From d2e9d75b0e9ce2b1a3c05e7b4ae7216323b3a516 Mon Sep 17 00:00:00 2001
From: Myzel394 <50424412+Myzel394@users.noreply.github.com>
Date: Sun, 28 Jan 2024 20:45:02 +0100
Subject: [PATCH] feat: Add first wip for parsers

---
 Cargo.lock                 | 40 +++++++++++++++++
 Cargo.toml                 |  2 +
 src/client.rs              | 16 +++++--
 src/engines.rs             |  2 +
 src/engines/duckduckgo.rs  | 90 ++++++++++++++++++++++++++++++++++++++
 src/engines/engine_base.rs | 13 ++++++
 src/main.rs                | 24 ++++++----
 7 files changed, 175 insertions(+), 12 deletions(-)
 create mode 100644 src/engines.rs
 create mode 100644 src/engines/duckduckgo.rs
 create mode 100644 src/engines/engine_base.rs

diff --git a/Cargo.lock b/Cargo.lock
index f5624b3..2d4582f 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -17,6 +17,15 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
+[[package]]
+name = "aho-corasick"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "autocfg"
 version = "1.1.0"
@@ -537,6 +546,35 @@ dependencies = [
  "bitflags 1.3.2",
 ]
 
+[[package]]
+name = "regex"
+version = "1.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b62dbe01f0b06f9d8dc7d49e05a0785f153b00b2c227856282f671e0318c9b15"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5bb987efffd3c6d0d8f5f89510bb458559eab11e4f869acb20bf845e016259cd"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08c74e62047bb2de4ff487b251e4a92e24f48745648451635cec7d591162d9f"
+
 [[package]]
 name = "reqwest"
 version = "0.11.23"
@@ -787,6 +825,8 @@ dependencies = [
 name = "tcp_test"
 version = "0.1.0"
 dependencies = [
+ "lazy_static",
+ "regex",
  "reqwest",
  "rustls",
  "tokio",
diff --git a/Cargo.toml b/Cargo.toml
index e92e71c..531d9da 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -6,6 +6,8 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+lazy_static = "1.4.0"
+regex = "1.10.3"
 reqwest = "0.11.23"
 rustls = "0.22.2"
 tokio = "1.35.1"
diff --git a/src/client.rs b/src/client.rs
index af98868..29930da 100644
--- a/src/client.rs
+++ b/src/client.rs
@@ -58,7 +58,16 @@ pub mod client {
                     "{} {} HTTP/1.1\r\n",
                     "Host: {}\r\n",
                     "Connection: close\r\n",
-                    "Accept-Encoding: identity\r\n",
+                    // "Accept-Encoding: identity\r\n",
+                    "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36\r\n",
+                    "Upgrade-Insecure-Requests: 1\r\n",
+                    "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8\r\n",
+                    "Dnt: 1\r\n",
+                    "Accept-Language: en-US,en;q=0.9\r\n",
+                    "Content-Type: application/x-www-form-urlencoded\r\n",
+                    "Content-Length: 6\r\n",
+                    "\r\n",
+                    "q=duck\r\n",
                     "\r\n",
                 ),
                 method,
@@ -70,13 +79,14 @@ pub mod client {
         pub fn request(
             &self,
             method: &str,
-            on_partial: fn(&[u8; PACKET_SIZE], &[u8]),
+            // on_partial: Box<dyn FnMut(&[u8; PACKET_SIZE], &[u8])>,
         ) -> Result<Vec<u8>, Box<dyn Error>> {
             let mut connection = self.create_connection()?;
 
             let mut sock = self.create_tcp_stream()?;
             let mut tls = rustls::Stream::new(&mut connection, &mut sock);
             let http_header = self.create_http_header(method)?;
+            dbg!(&http_header);
             tls.write_all(&http_header.as_bytes())?;
 
             // Read packages one by one
@@ -86,7 +96,7 @@ pub mod client {
 
                 let n = tls.read(&mut buf)?;
 
-                on_partial(&buf, &data);
+                // (on_partial)(&buf, &data);
 
