scraper links coto

.vscode/launch.json

@@ -0,0 +1,29 @@
+{
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "type": "node",
+      "request": "launch",
+      "name": "Launch Program",
+      "skipFiles": ["<node_internals>/**"],
+      "cwd": "${workspaceFolder}/scraper",
+      "runtimeArgs": ["--import", "tsx/esm"],
+      "program": "${workspaceFolder}/scraper/scrap.ts",
+      "args": ["carrefour.warc.gz"],
+      "outFiles": ["${workspaceFolder}/**/*.js"]
+    },
+    {
+      "type": "node",
+      "request": "launch",
+      "name": "coto-link-scraper",
+      "skipFiles": ["<node_internals>/**"],
+      "cwd": "${workspaceFolder}/coto-link-scraper",
+      "runtimeArgs": ["--import", "tsx/esm"],
+      "program": "${workspaceFolder}/coto-link-scraper/index.ts",
+      "outFiles": ["${workspaceFolder}/**/*.js"]
+    },
+  ]
+}

coto-link-scraper/index.ts

@@ -0,0 +1,38 @@
+// Import puppeteer
+import puppeteer from "puppeteer";
+
+(async () => {
+  const browser = await puppeteer.launch();
+  const page = await browser.newPage();
+  await page.goto(
+    "https://www.cotodigital3.com.ar/sitios/cdigi/browse/catalogo-almac%C3%A9n/"
+  );
+
+  async function getHrefs() {
+    const element = await page.waitForSelector(".product_info_container a");
+    await element?.dispose();
+    const hrefs = await page.evaluate(() =>
+      Array.from(
+        document.querySelectorAll<HTMLAnchorElement>(
+          ".product_info_container a"
+        ),
+        (a) => new URL(a.href).toString()
+      )
+    );
+    return hrefs;
+  }
+  try {
+    while (true) {
+      const hrefs = await getHrefs();
+      hrefs.forEach((href) => console.log(href));
+
+      const btn = await page.waitForSelector('a[title="Siguiente"]', {
+        timeout: 5000,
+      });
+      await btn?.click();
+      await btn?.dispose();
+    }
+  } finally {
+    await browser.close();
+  }
+})();

coto-link-scraper/package.json

@@ -0,0 +1,17 @@
+{
+  "name": "coto-link-scraper",
+  "type": "module",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "dependencies": {
+    "puppeteer": "^21.6.1",
+    "tsx": "^4.7.0"
+  }
+}