misc-mirrors/article_scraper
1
0
Fork 0
mirror of https://gitlab.com/news-flash/article_scraper.git synced 2025-07-08 16:40:00 +02:00
Code Releases Activity

improve title extraction

Browse source
This commit is contained in:
Jan Lukas Gernert 2023-02-20 02:32:58 +01:00
parent cce912c354
commit 98c06e11f4
7 changed files with 107 additions and 54 deletions
Download patch file Download diff file Expand all files Collapse all files

29
src/full_text_parser/readability/tests.rs
View file

@ -1,17 +1,30 @@
use libxml::tree::{Document, Node};
use libxml::{
tree::{Document, Node},
xpath::Context,
};
use reqwest::Url;
use crate::full_text_parser::config::ConfigEntry;
use crate::{
article::Article,
full_text_parser::{config::ConfigEntry, metadata},
};
async fn prepare(html: &str, url: &Url) -> Document {
async fn prepare(html: &str, url: &Url) -> (Document, Context, Article) {
let empty_config = ConfigEntry::default();
let document = crate::FullTextParser::parse_html(html, None, &empty_config).unwrap();
let xpath_ctx = crate::FullTextParser::get_xpath_ctx(&document).unwrap();
crate::FullTextParser::strip_junk(&xpath_ctx, None, &empty_config, url);
document
let article = Article {
title: None,
author: None,
url: url.clone(),
date: None,
thumbnail_url: None,
document: None,
};
(document, xpath_ctx, article)
}
#[tokio::test]
async fn test_1() {
let _ = env_logger::builder().is_test(true).try_init();
@ -19,9 +32,11 @@ async fn test_1() {
let html = std::fs::read_to_string(r"./resources/tests/readability-test-1.html")
.expect("Failed to read HTML");
let url = Url::parse("http://google.com").unwrap();
let document = prepare(&html, &url).await;
let (document, xpath_ctx, mut article) = prepare(&html, &url).await;
let mut root = Node::new("article", None, &document).unwrap();
super::Readability::extract_body(document, &mut root).unwrap();
metadata::extract(&xpath_ctx, None, None, &mut article);
super::Readability::extract_body(document, &mut root, article.title.as_deref()).unwrap();
}