{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "## Web2Quiz: Generator Quiz from webpage content."
      ],
      "metadata": {
        "id": "n3vd295elWxh"
      },
      "id": "n3vd295elWxh"
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "f4484fcf-8b39-4c3f-9674-37970ed71988",
      "metadata": {
        "id": "f4484fcf-8b39-4c3f-9674-37970ed71988"
      },
      "outputs": [],
      "source": [
        "#.env upload\n",
        "from google.colab import files\n",
        "uploaded = files.upload()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install dotenv\n"
      ],
      "metadata": {
        "id": "VTpN_jVbMKuk"
      },
      "id": "VTpN_jVbMKuk",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "from dotenv import load_dotenv"
      ],
      "metadata": {
        "id": "twYi9eJwL2h1"
      },
      "id": "twYi9eJwL2h1",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "load_dotenv(override=True)\n",
        "api_key = os.getenv('OPENROUTER_KEY')\n",
        "\n",
        "# Check the key\n",
        "if not api_key:\n",
        "    print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
        "# elif not api_key.startswith(\"sk-proj-\"):\n",
        "#     print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
        "elif api_key.strip() != api_key:\n",
        "    print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
        "else:\n",
        "    print(\"API key found and looks good so far!\")\n"
      ],
      "metadata": {
        "id": "NRnUTEkZL2eZ"
      },
      "id": "NRnUTEkZL2eZ",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install openai"
      ],
      "metadata": {
        "id": "RRuKJ_pzL2be"
      },
      "id": "RRuKJ_pzL2be",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install requests beautifulsoup4\n",
        "!pip install selenium"
      ],
      "metadata": {
        "id": "DWsPpdjOVPTW"
      },
      "id": "DWsPpdjOVPTW",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from bs4 import BeautifulSoup\n",
        "import requests\n",
        "from tempfile import mkdtemp\n",
        "from selenium import webdriver\n",
        "from selenium.webdriver.chrome.options import Options\n",
        "from selenium.webdriver.support.ui import WebDriverWait\n",
        "from selenium.webdriver.support import expected_conditions as EC\n",
        "from selenium.webdriver.common.by import By\n",
        "\n",
        "class Website:\n",
        "    def __init__(self, url, use_selenium=False):\n",
        "        \"\"\"\n",
        "        Create Website object from the given URL.\n",
        "        If use_selenium=True, fetch page with Selenium.\n",
        "        Otherwise, use requests + BeautifulSoup.\n",
        "        \"\"\"\n",
        "        self.url = url\n",
        "        self.title = \"\"\n",
        "        self.text = \"\"\n",
        "        self.use_selenium = use_selenium\n",
        "\n",
        "        if self.use_selenium:\n",
        "            html = self._fetch_with_selenium()\n",
        "        else:\n",
        "            html = self._fetch_with_requests()\n",
        "\n",
        "        if not html:\n",
        "            self.title = \"Error fetching page\"\n",
        "            self.text = \"Could not retrieve HTML content.\"\n",
        "            return\n",
        "\n",
        "        soup = BeautifulSoup(html, \"html.parser\")\n",
        "        self.title = soup.title.string if soup.title else \"No title found\"\n",
        "\n",
        "        # content_div = soup.find('div', id='content')\n",
        "        if soup.body:\n",
        "            for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\", \"header\", \"footer\", \"nav\", \"aside\"]):\n",
        "                irrelevant.decompose()\n",
        "            self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n",
        "        else:\n",
        "            self.text = \"No body tag found in the HTML.\"\n",
        "\n",
        "    # Basic html scrapper\n",
        "    def _fetch_with_requests(self):\n",
        "        \"\"\"Fetch HTML using requests.\"\"\"\n",
        "        try:\n",
        "            headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
        "            response = requests.get(self.url, headers=headers, timeout=10)\n",
        "            response.raise_for_status()\n",
        "            return response.text\n",
