improve Jupyter Notebook

copernicus_services_miner.ipynb

@@ -74,30 +74,19 @@
     "                href = a.get(\"href\")\n",
     "                if href and href.startswith(\"/en/access-data/\"):\n",
     "                    full_url = url\n",
-    "                    data_list.append({\"Page Number\": page, \"Full URL\": full_url, \"Link\": href})\n",
+    "                    data_list.append({\"Page Number\": page, \"Page_URL\": full_url, \"Link\": href})\n",
     "        else:\n",
     "            print(f\"No <div> with specified classes found on page {page}\")\n",
     "    else:\n",
     "        print(f\"Failed to fetch data from page {page}. Status code: {response.status_code}\")\n",
     "\n",
     "# Convert the list of dictionaries to a Pandas DataFrame\n",
     "df = pd.DataFrame(data_list)\n",
-    "\n",
-    "print(\"Mining and extraction complete.\")\n",
-    "print(\"Links starting with '/en/access-data/' have been added to the DataFrame.\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "df[\"Service_URL\"] = \"https://www.copernicus.eu\" + df[\"Link\"]\n",
     "del df[\"Link\"]\n",
     "\n",
-    "df[\"Page_URL\"] = df[\"Full URL\"]\n",
-    "del df[\"Full URL\"]"
+    "print(\"Mining and extraction complete.\")\n",
+    "print(\"Links starting with '/en/access-data/' have been added to the DataFrame.\")"
    ]
   },
   {