{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1e45263e",
   "metadata": {},
   "source": [
    "# Web Data Extraction and Summarization using openAI Latest model gpt-5-mini"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df155151",
   "metadata": {},
   "source": [
    "####         Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "588f8e43",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import requests\n",
    "from dotenv import load_dotenv\n",
    "from bs4 import BeautifulSoup\n",
    "from IPython.display import Markdown, display\n",
    "from openai import OpenAI "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5925769",
   "metadata": {},
   "source": [
    "#### load api key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6cca85ec",
   "metadata": {},
   "outputs": [],
   "source": [
    "load_dotenv(override=True)\n",
    "api_key = os.getenv('OPENAI_API_KEY')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56703f80",
   "metadata": {},
   "source": [
    "#### ScrapWebsite using  BeautifulSoup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3d60c909",
   "metadata": {},
   "outputs": [],
   "source": [
    "headers = {\n",
    " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n",
    "}\n",
    "\n",
    "class ScrapeWebsite:\n",
    "\n",
    "    def __init__(self, url):\n",
    "        \"\"\" Scraping Website which provides title and content\"\"\"\n",
    "        self.url = url\n",
    "        response = requests.get(self.url, headers=headers)\n",
    "        soup = BeautifulSoup(response.content, 'html.parser')\n",
    "        self.title = soup.title.string if soup.title else \"No title found\"\n",
    "        for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
    "            irrelevant.decompose()\n",
    "        self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a8b73c27",
   "metadata": {},
   "source": [
    "#### System Prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4a0c3bda",
   "metadata": {},
   "outputs": [],
   "source": [
    "system_prompt = \"You are an analyst that analyses the content of the website \\\n",
    "    provides summary and ignore text related to navigation. Respond in markdown.\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9117963b",
   "metadata": {},
   "source": [
    "#### User Prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ab164d55",
   "metadata": {},
   "outputs": [],
   "source": [
    "def user_prompt_for(website):\n",
    "    user_prompt = f\"You are looking at a website titled {website.title}\"\n",
    "    user_prompt += \"\\nThe contents of this website is as follows; Please provide short summary in Markdown. Please include news and \\\n",
    "        announcements\"\n",
    "    user_prompt+=website.text\n",
    "    return user_prompt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de7423fb",
   "metadata": {},
   "source": [
    "#### Format messages in openAI standard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "47c82247",
   "metadata": {},
   "outputs": [],
   "source": [
    "def messages_for(website):\n",
    "    return [\n",
    "        {\"role\":\"system\", \"content\": system_prompt},\n",
    "        {\"role\":\"user\", \"content\": user_prompt_for(website)}\n",
    "    ]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e9bb6e1",
   "metadata": {},
   "source": [
    "#### Summarise the content in website using openAI latest model gpt-5-mini"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "068d6bb2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def summarise(url):\n",
    "    website = ScrapeWebsite(url)\n",
    "    openai = OpenAI()\n",
    "    response = openai.chat.completions.create(model=\"gpt-5-mini\", messages=messages_for(website))\n",
    "    return response.choices[0].message.content"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7e6e9da6",
   "metadata": {},
   "source": [
    "#### Show summary as Markdown"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cd86c2ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "def display_summary(url):\n",
    "    summary = summarise(url)\n",
    "    display(Markdown(summary))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed5e50d2",
   "metadata": {},
   "source": [
    "#### Output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "74a056b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "display_summary(\"https://www.firstpost.com/world/united-states/\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llms",
   "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": "3.11.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}