Asynchronous web scraper engine written in rust.
Features:
* fully based on async-std
* derive macro based api
* struct based api
* stateful scraper (structs can hold state)
* ability to download files
* ability to schedule navigation jobs in an async manner
```rust,no_run extern crate crabler;
use std::path::Path;
use crabler::*; use surf::Url;
struct Scraper {}
impl Scraper { async fn responsehandler(&self, response: Response) -> Result<()> { if response.url.endswith(".png") && response.status == 200 { println!("Finished downloading {} -> {:?}", response.url, response.download_destination); } Ok(()) }
async fn walk_handler(&self, mut response: Response, a: Element) -> Result<()> {
if let Some(href) = a.attr("href") {
// Create absolute URL
let url = Url::parse(&href)
.unwrap_or_else(|_| Url::parse(&response.url).unwrap().join(&href).unwrap());
// Attempt to download an image
if href.ends_with(".png") {
let image_name = url.path_segments().unwrap().last().unwrap();
let p = Path::new("/tmp").join(image_name);
let destination = p.to_string_lossy().to_string();
if !p.exists() {
println!("Downloading {}", destination);
// Schedule crawler to download file to some destination
// downloading will happen in the background, await here is just to wait for job queue
response.download_file(url.to_string(), destination).await?;
} else {
println!("Skipping existing file {}", destination);
}
} else {
// Or schedule crawler to navigate to a given url
response.navigate(url.to_string()).await?;
};
}
Ok(())
}
}
async fn main() -> Result<()> { let scraper = Scraper {};
// Run scraper starting from given url and using 20 worker threads
scraper.run(Opts::new().with_urls(vec!["https://www.rust-lang.org/"]).with_threads(20)).await
} ```