Air_Quality_Data_Analysis.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YPGBy48HM6E0",
        "outputId": "2aa67f76-ca3a-4d6c-df1a-cb775fe718e9"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[31mERROR: Could not find a version that satisfies the requirement cpcb_api (from versions: none)\u001b[0m\u001b[31m\n",
            "\u001b[0m\u001b[31mERROR: No matching distribution found for cpcb_api\u001b[0m\u001b[31m\n",
            "\u001b[0m"
          ]
        }
      ],
      "source": [
        "# !pip install cpcb_api pytorch transformers matplotlib"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# import torch\n",
        "# from torch.utils.data import TensorDataset, DataLoader\n",
        "# import cpcb_api as cpcb\n",
        "# from sklearn.preprocessing import StandardScaler\n",
        "# from sklearn.metrics import mean_squared_error, r2_score\n",
        "# from transformers import AutoTokenizer, AutoModelForSeq2SeqLM"
      ],
      "metadata": {
        "id": "y0VbodsYQzeh",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 383
        },
        "outputId": "6493d24b-e2ac-4a9a-d04e-a50fbdd0715e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "ModuleNotFoundError",
          "evalue": "No module named 'cpcb_api'",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-2-eec9e638e797>\u001b[0m in \u001b[0;36m<cell line: 3>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mTensorDataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mDataLoader\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mcpcb_api\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mcpcb\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpreprocessing\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mStandardScaler\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmean_squared_error\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mr2_score\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'cpcb_api'",
            "",
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0;32m\nNOTE: If your import is failing due to a missing package, you can\nmanually install dependencies using either !pip or !apt.\n\nTo view examples of installing some common dependencies, click the\n\"Open Examples\" button below.\n\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n"
          ],
          "errorDetails": {
            "actions": [
              {
                "action": "open_url",
                "actionText": "Open Examples",
                "url": "/notebooks/snippets/importing_libraries.ipynb"
              }
            ]
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# git clone https://github.com/abhijit-sharma/cpcb_api.git\n",
        "# cd cpcb_api\n",
        "# pip install .\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 106
        },
        "id": "R0ZVcMbGRi-1",
        "outputId": "fd97a5f2-4d18-494d-f557-1fdeaaad4ef5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "SyntaxError",
          "evalue": "invalid syntax (<ipython-input-3-05fbcdee3638>, line 1)",
          "traceback": [
            "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-3-05fbcdee3638>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m    git clone https://github.com/abhijit-sharma/cpcb_api.git\u001b[0m\n\u001b[0m        ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# %%shell\n",
        "# git clone https://github.com/abhijit-sharma/cpcb_api.git\n",
        "# cd cpcb_api\n",
        "# pip install ."
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 408
        },
        "id": "4vo4gnZaRp0m",
        "outputId": "907fbf6d-371d-4fc5-9b06-a857fc28f9de"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'cpcb_api'...\n",
            "fatal: could not read Username for 'https://github.com': No such device or address\n",
            "/bin/bash: line 2: cd: cpcb_api: No such file or directory\n",
            "\u001b[31mERROR: Directory '.' is not installable. Neither 'setup.py' nor 'pyproject.toml' found.\u001b[0m\u001b[31m\n",
            "\u001b[0m"
          ]
        },
        {
          "output_type": "error",
          "ename": "CalledProcessError",
          "evalue": "Command 'git clone https://github.com/abhijit-sharma/cpcb_api.git\ncd cpcb_api\npip install .\n' returned non-zero exit status 1.",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mCalledProcessError\u001b[0m                        Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-4-74af006b62e4>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_cell_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'shell'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m''\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'git clone https://github.com/abhijit-sharma/cpcb_api.git\\ncd cpcb_api\\npip install .\\n'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/google/colab/_shell.py\u001b[0m in \u001b[0;36mrun_cell_magic\u001b[0;34m(self, magic_name, line, cell)\u001b[0m\n\u001b[1;32m    332\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mline\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mcell\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    333\u001b[0m       \u001b[0mcell\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m' '\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 334\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_cell_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmagic_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mline\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcell\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    335\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    336\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/IPython/core/interactiveshell.py\u001b[0m in \u001b[0;36mrun_cell_magic\u001b[0;34m(self, magic_name, line, cell)\u001b[0m\n\u001b[1;32m   2471\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuiltin_trap\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2472\u001b[0m                 \u001b[0margs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mmagic_arg_s\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcell\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2473\u001b[0;31m                 \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2474\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2475\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/google/colab/_system_commands.py\u001b[0m in \u001b[0;36m_shell_cell_magic\u001b[0;34m(args, cmd)\u001b[0m\n\u001b[1;32m    110\u001b[0m   \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_run_command\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcmd\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mclear_streamed_output\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    111\u001b[0m   \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mparsed_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mignore_errors\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 112\u001b[0;31m     \u001b[0mresult\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcheck_returncode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    113\u001b[0m   \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    114\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/google/colab/_system_commands.py\u001b[0m in \u001b[0;36mcheck_returncode\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    135\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0mcheck_returncode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    136\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreturncode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 137\u001b[0;31m       raise subprocess.CalledProcessError(\n\u001b[0m\u001b[1;32m    138\u001b[0m           \u001b[0mreturncode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreturncode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcmd\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moutput\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    139\u001b[0m       )\n",
            "\u001b[0;31mCalledProcessError\u001b[0m: Command 'git clone https://github.com/abhijit-sharma/cpcb_api.git\ncd cpcb_api\npip install .\n' returned non-zero exit status 1."
