Scraping the table names from from https://www150.statcan.gc.ca/n1/en/type/data

Will compare against the productIds available at  https://www150.statcan.gc.ca/t1/wds/rest/getAllCubesListLite

experiments/scrape_statcan_tables/aria2c_download.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "561e3485-50c3-4177-861a-5989ae437b33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "import aria2p\n",
+    "\n",
+    "# initialization, these are the default values\n",
+    "aria2 = aria2p.API(\n",
+    "    aria2p.Client(\n",
+    "        host=\"http://localhost\",\n",
+    "        port=6800,\n",
+    "        secret=\"\"\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e30a5be2-a498-4f3c-9a94-a7a2659f258d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Helper function to wait for download to finish\n",
+    "def wait_for_download(download):\n",
+    "    print(f\"Waiting for download: {download.name}\")\n",
+    "    while download.is_active:\n",
+    "        print(f\"Progress: {download.progress_string()} - {download.status}\")\n",
+    "        time.sleep(10)\n",
+    "        download = aria2.get_download(download.gid)  # refresh state\n",
+    "    print(f\"Download completed: {download.name} - Status: {download.status}\")\n",
+    "    return download"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9fc190bd-3c68-48d7-902e-770bbd69fc38",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Waiting for download: test.parquet\n",
+      "Progress: 0.00% - active\n"
+     ]
+    }
+   ],
+   "source": [
+    "urls = ['https://data.dataforcanada.org/processed/statistics_canada/boundaries/2021/digital_boundary_files/db_2021.parquet']\n",
+    "\n",
+    "download = aria2.add_uris(urls, options={\"out\": \"test.parquet\"})\n",
+    "download = wait_for_download(download)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8000ee01-d10c-44d9-a826-2d3c44dabd7a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}