Merge pull request #872 from domienbakker/domienbakker/day1-solution

Domienbakker/day1 solution

week1/community-contributions/domienbakker/day1.selenium.scraper.ipynb

@@ -0,0 +1,151 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0bb7f4e9",
+   "metadata": {},
+   "source": [
+    "### Prepare dependencies\n",
+    "I had issues with selenium and my chromedriver, I had to install the exact dependencies below to make it work.\n",
+    "First add the dependency selenium by executing folowing command\n",
+    "``` bash\n",
+    "uv pip install selenium==4.11.2\n",
+    "uv pip install urllib3==1.26.16\n",
+    "```\n",
+    "***Do not forget to restart the Jupyter kernel to make the package available.***"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7a116541",
+   "metadata": {},
+   "source": [
+    "### Prefered Web Browser\n",
+    "This script will use Safari on MacOSX, please install the Safari driver when required [Safari driver](https://webkit.org/blog/6900/webdriver-support-in-safari-10).\n",
+    "It will assume that Edge is used on Windows systems, install the Chrome driver from: [ChromeDriver](https://googlechromelabs.github.io/chrome-for-testing/#stable) \n",
+    "Feel free to add other browser support when required.\n",
+    "\n",
+    "I am on Windows and I extracted the ChromeDriver and put it in my %USERPROFILE%\\AppData\\Local\\Microsoft\\WindowsApps folder to ensure that it is available via the PATH. Any folder available in the PATH environment setting will work.\n",
+    "Start cmd and execute set to see all folders in the PATH environment setting.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1353f8ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "\n",
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from scraper import fetch_website_contents\n",
+    "from IPython.display import Markdown, display\n",
+    "from openai import OpenAI\n",
+    "from selenium import webdriver"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "24d86842",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def verify_openai_api_key():\n",
+    "    \"\"\"Verify that the OpenAI API key is set in the environment variables.\"\"\"\n",
+    "    load_dotenv(override=True)\n",
+    "    api_key = os.getenv('OPENAI_API_KEY')\n",
+    "\n",
+    "    if not api_key:\n",
+    "        raise ValueError(\"OPENAI_API_KEY is not set in environment variables.\")\n",
+    "    \n",
+    "    # Dry run with a simple request to verify the key.\n",
+    "    try:\n",
+    "        client = OpenAI(api_key=api_key)\n",
+    "        client.models.list()\n",
+    "    except:\n",
+    "        raise ValueError(\"Invalid OPENAI_API_KEY.\")\n",
+    "    \n",
+    "    return api_key\n",
+    "\n",
+    "def get_webdriver():\n",
+    "    \"\"\"Initialize and return a Selenium WebDriver based on the operating system.\"\"\"\n",
+    "        \n",
+    "    # Verify the os, use Safari for MacOS, Chrome for others.\n",
+    "    if os.name == 'posix':        \n",
+    "        driver = webdriver.Safari()\n",
+    "    else:\n",
+    "        driver = webdriver.Chrome()\n",
+    "    return driver\n",
+    "\n",
+    "def fetch_website_contents_selenium(url: str) -> str:\n",
+    "    \"\"\"Fetch website contents using Selenium WebDriver.\"\"\"\n",
+    "    driver = get_webdriver()\n",
+    "    driver.get(url)\n",
+    "    content = driver.page_source\n",
+    "    driver.quit()\n",
+    "    return content\n",
+    "\n",
+    "def messages_for(website: str) -> list[dict]:\n",
+    "    return [\n",
+    "        {\n",
+    "            \"role\": \"system\",\n",
+    "            \"content\": \"\"\"You are a helpful assistant that summarizes website content.\n",
+    "            You can perfectly understand HTML structure and extract meaningful information from it.\"\"\"\n",
+    "        },\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": f\"Summarize the following website content:\\n\\n{website}\"\n",
+    "        }\n",
+    "    ]\n",
+    "\n",
+    "def summarize_website(url: str, api_key: str) -> str:\n",
+    "    content = fetch_website_contents_selenium(url)\n",
+    "    openai_client = OpenAI(api_key=api_key)\n",
+    "    response = openai_client.chat.completions.create(\n",
+    "        model = \"gpt-4.1-mini\",\n",
+    "        messages = messages_for(content)\n",
+    "    )\n",
+    "    return response.choices[0].message.content\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9a7e7f0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    api_key = verify_openai_api_key()\n",
+    "    print(summarize_website(\"https://www.forbes.com/\", api_key))\n",
+    "except Exception as e:\n",
+    "    print(f\"Error: {e}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llm-engineering",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}