magpie-html 0.1.3 → 0.1.5

package/README.md

@@ -7,11 +7,16 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](https://opensource.org/licenses/MIT)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.7-blue?style=flat-square&logo=typescript)](https://www.typescriptlang.org/)
 [![Node.js](https://img.shields.io/badge/Node.js-%3E%3D18-green?style=flat-square&logo=node.js)](https://nodejs.org/)
+[![Live Demo](https://img.shields.io/badge/Live_Demo-CrispRead-eb6864?style=flat-square&logo=rss&logoColor=white)](https://crispread.com)
 
 **Modern web scraping for when you need the good parts, not the markup soup.** Extracts clean article content, parses feeds (RSS, Atom, JSON), and gathers metadata from any page. Handles broken encodings, malformed feeds, and the chaos of real-world HTML. TypeScript-native, works everywhere. Named after the bird known for collecting valuable things... you get the idea.
 
 <div align="center">
   <img src="https://raw.githubusercontent.com/Anonyfox/magpie-html/main/assets/magpie-html-logo.png" alt="Magpie HTML Logo" width="300">
+
+<br><br>
+<strong>Production-ready</strong> · Powers <a href="https://crispread.com">CrispRead</a>, a trilingual news aggregator processing thousands of articles daily.
+
 </div>
 
 ## Features
@@ -454,6 +459,6 @@ If this package helps your project, consider sponsoring its maintenance:
 
 ---
 
-**[Anonyfox](https://anonyfox.com) • [MIT License](LICENSE)**
+**[Anonyfox](https://anonyfox.com) • [API Docs](https://anonyfox.github.io/magpie-html) • [MIT License](LICENSE)**
 
 </div>

package/dist/index.cjs

@@ -838,6 +838,32 @@ function parseAtomDate(dateString) {
 }
 
 // src/feed/atom/extract-entry.ts
+function extractAtomDate(element) {
+  let dateText = element.querySelector("updated")?.textContent;
+  if (dateText) {
+    const parsed = parseAtomDate(dateText);
+    if (parsed) return parsed;
+  }
+  dateText = element.querySelector("modified")?.textContent;
+  if (dateText) {
+    const parsed = parseAtomDate(dateText);
+    if (parsed) return parsed;
+  }
+  dateText = element.querySelector("issued")?.textContent;
+  if (dateText) {
+    const parsed = parseAtomDate(dateText);
+    if (parsed) return parsed;
+  }
+  const dcDateElements = element.children.filter((child) => child.tagName === "dc:date");
+  if (dcDateElements.length > 0) {
+    dateText = dcDateElements[0].textContent;
+    if (dateText) {
+      const parsed = parseAtomDate(dateText);
+      if (parsed) return parsed;
+    }
+  }
+  return null;
+}
 function extractPerson(element) {
   const name = element.querySelector("name")?.textContent;
   if (!name) {
@@ -980,13 +1006,11 @@ function extractEntry(entryElement) {
   if (!title) {
     throw new Error("Invalid Atom entry: missing required <title> element");
   }
-  const updatedRaw = entryElement.querySelector("updated")?.textContent;
-  if (!updatedRaw) {
-    throw new Error("Invalid Atom entry: missing required <updated> element");
-  }
-  const updated = parseAtomDate(updatedRaw);
+  const updated = extractAtomDate(entryElement);
   if (!updated) {
-    throw new Error("Invalid Atom entry: invalid <updated> date");
+    throw new Error(
+      "Invalid Atom entry: missing or invalid date (tried <updated>, <modified>, <issued>, <dc:date>)"
+    );
   }
   const entry = {
     id: cleanText(id),
@@ -1236,6 +1260,32 @@ function parseXML(xml) {
 }
 
 // src/feed/atom/extract-feed.ts
+function extractAtomDate2(element) {
+  let dateText = element.querySelector("updated")?.textContent;
+  if (dateText) {
+    const parsed = parseAtomDate(dateText);
+    if (parsed) return parsed;
+  }
+  dateText = element.querySelector("modified")?.textContent;
+  if (dateText) {
+    const parsed = parseAtomDate(dateText);
+    if (parsed) return parsed;
+  }
+  dateText = element.querySelector("issued")?.textContent;
+  if (dateText) {
+    const parsed = parseAtomDate(dateText);
+    if (parsed) return parsed;
+  }
+  const dcDateElements = element.children.filter((child) => child.tagName === "dc:date");
+  if (dcDateElements.length > 0) {
+    dateText = dcDateElements[0].textContent;
+    if (dateText) {
+      const parsed = parseAtomDate(dateText);
+      if (parsed) return parsed;
+    }
+  }
+  return null;
+}
 function extractPerson2(element) {
   const name = element.querySelector("name")?.textContent;
   if (!name) {
@@ -1383,13 +1433,11 @@ function extractFeed(xml) {
   if (!title) {
     throw new Error("Invalid Atom feed: missing required <title> element");
   }
-  const updatedRaw = feed.querySelector("updated")?.textContent;
-  if (!updatedRaw) {
-    throw new Error("Invalid Atom feed: missing required <updated> element");
-  }
-  const updated = parseAtomDate(updatedRaw);
+  const updated = extractAtomDate2(feed);
   if (!updated) {
-    throw new Error("Invalid Atom feed: invalid <updated> date");
+    throw new Error(
+      "Invalid Atom feed: missing or invalid date (tried <updated>, <modified>, <issued>, <dc:date>)"
+    );
   }
   const result = {
     id: cleanText(id),
@@ -2451,13 +2499,12 @@ async function pluck(input, init) {
   const startTime = Date.now();
   const options = normalizeOptions2(init);
   const originalUrl = typeof input === "string" || input instanceof URL ? String(input) : input.url;
-  const abortController = new AbortController();
-  const timeoutId = setTimeout(() => abortController.abort(), options.timeout);
+  const signal = AbortSignal.timeout(options.timeout);
   try {
     const { response, redirectChain, redirectDuration } = await followRedirects(
       input,
       options,
-      abortController.signal
+      signal
     );
     const finalUrl = response.url;
     if (options.throwOnHttpError && !response.ok) {
@@ -2494,15 +2541,13 @@ async function pluck(input, init) {
     if (error instanceof PluckTimeoutError || error instanceof PluckNetworkError) {
       throw error;
     }
-    if (error.name === "AbortError") {
+    if (error.name === "TimeoutError") {
       throw new PluckTimeoutError(`Request timeout after ${options.timeout}ms`, options.timeout);
     }
     if (error instanceof TypeError) {
       throw new PluckNetworkError(`Network error: ${error.message}`, error);
     }
     throw error;
-  } finally {
-    clearTimeout(timeoutId);
   }
 }
 function normalizeOptions2(init) {