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import requests\n",
        "from bs4 import BeautifulSoup\n",
        "import torch\n",
        "from transformers import GPT2LMHeadModel, GPT2Tokenizer\n",
        "import matplotlib.pyplot as plt"
      ],
      "metadata": {
        "id": "2Y0ZcU9YSG6W"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "url = \"https://cpcb.nic.in/automatic-monitoring-data/\""
      ],
      "metadata": {
        "id": "yg2dMYrPT2pB"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "response = requests.get(url)"
      ],
      "metadata": {
        "id": "4rUv2FWjT-dw"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "soup = BeautifulSoup(response.content, \"html.parser\")"
      ],
      "metadata": {
        "id": "tn6SASD7UDqN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "station_id = \"DL_09\"  # Replace 'your_station_id' with the actual station ID\n",
        "station_data_link = soup.find(\"a\", {\"id\": station_id})"
      ],
      "metadata": {
        "id": "NROVlp1uUHRs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_url = station_data_link[\"href\"]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "Vis7O63WUTGu",
        "outputId": "8daff067-d52c-4be3-afc8-5bea8fe22699"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "TypeError",
          "evalue": "'NoneType' object is not subscriptable",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-10-0d6ccb594d28>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstation_data_link\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"href\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;31mTypeError\u001b[0m: 'NoneType' object is not subscriptable"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "if response.status_code == 200:\n",
        "    # Parse the HTML content\n",
        "    soup = BeautifulSoup(response.content, \"html.parser\")\n",
        "\n",
        "    # Find the link(s) to the data file(s) for the specific station\n",
        "    station_id = \"DL_10\"  # Replace 'your_station_id' with the actual station ID\n",
        "    station_data_link = soup.find(\"a\", {\"id\": station_id})\n",
        "\n",
        "    # Check if the link was found\n",
        "    if station_data_link:\n",
        "        # Extract the URL of the data file\n",
        "        data_url = urljoin(url, station_data_link[\"href\"])\n",
        "\n",
        "        # Download the data file\n",
        "        data_response = requests.get(data_url)\n",
        "\n",
        "        # Check if the data file was downloaded successfully\n",
        "        if data_response.status_code == 200:\n",
        "            # Save the data to a file\n",
        "            with open(\"station_data.csv\", \"wb\") as file:\n",
        "                file.write(data_response.content)\n",
        "\n",
        "            # Load the data into a DataFrame\n",
        "            data = pd.read_csv(\"station_data.csv\")\n",
        "\n",
        "            # Preprocess the data as needed\n",
        "            # For simplicity, let's assume the data is already preprocessed and ready for modeling\n",
        "\n",
        "            print(\"Data downloaded and preprocessed successfully.\")\n",
        "        else:\n",
        "            print(\"Failed to download data file.\")\n",
        "    else:\n",
        "        print(\"Station data link not found.\")\n",
        "else:\n",
        "    print(\"Failed to fetch website content.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Bypo_rs5UWF4",
        "outputId": "923edac9-c4dc-4439-9b57-eee45e6dbfe7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Station data link not found.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from urllib.parse import urljoin\n",
        "if response.status_code == 200:\n",
        "    # Parse the HTML content\n",
        "    soup = BeautifulSoup(response.content, \"html.parser\")\n",
        "\n",
        "    # Find all links on the page\n",
        "    links = soup.find_all(\"a\")\n",
        "\n",
        "    # Filter the links to find those related to air quality data\n",
        "    relevant_links = [link for link in links if \"air quality data\" in link.text.lower()]\n",
        "\n",
        "    if relevant_links:\n",
        "        # Extract the URL of the first relevant link\n",
        "        data_url = urljoin(url, relevant_links[0][\"href\"])\n",
        "\n",
        "        # Download the data file\n",
        "        data_response = requests.get(data_url)\n",
        "\n",
        "        # Check if the data file was downloaded successfully\n",
        "        if data_response.status_code == 200:\n",
        "            # Save the data to a file\n",
        "            with open(\"station_data.csv\", \"wb\") as file:\n",
        "                file.write(data_response.content)\n",
        "\n",
        "            # Load the data into a DataFrame\n",
        "            data = pd.read_csv(\"station_data.csv\")\n",
        "\n",
        "            # Preprocess the data as needed\n",
        "            # For simplicity, let's assume the data is already preprocessed and ready for modeling\n",
        "\n",
        "            print(\"Data downloaded and preprocessed successfully.\")\n",
        "        else:\n",
        "            print(\"Failed to download data file.\")\n",
        "    else:\n",
        "        print(\"No relevant links found for air quality data.\")\n",
        "else:\n",
        "    print(\"Failed to fetch website content.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 332
        },
        "id": "0IKVHWfFUjqQ",
        "outputId": "5d686241-a731-4209-f277-d3453ee212a8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "KeyError",
          "evalue": "'href'",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-18-227bad8f5d90>\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     12\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mrelevant_links\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     13\u001b[0m         \u001b[0;31m# Extract the URL of the first relevant link\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m         \u001b[0mdata_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0murljoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrelevant_links\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"href\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     16\u001b[0m         \u001b[0;31m# Download the data file\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/bs4/element.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1571\u001b[0m         \"\"\"tag[key] returns the value of the 'key' attribute for the Tag,\n\u001b[1;32m   1572\u001b[0m         and throws an exception if it's not there.\"\"\"\n\u001b[0;32m-> 1573\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mattrs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1574\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1575\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__iter__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyError\u001b[0m: 'href'"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "48yXPeZtVPWu"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}