Feat/website screenshotting

package.json

@@ -13,6 +13,7 @@
     "nanoid": "^3.2.0",
     "node-fetch": "2",
     "node-tesseract-ocr": "^2.2.1",
+    "puppeteer": "^19.4.0",
     "sequelize": "^6.19.0",
     "sqlite3": "^5.0.5",
     "string-similarity": "^4.0.4"

src/events/MessageScanner.event.ts

@@ -1,13 +1,13 @@
 import { GuildChannel, Message } from "discord.js";
 import { Event } from "../handlers/EventHandler";
+import puppeteer from "puppeteer";
 // @ts-ignore
 import Tesseract from "node-tesseract-ocr";
 import fetch from "node-fetch";
 import { client } from "../index";
 import { BinLink } from "../types";
 import AutoResponseManager from "../managers/AutoResponseManager";
 import StatisticsManager from "../managers/StatisticsManager";
-
 const tesseractConfig = {
     lang: "eng",
     oem: 2,
@@ -59,6 +59,28 @@ export default class ReadyEvent extends Event<"messageCreate"> {
             text += " " + content;
         }
 
+        // Links in text
+        const urlExpression = /https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b[-a-zA-Z0-9()@:%_\+.~#?&//=]*/gi;
+        const matches = msg.content.match(urlExpression);
+        if (matches) {
+            for (const match of matches) {
+                let browser;
+                try {
+                    browser = await puppeteer.launch({ headless: true });
+                    const page = await browser.newPage();
+                    await page.setViewport({ width: 1440, height: 1080 });
+                    await page.goto(match);
+                    const screenshot = await page.screenshot({ type: 'jpeg', quality: 100 });
+
+                    text += (" " + (await Tesseract.recognize(screenshot, tesseractConfig)));
+                } catch (err: any) {
+                    console.log(`❌ Browser error: ${err.message}`);
+                } finally {
+                    await browser?.close();
+                }
+            }
+        }
+
         // Paste links
         const bins = JSON.parse(
             client.github.getFileFromRepo("bin_links.json")