USA_WebScrapping.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": "Xok0Apfor6ti",
        "outputId": "82ad29ad-5691-46d4-e686-3187fa180eae"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Inventory data has been saved to inventory_data.csv\n",
            "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\n",
            "<html>\n",
            " <head>\n",
            "  <meta content=\"text/html; charset=utf-8\" http-equiv=\"Content-Type\"/>\n",
            "  <title>\n",
            "   ERROR: The request could not be satisfied\n",
            "  </title>\n",
            " </head>\n",
            " <body>\n",
            "  <h1>\n",
            "   403 ERROR\n",
            "  </h1>\n",
            "  <h2>\n",
            "   The request could not be satisfied.\n",
            "  </h2>\n",
            "  <hr noshade=\"\" size=\"1px\"/>\n",
            "  Request blocked.\n",
            "We can't connect to the server for this app or website at this time. There might be too much traffic or a configuration error. Try again later, or contact the app or website owner.\n",
            "  <br clear=\"all\"/>\n",
            "  If you provide content to customers through CloudFront, you can find steps to troubleshoot and help prevent this error by reviewing the CloudFront documentation.\n",
            "  <br clear=\"all\"/>\n",
            "  <hr noshade=\"\" size=\"1px\"/>\n",
            "  <pre>\n",
            "Generated by cloudfront (CloudFront)\n",
            "Request ID: ARjPzAupZj8GgSAi0Nv3uvFqcRXlJazO2srq0wlZRjJcT69Ae6Lh6Q==\n",
            "</pre>\n",
            "  <address>\n",
            "  </address>\n",
            " </body>\n",
            "</html>\n",
            "\n"
          ]
        }
      ],
      "source": [
        "from bs4 import BeautifulSoup\n",
        "import pandas as pd\n",
        "import requests\n",
        "\n",
        "# Define the URL of the website to scrape\n",
        "url = 'https://www.cityfurniture.com/browse/living-room'  # Replace with the actual URL of the inventory page\n",
        "\n",
        "# Send a request to the website\n",
        "response = requests.get(url)\n",
        "#response.raise_for_status()  # Check if the request was successful\n",
        "\n",
        "# Parse the webpage content\n",
        "soup = BeautifulSoup(response.content, 'html.parser')\n",
        "\n",
        "\n",
        "# Find the relevant data (This example assumes there are divs with class 'product' containing inventory info)\n",
        "products = []\n",
        "for product_div in soup.find_all('div', class_='product'):  # Adjust the class name based on the actual HTML structure\n",
        "    product_name = product_div.find('div', class_='product-name').text.strip()  # Adjust based on actual HTML structure\n",
        "    inventory_status = product_div.find('div', class_='inventory-status').text.strip()  # Adjust based on actual HTML structure\n",
        "\n",
        "    # Add the data to the list\n",
        "    products.append({\n",
        "        'Product Name': product_name,\n",
        "        'Inventory Status': inventory_status\n",
        "    })\n",
        "\n",
        "# Convert the list of dictionaries to a pandas DataFrame\n",
        "df = pd.DataFrame(products)\n",
        "\n",
        "# Save the DataFrame to a CSV file\n",
        "df.to_csv('inventory_data.csv', index=False)\n",
        "\n",
        "print('Inventory data has been saved to inventory_data.csv')\n",
        "print(soup.prettify())  # Print the entire HTML structure\n",
        "for product_div in soup.find_all('div', class_='product-item'):\n",
        "    print(product_div)  # Print each product div\n",
        "    product_name = product_div.find('div', class_='product-title').text.strip()\n",
        "    print(product_name)  # Print the product name\n",
        "    inventory_status = product_div.find('div', class_='stock-status').text.strip()\n",
        "    print(inventory_status)  # Print the inventory status\n"
      ]
    }
  ]
}