kemitix/paperoni
Archived
1
0
Fork 0
Code Issues 4 Pull requests 3 Projects Releases Packages Wiki Activity

Add template for epub output

Browse source 
Change output format to name file with the title name
Add getters in MetaData
This commit is contained in:
Kenneth Gitere 2020-10-22 13:55:02 +03:00
parent 703de7e3bf
commit db11e78d8c
3 changed files with 42 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
src/extractor.rs
View file

@ -1,14 +1,15 @@
use async_std::fs::File;
use async_std::io::prelude::*;
use async_std::task;
use kuchiki::NodeRef;
use kuchiki::{traits::*, NodeRef};
use url::Url;
use super::moz_readability::Readability;
use crate::moz_readability::{MetaData, Readability};
pub type ResourceInfo = (String, Option<String>);
pub struct Extractor {
article: Option<NodeRef>,
pub img_urls: Vec<ResourceInfo>,
readability: Readability,
}
@ -17,6 +18,7 @@ impl Extractor {
/// Create a new instance of an HTML extractor given an HTML string
pub fn from_html(html_str: &str) -> Self {
Extractor {
article: None,
img_urls: Vec::new(),
readability: Readability::new(html_str),
}
@ -26,6 +28,20 @@ impl Extractor {
/// the source of the content
pub fn extract_content(&mut self, url: &str) {
self.readability.parse(url);
if let Some(article_node_ref) = &self.readability.article_node {
let template = r#"
<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
<head>
</head>
<body>
</body>
</html>
"#;
let doc = kuchiki::parse_html().one(template);
let body = doc.select_first("body").unwrap();
body.as_node().append(article_node_ref.clone());
self.article = Some(doc);
}
}
/// Traverses the DOM tree of the content and retrieves the IMG URLs
@ -94,7 +110,11 @@ impl Extractor {
}
pub fn article(&self) -> Option<&NodeRef> {
self.readability.article_node.as_ref()
self.article.as_ref()
}
pub fn metadata(&self) -> &MetaData {
&self.readability.metadata
}
}

8
src/main.rs
View file

@ -46,7 +46,8 @@ fn download(url: String) {
.download_images(&Url::parse(&url).unwrap())
.await
.expect("Unable to download images");
let mut out_file = File::create("out.epub").unwrap();
let mut out_file =
File::create(format!("{}.epub", extractor.metadata().title())).unwrap();
let mut html_buf = Vec::new();
extractor
.article()
@ -55,6 +56,11 @@ fn download(url: String) {
.expect("Unable to serialize");
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).unwrap();
}
epub.metadata("title", extractor.metadata().title())
.unwrap();
epub.add_content(EpubContent::new("code.xhtml", html_buf.as_bytes()))
.unwrap();
for img in extractor.img_urls {

14
src/moz_readability/mod.rs
View file

@ -55,6 +55,7 @@ pub struct Readability {
pub article_node: Option<NodeRef>,
article_dir: Option<String>,
flags: u32,
pub metadata: MetaData,
}
#[derive(Debug, PartialEq)]
@ -72,14 +73,15 @@ impl Readability {
article_node: None,
article_dir: None,
flags: FLAG_STRIP_UNLIKELYS | FLAG_WEIGHT_CLASSES | FLAG_CLEAN_CONDITIONALLY,
metadata: MetaData::new(),
}
}
pub fn parse(&mut self, url: &str) {
self.unwrap_no_script_tags();
self.remove_scripts();
self.prep_document();
let meta_data = self.get_article_metadata();
self.article_title = meta_data.title.clone();
self.metadata = self.get_article_metadata();
self.article_title = self.metadata.title.clone();
self.grab_article();
self.post_process_content(url);
}
@ -2077,6 +2079,14 @@ impl MetaData {
title: "".into(),
}
}
pub fn title(&self) -> &str {
&self.title
}
pub fn byline(&self) -> Option<&String> {
self.byline.as_ref()
}
}
#[cfg(test)]