                 if n == 0 {
                     break;
diff --git a/src/engines.rs b/src/engines.rs
new file mode 100644
index 0000000..d55bb15
--- /dev/null
+++ b/src/engines.rs
@@ -0,0 +1,2 @@
+pub mod duckduckgo;
+pub mod engine_base;
diff --git a/src/engines/duckduckgo.rs b/src/engines/duckduckgo.rs
new file mode 100644
index 0000000..8b30fe2
--- /dev/null
+++ b/src/engines/duckduckgo.rs
@@ -0,0 +1,90 @@
+// Search engine parser for DuckDuckGo
+pub mod duckduckgo {
+    // Results start at:
+    //     <div id="links" class="results">
+    // Example for a result:
+    //     <div class="result results_links results_links_deep web-result ">
+    //         <div class="links_main links_deep result__body">
+    //             <h2 class="result__title">
+    //                 <a
+    //                     rel="nofollow" class="result__a"
+    //                     href="https://www.speedtest.net/">
+    //                     Speedtest by Ookla - The Global Broadband Speed Test
+    //                 </a>
+    //             </h2>
+    //             <div class="result__extras">
+    //                 <div class="result__extras__url">
+    //                     <span class="result__icon">
+    //                       <a rel="nofollow" href="https://www.speedtest.net/">
+    //                         <img class="result__icon__img" width="16" height="16" alt=""
+    //                           src="//external-content.duckduckgo.com/ip3/www.speedtest.net.ico" name="i15" />
+    //                       </a>
+    //                   </span>
+    //                     <a class="result__url" href="https://www.speedtest.net/">
+    //                         www.speedtest.net
+    //                     </a>
+    //                 </div>
+    //             </div>
+    //             <a
+    //                 class="result__snippet"
+    //                 href="https://www.speedtest.net/">
+    //                     Use Speedtest on all your devices with our free desktop and mobile apps.
+    //             </a>
+    //             <div class="clear"></div>
+    //         </div>
+    //     </div>
+    use lazy_static::lazy_static;
+    use regex::Regex;
+
+    use crate::engines::engine_base::engine_base::{EngineBase, SearchResult};
+
+    lazy_static! {
+        static ref RESULTS_START: Regex = Regex::new(r#"id=\"links\""#).unwrap();
+        static ref SINGLE_RESULT: Regex = Regex::new(r#"<div class="result.*?<a.*?href="(?<url>.*?)".*?>(?<title>.*?)<\/a>.*?class="result__snippet".*?>(?<description>.*?)<\/a>.*?class="clear".*?<\/div>( <\/div>){2}"#).unwrap();
+        static ref STRIP: Regex = Regex::new(r"\s+").unwrap();
+    }
+
+    pub struct DuckDuckGo {
+        pub search_results: Vec<SearchResult>,
+        results_started: bool,
+        previous_block: String,
+    }
+
+    impl EngineBase for DuckDuckGo {
+        fn get_search_results(&self) -> &Vec<SearchResult> {
+            &self.search_results
+        }
+
+        fn parse_packet<'a>(&mut self, packet: impl Iterator<Item = &'a u8>) {
+            let bytes: Vec<u8> = packet.map(|bit| *bit).collect();
+            let raw_text = String::from_utf8_lossy(&bytes);
+            let text = STRIP.replace_all(&raw_text, " ");
+
+            if self.results_started {
+                self.previous_block.push_str(&text);
+
+                match SINGLE_RESULT.captures(&self.previous_block.to_owned()) {
+                    Some(captures) => {
+                        self.previous_block.clear();
+                        println!("{}", &captures.name("title").unwrap().as_str());
+                        println!("{}", &captures.name("description").unwrap().as_str());
+                        println!("{}", &captures.name("url").unwrap().as_str());
+                    }
+                    None => {}
+                }
+            } else if RESULTS_START.is_match(&text) {
+                self.results_started = true;
+            }
+        }
+    }
+
+    impl DuckDuckGo {
+        pub fn new() -> Self {
+            Self {
+                search_results: Vec::new(),
+                results_started: false,
+                previous_block: String::new(),
+            }
+        }
+    }
+}
diff --git a/src/engines/engine_base.rs b/src/engines/engine_base.rs
new file mode 100644
index 0000000..2389879
--- /dev/null
+++ b/src/engines/engine_base.rs
@@ -0,0 +1,13 @@
+pub mod engine_base {
+    pub struct SearchResult {
+        pub title: String,
+        pub url: String,
+        pub description: String,
+    }
+
+    pub trait EngineBase {
+        fn get_search_results(&self) -> &Vec<SearchResult>;
+
+        fn parse_packet<'a>(&mut self, packet: impl Iterator<Item = &'a u8>);
+    }
+}
diff --git a/src/main.rs b/src/main.rs
index decea9d..b789839 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -1,15 +1,21 @@
+use std::{cmp::min, io::Read};
+
 use client::client::{Client, PACKET_SIZE};
+use engines::{duckduckgo::duckduckgo::DuckDuckGo, engine_base::engine_base::EngineBase};
 
 pub mod client;
-
-fn handle_response(packet: &[u8; PACKET_SIZE], bytes: &[u8]) {
-    println!("===========");
-    let response = String::from_utf8_lossy(packet);
-    dbg!(&packet.len());
-    println!("{}", response);
-}
+pub mod engines;
 
 fn main() {
-    let client = Client::new("https://www.google.com/");
-    client.request(&"GET", handle_response);
+    let mut ddg = DuckDuckGo::new();
+    let client = Client::new("https://html.duckduckgo.com/html/");
+
+    let packets = client.request(&"POST").unwrap();
+
+    for ii in (0..packets.len()).step_by(PACKET_SIZE) {
+        let end_range = min(packets.len(), ii + PACKET_SIZE);
+
+        let slice = &packets[ii..end_range];
+        &ddg.parse_packet(slice.iter());
+    }
 }