@@ 0,0 1,163 @@
++++
+title = "Rust script: search-torrent"
+
+[taxonomies]
+tags = ["rust", "script", "torren", "search"]
+categories = ["programming"]
+
+[extra]
+image = "bittorrent.jpg"
+image_alt = "BitTorrent Download"
+image_credit = "<a href=\"https://www.flickr.com/photos/95021520@N00\">nrkbeta</a> / CC BY-SA 2.0"
++++
+
+A simple HTML scraping script to query for magnet links on BitTorrent sites.
+<!-- more -->
+
+## Searching for BitTorrent content
+
+Before you can download something with [BitTorrent] you need to find the `.torrent` file or [magnet] link for the content.
+
+This searching is usually done with the help of one of the many [BitTorrent] hosting sites.
+The problem with these sites is that they often require [JavaScript] to be used and I would not trust them to be safe.
+
+## Rust command-line script
+
+I could find some [JavaScript] [scripts on GitHub](https://github.com/JimmyLaurent/torrent-search-api) that allow searching these sites, but they would be difficult to install and run as command-line programs.
+
+I have written a simple single file [Rust] script that can be run with the use of my [denim] scripting crate.
+
+
+```rust
+#!/usr/bin/env denim
+
+/* Cargo.toml
+[package]
+name = "search-torrent"
+version = "0.1.0"
+authors = ["Anonymous"]
+edition = "2018"
+
+[dependencies]
+cotton = "0.0.7"
+structopt = "0.3.2"
+reqwest = { version = "0.10.8", features = ["blocking"] }
+url = "2.1.1"
+scraper = "0.12.0"
+*/
+
+use cotton::prelude::*;
+use url::Url;
+use scraper::{Html, Selector};
+
+/// Searches for torrent magnet links given a search term.
+#[derive(Debug, StructOpt)]
+struct Cli {
+ #[structopt(flatten)]
+ logging: LoggingOpt,
+
+ #[structopt()]
+ query: String,
+}
+
+fn main() -> FinalResult {
+ let args = Cli::from_args();
+ init_logger(&args.logging, vec![module_path!()]);
+
+ // https://github.com/JimmyLaurent/torrent-search-api/blob/master/lib/providers/1337x.js
+ let base = Url::parse("https://www.1337x.to/")?;
+ let search = base.join("search/")?;
+
+ info!("Searching for {:?} on {}", args.query, base);
+
+ let item = Selector::parse("tbody > tr").unwrap();
+
+ let title = Selector::parse("a:nth-child(2)").unwrap();
+ let link = Selector::parse("a:nth-child(2)").unwrap();
+ let time = Selector::parse(".coll-date").unwrap();
+ let seeds = Selector::parse(".seeds").unwrap();
+ let peers = Selector::parse(".leeches").unwrap();
+ let size = Selector::parse(".size").unwrap();
+
+ for page in 1.. {
+ let resp = reqwest::blocking::get(search.join(&format!("{}/", &args.query))?.join(&format!("{}/", page))?)?;
+ let body = resp.text()?;
+ debug!("{}", body);
+
+ let html = Html::parse_document(&body);
+
+ let items = html.select(&item).collect_vec();
+ if items.is_empty() {
+ break;
+ }
+
+ for item in items {
+ debug!("{}", item.inner_html());
+ let link = item.select(&link).next().ok_or("no link found")?.value().attr("href").ok_or("no href found")?;
+ let title = item.select(&title).next().ok_or("no title found")?.inner_html();
+ let time = item.select(&time).next().ok_or("no time found")?.inner_html();
+ let seeds = item.select(&seeds).next().ok_or("no seeds found")?.inner_html();
+ let peers = item.select(&peers).next().ok_or("no peers found")?.inner_html();
+ let size = item.select(&size).next().ok_or("no size found")?.inner_html();
+ let size = size.splitn(2, "<").next().unwrap();
+
+ info!("[{}, {}, seeds: {}, peers: {}] {}", time, size, seeds, peers, title);
+
+ let desc = base.join(link)?;
+ let resp = reqwest::blocking::get(desc)?;
+ let body = resp.text()?;
+ let html = Html::parse_document(&body);
+
+ let links = Selector::parse("a").unwrap();
+ let magnets = html
+ .select(&links)
+ .filter_map(|a| a.value().attr("href"))
+ .filter(|href| href.starts_with("magnet:"))
+ .sorted()
+ .dedup();
+
+ for magnet in magnets {
+ println!("{}", magnet);
+ }
+ }
+ }
+
+ Ok(())
+}
+```
+
+# Installation and usage
+
+Install [denim] from cargo:
+
+```
+cargo install denim
+```
+
+Copy the content of the script to file named `search-torrent` and make it executable:
+
+```
+vim search-torrent
+chmod +x search-torrent
+```
+
+Now you can run the script as-is, but if you want to see the build progress you can run it via [denim] with:
+
+```
+denim exec search-torrent -- -h
+```
+
+Once the build is complete you can perform your searches:
+
+
+```
+./search-torrent -v "Debian"
+```
+
+You should see a list of Debian ISO files along with their [magnet] links.
+
+[BitTorrent]: https://en.wikipedia.org/wiki/BitTorrent
+[magnet]: https://en.wikipedia.org/wiki/Magnet_URI_scheme
+[JavaScript]: https://en.wikipedia.org/wiki/JavaScript
+[Rust]: https://www.rust-lang.org/
+[denim]: https://crates.io/crates/denim