        "        except requests.exceptions.RequestException as e:\n",
        "            print(f\"Error fetching with requests: {e}\")\n",
        "            return None\n",
        "\n",
        "    # Dynamic html scrapper\n",
        "    def _fetch_with_selenium(self):\n",
        "        \"\"\"Fetch HTML using Selenium with improved options.\"\"\"\n",
        "        options = Options()\n",
        "        options.add_argument(\"--no-sandbox\")\n",
        "        options.add_argument(\"--disable-dev-shm-usage\")\n",
        "        options.add_argument(\"--headless\")\n",
        "        options.add_argument(f\"--user-data-dir={mkdtemp()}\")\n",
        "\n",
        "        driver = None\n",
        "        try:\n",
        "            driver = webdriver.Chrome(options=options)\n",
        "            driver.get(self.url)\n",
        "\n",
        "            WebDriverWait(driver, 10).until(\n",
        "                EC.presence_of_element_located((By.TAG_NAME, \"body\"))\n",
        "            )\n",
        "\n",
        "            html = driver.page_source\n",
        "            return html\n",
        "        except Exception as e:\n",
        "            print(f\"An error occurred during Selenium fetch: {e}\")\n",
        "            return None\n",
        "        finally:\n",
        "            if driver:\n",
        "                driver.quit()\n",
        "\n"
      ],
      "metadata": {
        "id": "PzBP0tXXcrP-"
      },
      "id": "PzBP0tXXcrP-",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "site1 = Website(\"https://en.wikipedia.org/wiki/Integration_testing\", use_selenium=False)\n",
        "print(\"Title:\", site1.title)\n",
        "print(\"Text preview:\", site1.text[:200])\n",
        "\n",
        "site2 = Website(\"https://www.tpointtech.com/java-for-loop\", use_selenium=True)\n",
        "print(\"Title:\", site2.title)\n",
        "print(\"Text preview:\", site2.text[:200])"
      ],
      "metadata": {
        "id": "vsNmh5b5c6Gq"
      },
      "id": "vsNmh5b5c6Gq",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Step 1: Create your prompts\n",
        "system_prompt = f\"You are a MCQ quiz generator. Analyze the provided TEXT and filter CONTENT relevent to {site1.title}. Then based on the relevant CONTENT generate 10 MCQs. List all correct options at the end.\"\n",
        "user_prompt = f\"Below is provided TEXT : \\n{site1.text}\"\n",
        "\n",
        "# Step 2: Make the messages list\n",
        "messages = [\n",
        "    {\"role\": \"system\", \"content\": system_prompt},\n",
        "    {\"role\": \"user\", \"content\": user_prompt}\n",
        "]\n",
        "\n",
        "# Step 3: Call OpenAI\n",
        "openai = OpenAI(base_url=\"https://openrouter.ai/api/v1\", api_key=api_key)\n",
        "\n",
        "# Step 4: print the result\n",
        "response = openai.chat.completions.create(model=\"qwen/qwen2.5-vl-72b-instruct:free\", messages=messages)\n",
        "print(response.choices[0].message.content)"
      ],
      "metadata": {
        "collapsed": true,
        "id": "BYdc1w70QFD2"
      },
      "id": "BYdc1w70QFD2",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Step 1: Create your prompts\n",
        "system_prompt = f\"You are a MCQ quiz generator. Analyze the provided TEXT and filter CONTENT relevent to {site2.title}. Then based on the relevant CONTENT generate 10 MCQs. List all correct options at the end.\"\n",
        "user_prompt = f\"Below is provided TEXT : \\n{site2.text}\"\n",
        "\n",
        "# Step 2: Make the messages list\n",
        "messages = [\n",
        "    {\"role\": \"system\", \"content\": system_prompt},\n",
        "    {\"role\": \"user\", \"content\": user_prompt}\n",
        "]\n",
        "\n",
        "# Step 3: Call OpenAI\n",
        "openai = OpenAI(base_url=\"https://openrouter.ai/api/v1\", api_key=api_key)\n",
        "\n",
        "# Step 4: print the result\n",
        "response = openai.chat.completions.create(model=\"qwen/qwen2.5-vl-72b-instruct:free\", messages=messages)\n",
        "print(response.choices[0].message.content)"
      ],
      "metadata": {
        "id": "Rv8vxFHtQFBm"
      },
      "id": "Rv8vxFHtQFBm",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "o5tIkQ95_2Hc"
      },
      "id": "o5tIkQ95_2Hc",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "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": "3.11.12"
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}