rsshub/dist-lib/utils-BewxI9Mf.mjs

Make RSS Great Again!

import { t as ofetch_default } from "./ofetch-DKl_Ma9g.mjs";
import { t as parseDate } from "./parse-date-r5WDWHno.mjs";
import { t as cache_default } from "./cache-SV6W5EPy.mjs";
import { load } from "cheerio";

//#region lib/routes/dailypush/utils.ts
const BASE_URL = "https://www.dailypush.dev";
/**
* Extract author from article element
*/
function extractAuthor(article) {
	const sourceSpan = article.find("span.text-xs.font-medium.uppercase").first();
	if (sourceSpan.length > 0) return sourceSpan.text().trim();
	const authorMatch = article.find(".flex.items-center.gap-3").first().text().match(/^([^•]+?)(?:\s*•)/);
	if (authorMatch && !/\d{4}/.test(authorMatch[1])) return authorMatch[1].trim();
}
/**
* Extract categories/tags from article element
*/
function extractCategories(article, $) {
	return article.find("a[href^=\"/\"]").toArray().map((tagEl) => {
		const tagElement = $(tagEl);
		const tagHref = tagElement.attr("href");
		const tagText = tagElement.text().trim();
		if (tagHref && tagText && !tagHref.includes("article/") && !tagHref.includes("Summary") && tagText.length < 50 && !/^(Summary|stats|About|Tags|Toggle|Trending|Latest|Previous|Next)$/i.test(tagText)) return tagText;
		return null;
	}).filter((tagText) => tagText !== null);
}
/**
* Extract publication date from article element
*/
function extractPubDate(article) {
	const authorAndDate = article.find(".flex.items-center.justify-between.gap-4.flex-wrap").first().find(".flex.items-center.gap-3.text-xs").first();
	if (authorAndDate.length === 0) return;
	const spans = authorAndDate.find("span");
	let dateText;
	if (spans.length === 3) dateText = spans.eq(2).text().trim();
	else if (spans.length === 1) dateText = spans.eq(0).text().trim();
	if (!dateText) return;
	try {
		return parseDate(dateText);
	} catch {
		const match = dateText.match(/((?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s+\d+,\s+\d{4})/i);
		if (match && match[1]) try {
			return parseDate(match[1]);
		} catch {}
	}
}
/**
* Parse a single article element into an ArticleItem
*/
function parseArticle(article, $, baseUrl) {
	const titleLink = article.find("h2 a[href^=\"http\"]").first();
	if (titleLink.length === 0) return null;
	const title = titleLink.text().trim();
	const link = titleLink.attr("href");
	if (!title || !link || link.includes("dailypush.dev")) return null;
	const author = extractAuthor(article);
	const description = article.find("p.text-sm.text-muted-foreground").first().text().trim() || void 0;
	const categories = extractCategories(article, $);
	const summaryLink = article.find(".flex.items-center.justify-between.gap-4.flex-wrap").first().find("a[href*=\"/article/\"]").first().attr("href");
	const dailyPushUrl = summaryLink ? `${baseUrl}${summaryLink}` : void 0;
	const pubDate = extractPubDate(article);
	return {
		title,
		link,
		author: author || void 0,
		pubDate,
		category: categories.length > 0 ? categories : void 0,
		description,
		articleUrl: link,
		dailyPushUrl
	};
}
/**
* Parse all articles from the page
*/
function parseArticles($, baseUrl) {
	return $("article").toArray().map((articleEl) => {
		return parseArticle($(articleEl), $, baseUrl);
	}).filter((parsed) => parsed !== null);
}
/**
* Enhance items with full summaries from dailypush article pages
*/
async function enhanceItemsWithSummaries(items) {
	const itemsWithUrl = items.filter((item) => item.dailyPushUrl !== void 0);
	const itemsWithoutUrl = items.filter((item) => item.dailyPushUrl === void 0);
	return [...await Promise.all(itemsWithUrl.map((item) => cache_default.tryGet(item.dailyPushUrl, async () => {
		try {
			const summary = load(await ofetch_default(item.dailyPushUrl))("p.font-ibm-plex-sans.leading-relaxed").first();
			if (summary.length > 0 && summary.text().trim()) item.description = summary.text().trim();
		} catch {}
		return item;
	}))), ...itemsWithoutUrl];
}

//#endregion
export { enhanceItemsWithSummaries as n, parseArticles as r, BASE_URL as t };