decant-core 1.10.1 → 1.11.0

package/README.md

@@ -4,7 +4,7 @@
 
 [![npm version](https://img.shields.io/npm/v/decant-core?logo=npm&logoColor=white&label=npm&color=cb3837)](https://www.npmjs.com/package/decant-core)
 [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL--3.0-red.svg)](LICENSE)
-[![GitHub](https://img.shields.io/github/stars/Covai-Labs/decant-core?logo=github&logoColor=white&color=yellow&label=Stars)](https://github.com/Covai-Labs/decant-core/stargazers)
+[![GitHub](https://img.shields.io/github/stars/Covai-Labs/decant?logo=github&logoColor=white&color=yellow&label=Stars)](https://github.com/Covai-Labs/decant/stargazers)
 
 Every AI chat exporter ends up solving the same problem: extracting conversations from ChatGPT, Claude, Gemini, Perplexity, DeepSeek and other constantly changing AI interfaces.
 
@@ -41,7 +41,7 @@ AI platforms don't expose stable public APIs for reading conversation history. N
 
 Maintaining that per-platform logic in every exporter is wasteful and fragile. `decant-core` centralizes it:
 
-- ✅ **18 AI chat platform parsers** with normalized output — you get structured messages, models, metadata and Markdown, not DOM soup.
+- ✅ **19 AI chat platform parsers** with normalized output — you get structured messages, models, metadata and Markdown, not DOM soup.
 - ✅ **Web article extraction** — Mozilla Readability, Defuddle, and Article-Extractor run in parallel and arbitrate by content-quality scoring.
 - ✅ **Detection utilities** — tell an "AI chat page" apart from a "regular web page" before you decide which parser to run.
 - ✅ **Math & Markdown handling** — LaTeX normalization plus GFM tables/code fencing that survive round-trips into Obsidian, Logseq and Notion.
@@ -117,34 +117,35 @@ import { normalizeLatexMath } from "decant-core";
 
 ## Supported Platforms
 
-18 AI chat platform parsers plus generic web article extraction:
-
-| Platform                            | Parser                    | Extraction strategy                        |
-| :---------------------------------- | :------------------------ | :----------------------------------------- |
-| **ChatGPT**                         | `ChatGPTParser`           | DOM + internal API                         |
-| **Claude**                          | `ClaudeParser`            | DOM + internal API + React fiber           |
-| **Google Gemini**                   | `GeminiParser`            | DOM + batchexecute RPC                     |
-| **Microsoft Copilot**               | `CopilotParser`           | DOM (multi-domain)                         |
-| **Perplexity**                      | `PerplexityParser`        | Internal API + DOM fallback                |
-| **DeepSeek**                        | `DeepSeekParser`          | DOM + internal API (`fragments[]`)         |
-| **Qwen**                            | `QwenParser`              | DOM                                        |
-| **Meta AI**                         | `MetaParser`              | Internal API (GraphQL) + DOM fallback      |
-| **Mistral / Le Chat**               | `MistralParser`           | DOM                                        |
-| **Proton Lumo**                     | `LumoParser`              | DOM (API is E2E-encrypted, not readable)   |
-| **Z.ai**                            | `ZAiParser`               | Internal API (chat + batch) + DOM fallback |
-| **Grok**                            | `GrokParser`              | Internal API (response-node + load) + DOM  |
-| **Google AI Studio**                | `GoogleAIStudioParser`    | DOM                                        |
-| **NotebookLM**                      | `NotebookLMParser`        | DOM                                        |
-| **Google Search AI (AI Overviews)** | `GoogleSearchAIParser`    | DOM                                        |
-| **Gemini Cloud Assist**             | `GeminiCloudAssistParser` | DOM                                        |
-| **Joyland**                         | `JoylandParser`           | DOM                                        |
-| **Chub**                            | `ChubParser`              | DOM                                        |
-| **Generic Web Article**             | `ArticleParser`           | Readability + Defuddle + Article-Extractor |
+19 AI chat platform parsers plus generic web article extraction:
+
+| Platform                            | Parser                    | Extraction strategy                                   |
+| :---------------------------------- | :------------------------ | :---------------------------------------------------- |
+| **ChatGPT**                         | `ChatGPTParser`           | DOM + internal API                                    |
+| **Claude**                          | `ClaudeParser`            | DOM + internal API + React fiber                      |
+| **Google Gemini**                   | `GeminiParser`            | DOM + batchexecute RPC                                |
+| **Microsoft Copilot**               | `CopilotParser`           | DOM (multi-domain)                                    |
+| **Perplexity**                      | `PerplexityParser`        | Internal API + DOM fallback                           |
+| **DeepSeek**                        | `DeepSeekParser`          | DOM + internal API (`fragments[]`)                    |
+| **Qwen**                            | `QwenParser`              | DOM                                                   |
+| **Meta AI**                         | `MetaParser`              | Internal API (GraphQL) + DOM fallback                 |
+| **Mistral / Le Chat**               | `MistralParser`           | DOM                                                   |
+| **Proton Lumo**                     | `LumoParser`              | DOM (API is E2E-encrypted, not readable)              |
+| **Z.ai**                            | `ZAiParser`               | Internal API (chat + batch) + DOM fallback            |
+| **Grok**                            | `GrokParser`              | Internal API (response-node + load) + DOM             |
+| **Google AI Studio**                | `GoogleAIStudioParser`    | DOM                                                   |
+| **NotebookLM**                      | `NotebookLMParser`        | DOM                                                   |
+| **Google Search AI (AI Overviews)** | `GoogleSearchAIParser`    | DOM                                                   |
+| **Gemini Cloud Assist**             | `GeminiCloudAssistParser` | DOM                                                   |
+| **Joyland**                         | `JoylandParser`           | DOM                                                   |
+| **Chub**                            | `ChubParser`              | DOM                                                   |
+| **Duck.ai (DuckDuckGo AI)**         | `DuckAIParser`            | DOM (client-side privacy, no server chat history API) |
+| **Generic Web Article**             | `ArticleParser`           | Readability + Defuddle + Article-Extractor            |
 
