")).collect();
 
-    let client = Client::builder().user_agent(args.user_agent).build().unwrap();
-    let mut page = 0;
+    let client = Client::builder()
+        .user_agent(args.user_agent)
+        .build()
+        .unwrap();
 
-    loop {
+    for page in 0.. {
         println!("now scraping page {}", page + 1);
+        println!(
+            "https://rule34.xxx/index.php?page=post&s=list&tags={uri_tags}&pid={}",
+            page * 42
+        );
 
         let post_html = async || {
             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&tags={uri_tags}&pid={}",
                         page * 42
                     ))
                     .send()
@@ -85,9 +84,9 @@ async fn main() -> ExitCode {
                 println!("found image url: {img_url}");
             }
         }
-
-        page += 1;
     }
+
+    return ExitCode::SUCCESS;
 }
 
 fn extract_urls(html: &str) -> Vec<String> {