This commit is contained in:
imnyang 2025-06-06 23:51:13 +09:00
commit e6fb9d65d6
3 changed files with 165 additions and 96 deletions

154
is-html-fast/Cargo.lock generated
View file

@ -99,31 +99,6 @@ version = "0.8.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
[[package]]
name = "crossbeam-deque"
version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
dependencies = [
"crossbeam-epoch",
"crossbeam-utils",
]
[[package]]
name = "crossbeam-epoch"
version = "0.9.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
dependencies = [
"crossbeam-utils",
]
[[package]]
name = "crossbeam-utils"
version = "0.8.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
[[package]]
name = "displaydoc"
version = "0.2.5"
@ -135,12 +110,6 @@ dependencies = [
"syn",
]
[[package]]
name = "either"
version = "1.15.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
[[package]]
name = "encoding_rs"
version = "0.8.35"
@ -202,6 +171,21 @@ dependencies = [
"percent-encoding",
]
[[package]]
name = "futures"
version = "0.3.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "65bc07b1a8bc7c85c5f2e110c476c7389b4554ba72af57d8445ea63a576b0876"
dependencies = [
"futures-channel",
"futures-core",
"futures-executor",
"futures-io",
"futures-sink",
"futures-task",
"futures-util",
]
[[package]]
name = "futures-channel"
version = "0.3.31"
@ -218,12 +202,34 @@ version = "0.3.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "05f29059c0c2090612e8d742178b0580d2dc940c837851ad723096f87af6663e"
[[package]]
name = "futures-executor"
version = "0.3.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e28d1d997f585e54aebc3f97d39e72338912123a67330d723fdbb564d646c9f"
dependencies = [
"futures-core",
"futures-task",
"futures-util",
]
[[package]]
name = "futures-io"
version = "0.3.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9e5c1b78ca4aae1ac06c48a526a655760685149f0d465d21f37abfe57ce075c6"
[[package]]
name = "futures-macro"
version = "0.3.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "futures-sink"
version = "0.3.31"
@ -242,8 +248,10 @@ version = "0.3.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9fa08315bb612088cc391249efdc3bc77536f16c91f6cf495e6fbe85b20a4a81"
dependencies = [
"futures-channel",
"futures-core",
"futures-io",
"futures-macro",
"futures-sink",
"futures-task",
"memchr",
@ -561,8 +569,9 @@ dependencies = [
name = "is-html-fast"
version = "0.1.0"
dependencies = [
"rayon",
"futures",
"reqwest",
"tokio",
]
[[package]]
@ -599,6 +608,16 @@ version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "241eaef5fd12c88705a01fc1066c48c4b36e0dd4377dcdc7ec3942cea7a69956"
[[package]]
name = "lock_api"
version = "0.4.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "07af8b9cdd281b7915f413fa73f29ebd5d55d0d3f0155584dade1ff18cea1b17"
dependencies = [
"autocfg",
"scopeguard",
]
[[package]]
name = "log"
version = "0.4.27"
@ -713,6 +732,29 @@ dependencies = [
"vcpkg",
]
[[package]]
name = "parking_lot"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f1bf18183cf54e8d6059647fc3063646a1801cf30896933ec2311622cc4b9a27"
dependencies = [
"lock_api",
"parking_lot_core",
]
[[package]]
name = "parking_lot_core"
version = "0.9.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e401f977ab385c9e4e3ab30627d6f26d00e2c73eef317493c4ec6d468726cf8"
dependencies = [
"cfg-if",
"libc",
"redox_syscall",
"smallvec",
"windows-targets",
]
[[package]]
name = "percent-encoding"
version = "2.3.1"
@ -771,23 +813,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5"
[[package]]
name = "rayon"
version = "1.10.0"
name = "redox_syscall"
version = "0.5.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa"
checksum = "928fca9cf2aa042393a8325b9ead81d2f0df4cb12e1e24cef072922ccd99c5af"
dependencies = [
"either",
"rayon-core",
]
[[package]]
name = "rayon-core"
version = "1.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2"
dependencies = [
"crossbeam-deque",
"crossbeam-utils",
"bitflags",
]
[[package]]
@ -921,6 +952,12 @@ dependencies = [
"windows-sys 0.59.0",
]
[[package]]
name = "scopeguard"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
[[package]]
name = "security-framework"
version = "2.11.1"
@ -994,6 +1031,15 @@ version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
[[package]]
name = "signal-hook-registry"
version = "1.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9203b8055f63a2a00e2f593bb0510367fe707d7ff1e5c872de2f537b339e5410"
dependencies = [
"libc",
]
[[package]]
name = "slab"
version = "0.4.9"
@ -1116,11 +1162,25 @@ dependencies = [
"bytes",
"libc",
"mio",
"parking_lot",
"pin-project-lite",
"signal-hook-registry",
"socket2",
"tokio-macros",
"windows-sys 0.52.0",
]
[[package]]
name = "tokio-macros"
version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6e06d43f1345a3bcd39f6a56dbb7dcab2ba47e68e8ac134855e7e2bdbaf8cab8"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "tokio-native-tls"
version = "0.3.1"