 All parsers extend the base [`ChatParser`](ai/base.js) interface — a consistent `isAvailable(url)` +
 normalized `parse()` contract. For the full extraction-strategy breakdown and maintenance model, see
 [SUPPORTED_PLATFORMS.md](SUPPORTED_PLATFORMS.md), also published as the
-[platform matrix](https://covai-labs.github.io/decant-core/platforms/) on the developer docs site.
+[platform matrix](https://covai-labs.github.io/decant/platforms/) on the developer docs site.
 
 ---
 
@@ -163,7 +164,7 @@ Sample test fixtures located in [`tests/fixtures/`](tests/fixtures/) consist of
 ## Used by
 
 - [AI Chat Exporter](https://github.com/Covai-Labs/ai-chat-exporter) — export, archive and transfer AI conversations between platforms.
-- [Decant](https://github.com/Covai-Labs/decant) — the distraction-free web clipper and research batcher.
+- [Decant](https://github.com/Covai-Labs/decant-browser-extension) — the distraction-free web clipper and research batcher.
 
 These products are demonstrations of the library, not its purpose. Yours can be next — see [CONTRIBUTING.md](CONTRIBUTING.md).
 

package/ai/duck_ai.js

@@ -0,0 +1,209 @@
+import { ChatParser } from "./base.js";
+import { convertToMarkdown } from "../utils/html-to-markdown.js";
+
+export function isDuckAiUrl(url) {
+  if (!url || typeof url !== "string") return false;
+  try {
+    const parsed = new URL(url);
+    const host = parsed.hostname.toLowerCase();
+    if (host === "duck.ai" || host.endsWith(".duck.ai")) {
+      return true;
+    }
+    if (host === "duckduckgo.com" || host.endsWith(".duckduckgo.com")) {
+      if (parsed.pathname === "/chat" || parsed.pathname.startsWith("/chat/")) {
+        return true;
+      }
+      return parsed.searchParams.get("ia") === "chat";
+    }
+  } catch {
+    return false;
+  }
+  return false;
+}
+
+export class DuckAIParser extends ChatParser {
+  name = "Duck.ai";
+
+  isAvailable(url) {
+    return isDuckAiUrl(url);
+  }
+
+  async parse() {
+    // 1. Extract Title
+    let title = "";
+    if (typeof document !== "undefined" && document.title) {
+      title = document.title
+        .replace(/\s*-\s*DuckDuckGo.*$/i, "")
+        .replace(/\s*-\s*Duck\.ai.*$/i, "")
+        .trim();
+      if (/^(?:duckduckgo\s*ai\s*chat|duck\.ai)$/i.test(title)) {
+        title = "";
+      }
+    }
+
+    if (!title && typeof document !== "undefined") {
+      const activeChat = document.querySelector(
+        '[data-testid="ChatsList"] [aria-current="page"], [data-testid="ChatsList"] button, [data-testid="ChatsList"] a',
+      );
+      if (activeChat && activeChat.textContent) {
+        title = activeChat.textContent.trim();
+      }
+    }
+
+    // 2. Extract Messages
+    const messages = [];
+    let latestModel = "";
+
+    const userElements =
+      typeof document !== "undefined"
+        ? Array.from(document.querySelectorAll('[data-testid="user-message"]'))
+        : [];
+
+    for (let i = 0; i < userElements.length; i++) {
+      const userEl = userElements[i];
+
+      // Process User Message
+      const userClone = userEl.cloneNode(true);
+      // Remove inline favicon images
+      userClone
+        .querySelectorAll(
+          'img[src*="duckduckgo.com/ip3/"], img[src*="favicons"]',
+        )
+        .forEach((img) => img.remove());
+      const userText = convertToMarkdown(userClone);
+      if (userText.trim()) {
+        messages.push({
+          role: "User",
+          content: userText.trim(),
+        });
+      }
+
+      // Process Assistant Message
+      let assistantEl = userEl.nextElementSibling;
+      if (
+        !assistantEl ||
+        assistantEl.getAttribute("data-testid") === "user-message"
+      ) {
+        // Fallback: look within parent turn container for assistant message element
+        assistantEl =
+          userEl.parentElement?.querySelector('[id*="-assistant-message-"]') ||
+          null;
+      }
+
+      if (assistantEl) {
