Add backup url for Spam Dataset (#543)

* Add backup url for Spam Dataset

* import urllib

* fix url

ch06/01_main-chapter-code/ch06.ipynb

@@ -50,7 +50,7 @@
      "text": [
       "matplotlib version: 3.10.0\n",
       "numpy version: 2.0.2\n",
-      "tiktoken version: 0.8.0\n",
+      "tiktoken version: 0.9.0\n",
       "torch version: 2.6.0\n",
       "tensorflow version: 2.18.0\n",
       "pandas version: 2.2.3\n"
@@ -167,7 +167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "def7c09b-af9c-4216-90ce-5e67aed1065c",
    "metadata": {
     "colab": {
@@ -181,7 +181,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "sms_spam_collection/SMSSpamCollection.tsv already exists. Skipping download and extraction.\n"
+      "File downloaded and saved as sms_spam_collection/SMSSpamCollection.tsv\n"
      ]
     }
    ],
@@ -215,7 +215,13 @@
     "    os.rename(original_file_path, data_file_path)\n",
     "    print(f\"File downloaded and saved as {data_file_path}\")\n",
     "\n",
-    "download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)"
+    "try:\n",
+    "    download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
+    "except urllib.error.HTTPError:\n",
+    "    print(\"UCI Machine Learning Repository (https://archive.ics.uci.edu)\"\n",
+    "          \" temporary unavailable. Using backup URL.\")\n",
+    "    url = \"https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip\"\n",
+    "    download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path) "
    ]
   },
   {