Switch from urllib to requests to improve reliability (#867)

* Switch from urllib to requests to improve reliability

* Keep ruff linter-specific

* update

* update

* update

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

@@ -186,6 +186,56 @@
     }
    ],
    "source": [
+    "import requests\n",
+    "import zipfile\n",
+    "import os\n",
+    "from pathlib import Path\n",
+    "\n",
+    "url = \"https://archive.ics.uci.edu/static/public/228/sms+spam+collection.zip\"\n",
+    "zip_path = \"sms_spam_collection.zip\"\n",
+    "extracted_path = \"sms_spam_collection\"\n",
+    "data_file_path = Path(extracted_path) / \"SMSSpamCollection.tsv\"\n",
+    "\n",
+    "\n",
+    "def download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path):\n",
+    "    if data_file_path.exists():\n",
+    "        print(f\"{data_file_path} already exists. Skipping download and extraction.\")\n",
+    "        return\n",
+    "\n",
+    "    # Downloading the file\n",
+    "    response = requests.get(url, stream=True, timeout=60)\n",
+    "    response.raise_for_status()\n",
+    "    with open(zip_path, \"wb\") as out_file:\n",
+    "        for chunk in response.iter_content(chunk_size=8192):\n",
+    "            if chunk:\n",
+    "                out_file.write(chunk)\n",
+    "\n",
+    "    # Unzipping the file\n",
+    "    with zipfile.ZipFile(zip_path, \"r\") as zip_ref:\n",
+    "        zip_ref.extractall(extracted_path)\n",
+    "\n",
+    "    # Add .tsv file extension\n",
+    "    original_file_path = Path(extracted_path) / \"SMSSpamCollection\"\n",
+    "    os.rename(original_file_path, data_file_path)\n",
+    "    print(f\"File downloaded and saved as {data_file_path}\")\n",
+    "\n",
+    "\n",
+    "try:\n",
+    "    download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
+    "except (requests.exceptions.RequestException, TimeoutError) as e:\n",
+    "    print(f\"Primary URL failed: {e}. Trying 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)\n",
+    "\n",
+    "\n",
+    "\n",
+    "# The book originally used the following code below\n",
+    "# However, urllib uses older protocol settings that\n",
+    "# can cause problems for some readers using a VPN.\n",
+    "# The `requests` version above is more robust\n",
+    "# in that regard.\n",
+    "\n",
+    "\"\"\"\n",
     "import urllib.request\n",
     "import zipfile\n",
     "import os\n",
@@ -220,7 +270,8 @@
     "except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:\n",
     "    print(f\"Primary URL failed: {e}. Trying 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) "
+    "    download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
+    "\"\"\""
    ]
   },
   {

ch06/01_main-chapter-code/gpt_class_finetune.py

@@ -5,7 +5,7 @@
 
 # This is a summary file containing the main takeaways from chapter 6.
 
-import urllib.request
+import requests
 import zipfile
 import os
 from pathlib import Path
@@ -27,9 +27,12 @@ def download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path):
         return
 
     # Downloading the file
-    with urllib.request.urlopen(url) as response:
-        with open(zip_path, "wb") as out_file:
-            out_file.write(response.read())
+    response = requests.get(url, stream=True, timeout=60)
+    response.raise_for_status()
+    with open(zip_path, "wb") as out_file:
+        for chunk in response.iter_content(chunk_size=8192):
+            if chunk:
+                out_file.write(chunk)
 
     # Unzipping the file
     with zipfile.ZipFile(zip_path, "r") as zip_ref:
@@ -259,7 +262,7 @@ if __name__ == "__main__":
 
     try:
         download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)
-    except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:
+    except (requests.exceptions.RequestException, TimeoutError) as e:
         print(f"Primary URL failed: {e}. Trying backup URL...")
         url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
         download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)