View file

@ -4,5 +4,6 @@ version = "0.1.0"
edition = "2024"
[dependencies]
rayon = "1.10.0"
futures = "0.3.31"
reqwest = { version = "0.12.19", features = ["blocking", "json"]}
tokio = { version = "1", features = ["full"] }

View file

@ -1,59 +1,67 @@
use std::fs::{File, OpenOptions};
use std::io::{BufRead, BufReader, Write};
use std::sync::{Arc, Mutex};
use std::fs::File;
use std::io::Write;
use std::time::Duration;
use rayon::prelude::*;
use reqwest::blocking::Client;
use reqwest::header::CONTENT_TYPE;
use futures::stream::{FuturesUnordered, StreamExt};
use reqwest::Client;
use tokio::fs;
use tokio::io::AsyncBufReadExt;
fn main() -> Result<(), Box<dyn std::error::Error>> {
let input_file = File::open("domains.txt")?;
let reader = BufReader::new(input_file);
let domains: Vec<String> = reader.lines().filter_map(Result::ok).collect();
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
let file = fs::File::open("domains.txt").await?;
let reader = tokio::io::BufReader::new(file);
let mut lines = reader.lines();
let output_file = OpenOptions::new()
.create(true)
.write(true)
.truncate(true)
.open("domains-filtered.txt")?;
let client = Client::builder()
.timeout(Duration::from_secs(5))
.build()?;
let output = Arc::new(Mutex::new(output_file));
let mut tasks = FuturesUnordered::new();
let client = Arc::new(
Client::builder()
.timeout(Duration::from_secs(5))
.build()?,
);
while let Some(line) = lines.next_line().await? {
let client = client.clone();
let domain = line.clone();
tasks.push(tokio::spawn(async move {
let url = format!("https://{}", domain);
let resp = client.get(&url).send().await;
domains.par_iter().for_each(|domain| {
let url = format!("https://{}", domain);
println!("Checking {}", url);
let response = client.get(&url).send();
match response {
Ok(resp) => {
if let Some(content_type) = resp.headers().get(CONTENT_TYPE) {
if let Ok(content_type_str) = content_type.to_str() {
if content_type_str.starts_with("text/html") {
if let Ok(mut file) = output.lock() {
writeln!(file, "{}", domain).ok();
match resp {
Ok(resp) => {
if let Some(content_type) = resp.headers().get(reqwest::header::CONTENT_TYPE) {
if let Ok(content_type_str) = content_type.to_str() {
if content_type_str.starts_with("text/html") {
println!("✅ HTML: {}", domain);
return Some(domain);
} else {
println!("❌ Not HTML: {} ({})", domain, content_type_str);
}
println!("✅ HTML: {}", domain);
} else {
println!("❌ Not HTML: {} ({})", domain, content_type_str);
}
} else {
println!("❌ No Content-Type: {}", domain);
}
} else {
println!("❌ No Content-Type: {}", domain);
}
Err(_) => {
println!("⚠️ Failed to connect: {}", domain);
}
}
Err(_) => {
println!("⚠️ Failed to connect: {}", domain);
}
None
}));
}
let mut results = Vec::new();
while let Some(res) = tasks.next().await {
if let Ok(Some(domain)) = res {
results.push(domain);
}
});
}
// 📝 한 번에 출력
let mut output = File::create("domains-filtered.txt")?;
for domain in results {
writeln!(output, "{}", domain)?;
}
Ok(())
}