+        // Extract Model Badge if present
+        let turnModel = "";
+        const heading = assistantEl.querySelector(
+          '[id^="heading-"][id*="-assistant-message-"], [id*="-assistant-message-"] h2, [id*="-assistant-message-"] h3',
+        );
+        if (heading && heading.textContent) {
+          turnModel = heading.textContent.replace(/^[^a-zA-Z0-9]+/, "").trim();
+          if (turnModel) {
+            latestModel = turnModel;
+          }
+        }
+
+        const astClone = assistantEl.cloneNode(true);
+
+        // Remove header / heading
+        astClone
+          .querySelectorAll(
+            '[id^="heading-"], .OFnY5LgQty8A4PIj3XdY, button, [data-testid="feedback-prompt"]',
+          )
+          .forEach((el) => el.remove());
+
+        // Remove transient web search query box
+        astClone
+          .querySelectorAll('.f_6cBYM9KdwpDEKf3fGW, [class*="search"]')
+          .forEach((el) => el.remove());
+
+        // Remove actions / footer container
+        astClone
+          .querySelectorAll("._4aCfUrBe8vy05lxcMBX")
+          .forEach((el) => el.remove());
+
+        // Preprocess Streamdown code blocks into standard <pre><code class="language-xyz">...</code></pre>
+        astClone
+          .querySelectorAll('[data-streamdown="code-block"]')
+          .forEach((cb) => {
+            const header = cb.querySelector(
+              '[data-streamdown="code-block-header"]',
+            );
+            const lang =
+              header?.getAttribute("data-language") ||
+              header?.textContent?.trim().toLowerCase() ||
+              "";
+            const codeEl =
+              cb.querySelector('[data-streamdown="code-block-body"] code') ||
+              cb.querySelector("code");
+            const codeText = codeEl?.textContent || "";
+
+            const pre = astClone.ownerDocument.createElement("pre");
+            const code = astClone.ownerDocument.createElement("code");
+            if (lang) {
+              code.className = `language-${lang}`;
+            }
+            code.textContent = codeText;
+            pre.appendChild(code);
+            if (cb.parentNode) {
+              cb.parentNode.replaceChild(pre, cb);
+            }
+          });
+
+        // Clean up favicon images
+        astClone
+          .querySelectorAll(
+            'img[src*="duckduckgo.com/ip3/"], img[src*="favicons"]',
+          )
+          .forEach((img) => img.remove());
+
+        // Format Read More citation links: ensure space before domain name in citation text
+        astClone
+          .querySelectorAll(
+            "section h4 + div li a span > span, section ul li a span > span",
+          )
+          .forEach((domainSpan) => {
+            const domainText = domainSpan.textContent.trim();
+            if (domainText) {
+              domainSpan.textContent = ` (${domainText})`;
+            }
+          });
+
+        const astText = convertToMarkdown(astClone);
+        if (astText.trim()) {
+          const msg = {
+            role: "Duck.ai",
+            content: astText.trim(),
+          };
+          if (turnModel) {
+            msg.model = turnModel;
+          }
+          messages.push(msg);
+        }
+      }
+    }
+
+    if (!title && messages.length > 0) {
+      const firstUser = messages.find((m) => m.role === "User");
+      if (firstUser && firstUser.content) {
+        title = firstUser.content.slice(0, 60).trim();
+      }
+    }
+    title = title || "Duck.ai Conversation";
+
+    const currentUrl =
+      typeof window !== "undefined" && window.location
+        ? window.location.href || ""
+        : "";
+
+    const metadata = {
+      Source: "Duck.ai",
+      Date: new Date().toLocaleString(),
+      Link: currentUrl,
+      Method: "DOM",
+      ...(latestModel ? { Model: latestModel } : {}),
+    };
+
+    return { title, messages, url: currentUrl, metadata };
+  }
+}

