Anthony/readlater
1
0
Fork 0
mirror of https://github.com/Tony0410/readlater.git synced 2026-05-24 22:01:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add article publish date to list and reader views

Browse Source 
Extract publication dates from HTML meta tags when saving articles
and display them prominently in the article list and reader header.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Gemini Agent
2026-01-24 06:33:16 +00:00
parent 8151705b17
commit 96ece66204
12 changed files with 662 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
src/lib/utils/extract.ts
View File

@@ -33,6 +33,7 @@ export interface ExtractedArticle {
textContent: string;
leadImage: string | null;
wordCount: number;
publishedAt: Date | null;
}
export async function extractArticle(url: string): Promise<ExtractedArticle> {
@@ -86,6 +87,34 @@ export async function extractArticle(url: string): Promise<ExtractedArticle> {
leadImage = ogImage.getAttribute("content");
}
// Try to find publish date from various meta tags
let publishedAt: Date | null = null;
const dateSelectors = [
'meta[property="article:published_time"]',
'meta[name="article:published_time"]',
'meta[property="og:published_time"]',
'meta[name="pubdate"]',
'meta[name="publishdate"]',
'meta[name="date"]',
'meta[itemprop="datePublished"]',
'time[datetime]',
'time[pubdate]',
];
for (const selector of dateSelectors) {
const el = document.querySelector(selector);
if (el) {
const dateStr = el.getAttribute("content") || el.getAttribute("datetime");
if (dateStr) {
const parsed = new Date(dateStr);
if (!isNaN(parsed.getTime())) {
publishedAt = parsed;
break;
}
}
}
}
const textContent = article.textContent || "";
const content = article.content || "";
@@ -101,6 +130,7 @@ export async function extractArticle(url: string): Promise<ExtractedArticle> {
textContent,
leadImage,
wordCount,
publishedAt,
};
}
@@ -132,6 +162,34 @@ export async function extractFromHtml(
leadImage = ogImage.getAttribute("content");
}
// Try to find publish date from various meta tags
let publishedAt: Date | null = null;
const dateSelectors = [
'meta[property="article:published_time"]',
'meta[name="article:published_time"]',
'meta[property="og:published_time"]',
'meta[name="pubdate"]',
'meta[name="publishdate"]',
'meta[name="date"]',
'meta[itemprop="datePublished"]',
'time[datetime]',
'time[pubdate]',
];
for (const selector of dateSelectors) {
const el = document.querySelector(selector);
if (el) {
const dateStr = el.getAttribute("content") || el.getAttribute("datetime");
if (dateStr) {
const parsed = new Date(dateStr);
if (!isNaN(parsed.getTime())) {
publishedAt = parsed;
break;
}
}
}
}
const textContent = article.textContent || "";
const content = article.content || "";
@@ -147,5 +205,6 @@ export async function extractFromHtml(
textContent,
leadImage,
wordCount,
publishedAt,
};
}