{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "31d3c4a4-5442-4074-b812-42d60e0a0c04",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:29.195103Z",
     "start_time": "2025-04-26T11:54:29.192394Z"
    }
   },
   "outputs": [],
   "source": [
    "# In this example we read a footbal (soccer) game stat and we create a narration about the game as we are running a podcast\n",
    "# use this website as an example: https://understat.com/match/27683"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cf45e9d5-4913-416c-9880-5be60a96c0e6",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:30.218768Z",
     "start_time": "2025-04-26T11:54:30.215752Z"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import requests\n",
    "from dotenv import load_dotenv\n",
    "from IPython.display import Markdown, display\n",
    "from bs4 import BeautifulSoup\n",
    "from openai import OpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "af8fea69-60aa-430c-a16c-8757b487e07a",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:31.218616Z",
     "start_time": "2025-04-26T11:54:31.214154Z"
    }
   },
   "outputs": [],
   "source": [
    "load_dotenv(override=True)\n",
    "api_key = os.getenv('OPENAI_API_KEY')\n",
    "\n",
    "# Check the key\n",
    "\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(\n",
    "        \"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(\n",
    "        \"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!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "daee94d2-f82b-43f0-95d1-15370eda1bc7",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:32.216785Z",
     "start_time": "2025-04-26T11:54:32.183600Z"
    }
   },
   "outputs": [],
   "source": [
    "openai = OpenAI()\n",
    "url = \"https://understat.com/match/27683\"\n",
    "\n",
    "# If this doesn't work, try Kernel menu >> Restart Kernel and Clear Outputs Of All Cells, then run the cells from the top of this notebook down.\n",
    "# If it STILL doesn't work (horrors!) then please see the Troubleshooting notebook in this folder for full instructions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0712dd1d-b6bc-41c6-84ec-d965f696f7aa",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:33.025841Z",
     "start_time": "2025-04-26T11:54:33.023289Z"
    }
   },
   "outputs": [],
   "source": [
    "system_prompt = (\"You are a football (soccer) analyst. Yuo are used to read stats of football \\\n",
    "                 games and extract relevant information. You are asked to be a podcast host and \\\n",
    "                  you need to create a narration of the game based on the stats you read and based \\\n",
    "                  on the play by play moves (the one with minutes upfront). You're talking to the \\\n",
    "                 general audience so try to use a easy language and do not be too much telegraphic\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "70c972a6-8af6-4ff2-a338-6d7ba90e2045",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:33.730097Z",
     "start_time": "2025-04-26T11:54:33.725360Z"
    }
   },
   "outputs": [],
   "source": [
    "# Some websites need you to use proper headers when fetching them:\n",
    "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 Website:\n",
    "    def __init__(self, url):\n",
    "        \"\"\"\n",
    "        Create this Website object from the given url using the BeautifulSoup library\n",
    "        \"\"\"\n",
    "        self.url = url\n",
    "        response = requests.get(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)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4ccc1ba81c76ffb9",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:40.042357Z",
     "start_time": "2025-04-26T11:54:40.040384Z"
    }
   },
   "outputs": [],
   "source": [
    "def create_user_prompt(game):\n",
    "    user_prompt = f\"You are looking at {game.title} football game\"\n",
    "    user_prompt += \"\\nThis is the entire webpage of the game \\\n",
    "    Please provide a narration of the game in  markdown. \\\n",
    "    Focus only on what happened on the game and the stats and ignore all the standings and anything else.\\n\\n\"\n",
    "    user_prompt += game.text\n",
    "    return user_prompt\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e729956758b4d7b5",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:40.699042Z",
     "start_time": "2025-04-26T11:54:40.696698Z"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "82b71c1a-895a-48e7-a945-13e615bb0096",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:41.316244Z",
     "start_time": "2025-04-26T11:54:41.314110Z"
    }
   },
   "outputs": [],
   "source": [
    "# Define messages with system_prompt and user_prompt\n",
    "def messages_for(system_prompt_input, user_prompt_input):\n",
    "    return [\n",
    "        {\"role\": \"system\", \"content\": system_prompt_input},\n",
    "        {\"role\": \"user\", \"content\": user_prompt_input}\n",
    "    ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "854dc42e-2bbd-493b-958f-c20484908300",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-26T11:54:55.239164Z",
     "start_time": "2025-04-26T11:54:41.987168Z"
    }
   },
   "outputs": [],
   "source": [
    "# And now: call the OpenAI API.\n",
    "game = Website(url)\n",
    "\n",
    "response = openai.chat.completions.create(\n",
    "    model=\"gpt-4o-mini\",\n",
    "    messages=messages_for(system_prompt, create_user_prompt(game))\n",
    ")\n",
    "\n",
    "# Response is provided in Markdown and displayed accordingly\n",
    "display(Markdown(response.choices[0].message.content))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "758d2cbe-0f80-4572-8724-7cba77f701dd",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}