package/ai/index.js

@@ -28,6 +28,7 @@ export { GeminiCloudAssistParser } from "./gemini_cloud_assist.js";
 export { JoylandParser } from "./joyland.js";
 export { ChubParser } from "./chub.js";
 export { GrokParser } from "./grok.js";
+export { DuckAIParser } from "./duck_ai.js";
 
 // Utilities
 export { convertToMarkdown, cleanMarkdown } from "../utils/html-to-markdown.js";

package/detection/detect-platform.js

@@ -17,6 +17,7 @@ import { GeminiCloudAssistParser } from "../ai/gemini_cloud_assist.js";
 import { JoylandParser } from "../ai/joyland.js";
 import { ChubParser } from "../ai/chub.js";
 import { GrokParser } from "../ai/grok.js";
+import { DuckAIParser } from "../ai/duck_ai.js";
 
 /**
  * Ordered list of parsers. First match wins.
@@ -32,6 +33,7 @@ export const parsers = [
   new QwenParser(),
   new MetaParser(),
   new MistralParser(),
+  new DuckAIParser(),
   new LumoParser(),
   new ZAiParser(),
   new GoogleAIStudioParser(),

package/detection/domains.js

@@ -1,3 +1,5 @@
+import { isDuckAiUrl } from "../ai/duck_ai.js";
+
 /**
  * AI chat platform domain definitions.
  * Centralised so detection logic and UI (e.g. Decant's tip banner) share the same list.
@@ -23,6 +25,7 @@ export const AI_CHAT_DOMAINS = [
   "chub.ai",
   "characterhub.org",
   "grok.com",
+  "duck.ai",
 ];
 
 /**
@@ -51,4 +54,8 @@ export const URL_PATTERNS = [
     test: (url) => url.includes("console.cloud.google.com/gemini"),
     platform: "gemini-cloud-assist",
   },
+  {
+    test: isDuckAiUrl,
+    platform: "duck-ai",
+  },
 ];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "decant-core",
-  "version": "1.10.1",
+  "version": "1.11.0",
   "description": "A shared web extraction layer for AI conversations and regular web pages.",
   "type": "module",
   "engines": {
@@ -26,12 +26,12 @@
   ],
   "repository": {
     "type": "git",
-    "url": "git+https://github.com/Covai-Labs/decant-core.git"
+    "url": "git+https://github.com/Covai-Labs/decant.git"
   },
   "bugs": {
-    "url": "https://github.com/Covai-Labs/decant-core/issues"
+    "url": "https://github.com/Covai-Labs/decant/issues"
   },
-  "homepage": "https://github.com/Covai-Labs/decant-core#readme",
+  "homepage": "https://github.com/Covai-Labs/decant#readme",
   "scripts": {
     "test": "node --test tests/*.test.js",
     "lint": "eslint .",