commit
c82071a871
6 changed files with 98 additions and 60 deletions
2
Cargo.lock
generated
2
Cargo.lock
generated
|
@ -1242,7 +1242,7 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "paperoni"
|
||||
version = "0.2.1-alpha1"
|
||||
version = "0.2.2-alpha1"
|
||||
dependencies = [
|
||||
"async-std",
|
||||
"clap",
|
||||
|
|
|
@ -3,7 +3,7 @@ description = "A web article downloader"
|
|||
homepage = "https://github.com/hipstermojo/paperoni"
|
||||
repository = "https://github.com/hipstermojo/paperoni"
|
||||
name = "paperoni"
|
||||
version = "0.2.1-alpha1"
|
||||
version = "0.2.2-alpha1"
|
||||
authors = ["Kenneth Gitere <gitere81@gmail.com>"]
|
||||
edition = "2018"
|
||||
license = "MIT"
|
||||
|
@ -21,4 +21,4 @@ lazy_static = "1.4.0"
|
|||
md5 = "0.7.0"
|
||||
regex = "1.4.2"
|
||||
surf = "2.1.0"
|
||||
url = "2.2.0"
|
||||
url = "2.2.0"
|
||||
|
|
|
@ -6,7 +6,7 @@ pub fn cli_init() -> App<'static, 'static> {
|
|||
AppSettings::ArgRequiredElseHelp,
|
||||
AppSettings::UnifiedHelpMessage,
|
||||
])
|
||||
.version("0.2.1-alpha1")
|
||||
.version("0.2.2-alpha1")
|
||||
.about(
|
||||
"
|
||||
Paperoni is an article downloader.
|
||||
|
|
|
@ -68,7 +68,9 @@ impl Extractor {
|
|||
pub async fn download_images(&mut self, article_origin: &Url) -> async_std::io::Result<()> {
|
||||
let mut async_download_tasks = Vec::with_capacity(self.img_urls.len());
|
||||
self.extract_img_urls();
|
||||
println!("Downloading images...");
|
||||
if self.img_urls.len() > 0 {
|
||||
println!("Downloading images...");
|
||||
}
|
||||
for img_url in &self.img_urls {
|
||||
let img_url = img_url.0.clone();
|
||||
let abs_url = get_absolute_url(&img_url, article_origin);
|
||||
|
@ -129,6 +131,9 @@ impl Extractor {
|
|||
.expect("Image node does not exist");
|
||||
let mut img_node = img_ref.attributes.borrow_mut();
|
||||
*img_node.get_mut("src").unwrap() = img_path.clone();
|
||||
// srcset is removed because readers such as Foliate then fail to display
|
||||
// the image already downloaded and stored in src
|
||||
img_node.remove("srcset");
|
||||
self.img_urls.push((img_path, img_mime));
|
||||
}
|
||||
Ok(())
|
||||
|
|
138
src/main.rs
138
src/main.rs
|
@ -23,70 +23,106 @@ fn main() {
|
|||
|
||||
type HTMLResource = (String, String);
|
||||
|
||||
async fn fetch_url(url: &str) -> Result<HTMLResource, Box<dyn std::error::Error>> {
|
||||
async fn fetch_url(url: &str) -> Result<HTMLResource, Box<dyn std::error::Error + Send + Sync>> {
|
||||
let client = surf::Client::new();
|
||||
println!("Fetching...");
|
||||
let mut res = client
|
||||
.with(surf::middleware::Redirect::default())
|
||||
.get(url)
|
||||
.send()
|
||||
.await
|
||||
.expect(&format!("Unable to fetch {}", url));
|
||||
if res.status() == 200 {
|
||||
Ok((url.to_string(), res.body_string().await?))
|
||||
} else {
|
||||
Err("Request failed to return HTTP 200".into())
|
||||
|
||||
let mut redirect_count: u8 = 0;
|
||||
let base_url = Url::parse(&url)?;
|
||||
let mut url = base_url.clone();
|
||||
while redirect_count < 5 {
|
||||
redirect_count += 1;
|
||||
let req = surf::get(&url);
|
||||
let mut res = client.send(req).await?;
|
||||
if res.status().is_redirection() {
|
||||
if let Some(location) = res.header(surf::http::headers::LOCATION) {
|
||||
match Url::parse(location.last().as_str()) {
|
||||
Ok(valid_url) => url = valid_url,
|
||||
Err(e) => match e {
|
||||
url::ParseError::RelativeUrlWithoutBase => {
|
||||
url = base_url.join(location.last().as_str())?
|
||||
}
|
||||
e => return Err(e.into()),
|
||||
},
|
||||
};
|
||||
}
|
||||
} else if res.status().is_success() {
|
||||
if let Some(mime) = res.content_type() {
|
||||
if mime.essence() == "text/html" {
|
||||
return Ok((url.to_string(), res.body_string().await?));
|
||||
} else {
|
||||
return Err(format!(
|
||||
"Invalid HTTP response. Received {} instead of text/html",
|
||||
mime.essence()
|
||||
)
|
||||
.into());
|
||||
}
|
||||
} else {
|
||||
return Err("Unknown HTTP response".into());
|
||||
}
|
||||
} else {
|
||||
return Err(format!("Request failed: HTTP {}", res.status()).into());
|
||||
}
|
||||
}
|
||||
Err("Unable to fetch HTML".into())
|
||||
}
|
||||
|
||||
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.unwrap() }));
|
||||
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()
|
||||
.replace("/", " ")
|
||||
.replace("\\", " ")
|
||||
);
|
||||
let mut out_file = File::create(&file_name).unwrap();
|
||||
let mut html_buf = Vec::new();
|
||||
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("&", "&"))
|
||||
.unwrap();
|
||||
}
|
||||
epub.metadata("title", extractor.metadata().title().replace("&", "&"))
|
||||
.unwrap();
|
||||
epub.add_content(EpubContent::new("index.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);
|
||||
match url_task.await {
|
||||
Ok((url, html)) => {
|
||||
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()
|
||||
.replace("/", " ")
|
||||
.replace("\\", " ")
|
||||
);
|
||||
let mut out_file = File::create(&file_name).unwrap();
|
||||
let mut html_buf = Vec::new();
|
||||
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("&", "&"))
|
||||
.unwrap();
|
||||
}
|
||||
epub.metadata("title", extractor.metadata().title().replace("&", "&"))
|
||||
.unwrap();
|
||||
epub.add_content(EpubContent::new("index.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();
|
||||
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);
|
||||
}
|
||||
}
|
||||
epub.generate(&mut out_file).unwrap();
|
||||
println!("Created {:?}", file_name);
|
||||
Err(e) => println!("{}", e),
|
||||
}
|
||||
}
|
||||
})
|
||||
|
|
|
@ -193,10 +193,7 @@ impl Readability {
|
|||
.borrow_mut()
|
||||
.insert(attr_name, prev_value.value.clone());
|
||||
}
|
||||
// WARN: This assumes `next_element` returns an element node!!
|
||||
let inner_node_child =
|
||||
Self::next_element(inner_node_ref.first_child(), true);
|
||||
prev_elem.insert_after(inner_node_child.unwrap());
|
||||
prev_elem.insert_after(new_img.as_node().clone());
|
||||
prev_elem.detach();
|
||||
}
|
||||
}
|
||||
|
|
Reference in a new issue