paperoni/src/main.rs

85 lines
2.9 KiB
Rust
Raw Normal View History

#[macro_use]
extern crate lazy_static;
2020-05-01 18:42:41 +01:00
use std::fs::File;
use async_std::task;
2020-05-02 17:25:31 +01:00
use epub_builder::{EpubBuilder, EpubContent, ZipLibrary};
2020-05-02 16:33:45 +01:00
use url::Url;
2020-05-16 08:09:44 +01:00
mod cli;
mod extractor;
mod moz_readability;
use extractor::Extractor;
fn main() {
let app = cli::cli_init();
let arg_matches = app.get_matches();
if let Some(vals) = arg_matches.values_of("urls") {
let urls = vals.map(|val| val.to_string()).collect::<Vec<_>>();
download(urls);
2020-05-16 08:09:44 +01:00
}
}
type HTMLResource = (String, String);
async fn fetch_url(url: &str) -> HTMLResource {
2020-05-16 08:09:44 +01:00
let client = surf::Client::new();
println!("Fetching...");
// TODO: Add middleware for following redirects
(
url.to_string(),
client
.get(url)
.recv_string()
.await
.expect("Unable to fetch URL"),
)
2020-05-16 08:09:44 +01:00
}
fn download(urls: Vec<String>) {
let mut async_url_tasks = Vec::with_capacity(urls.len());
for url in urls {
async_url_tasks.push(task::spawn(async move { fetch_url(&url).await }));
}
task::block_on(async {
for url_task in async_url_tasks {
let (url, html) = url_task.await;
println!("Extracting");
let mut extractor = Extractor::from_html(&html);
extractor.extract_content(&url);
if extractor.article().is_some() {
extractor
.download_images(&Url::parse(&url).unwrap())
.await
.expect("Unable to download images");
let file_name = format!("{}.epub", extractor.metadata().title());
let mut out_file = File::create(&file_name).unwrap();
let mut html_buf = Vec::new();
2020-11-24 11:54:23 +00:00
extractor::serialize_to_xhtml(extractor.article().unwrap(), &mut html_buf)
.expect("Unable to serialize to xhtml");
let html_buf = std::str::from_utf8(&html_buf).unwrap();
let mut epub = EpubBuilder::new(ZipLibrary::new().unwrap()).unwrap();
if let Some(author) = extractor.metadata().byline() {
epub.metadata("author", author.replace("&", "&amp;"))
.unwrap();
}
epub.metadata("title", extractor.metadata().title().replace("&", "&amp;"))
.unwrap();
epub.add_content(EpubContent::new("code.xhtml", html_buf.as_bytes()))
.unwrap();
for img in extractor.img_urls {
let mut file_path = std::env::temp_dir();
file_path.push(&img.0);
let img_buf = File::open(&file_path).expect("Can't read file");
epub.add_resource(file_path.file_name().unwrap(), img_buf, img.1.unwrap())
.unwrap();
}
epub.generate(&mut out_file).unwrap();
println!("Created {:?}", file_name);
}
}
2020-05-02 17:25:31 +01:00
})
}