diff --git a/week1/community-contributions/day1-webscraping-playwright.ipynb b/week1/community-contributions/day1-webscraping-playwright.ipynb new file mode 100644 index 0000000..75cc7d8 --- /dev/null +++ b/week1/community-contributions/day1-webscraping-playwright.ipynb @@ -0,0 +1,224 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "id": "4e2a9393-7767-488e-a8bf-27c12dca35bd", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "\n", + "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\n", + "\n", + "# If you get an error running this cell, then please head over to the troubleshooting notebook!" + ] + }, + { + "cell_type": "markdown", + "id": "6900b2a8-6384-4316-8aaa-5e519fca4254", + "metadata": {}, + "source": [ + "# Connecting to OpenAI\n", + "\n", + "The next cell is where we load in the environment variables in your `.env` file and connect to OpenAI.\n", + "\n", + "## Troubleshooting if you have problems:\n", + "\n", + "Head over to the [troubleshooting](troubleshooting.ipynb) notebook in this folder for step by step code to identify the root cause and fix it!\n", + "\n", + "If you make a change, try restarting the \"Kernel\" (the python process sitting behind this notebook) by Kernel menu >> Restart Kernel and Clear Outputs of All Cells. Then try this notebook again, starting at the top.\n", + "\n", + "Or, contact me! Message me or email ed@edwarddonner.com and we will get this to work.\n", + "\n", + "Any concerns about API costs? See my notes in the README - costs should be minimal, and you can control it at every point. You can also use Ollama as a free alternative, which we discuss during Day 2." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "7b87cadb-d513-4303-baee-a37b6f938e4d", + "metadata": {}, + "outputs": [], + "source": [ + "# Load environment variables in a file called .env\n", + "\n", + "load_dotenv()\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(\"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" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "019974d9-f3ad-4a8a-b5f9-0a3719aea2d3", + "metadata": {}, + "outputs": [], + "source": [ + "openai = OpenAI()\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, or try the below line instead:\n", + "# openai = OpenAI(api_key=\"your-key-here-starting-sk-proj-\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "abdb8417-c5dc-44bc-9bee-2e059d162699", + "metadata": {}, + "outputs": [], + "source": [ + "# Define our system prompt - you can experiment with this later, changing the last sentence to 'Respond in markdown in Spanish.\"\n", + "\n", + "system_prompt = \"You are an assistant that analyzes the contents of a website \\\n", + "and provides a short summary, ignoring text that might be navigation related. \\\n", + "Respond in markdown.\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f0275b1b-7cfe-4f9d-abfa-7650d378da0c", + "metadata": {}, + "outputs": [], + "source": [ + "# A function that writes a User Prompt that asks for summaries of websites:\n", + "\n", + "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; \\\n", + "please provide a short summary of this website in markdown. \\\n", + "If it includes news or announcements, then summarize these too.\\n\\n\"\n", + " user_prompt += website.text\n", + " return user_prompt" + ] + }, + { + "cell_type": "markdown", + "id": "36ed9f14-b349-40e9-a42c-b367e77f8bda", + "metadata": {}, + "source": [ + "## An extra exercise for those who enjoy web scraping\n", + "\n", + "You may notice that if you try the course example with \"https://openai.com\" - it doesn't work! That's because OpenAI has a fancy website that uses Javascript. There are many ways around this that some of you might be familiar with. Below an example created with Playwright." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "dca2768e", + "metadata": {}, + "outputs": [], + "source": [ + "! pip install playwright\n", + "! playwright install" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "682eff74-55c4-4d4b-b267-703edbc293c7", + "metadata": {}, + "outputs": [], + "source": [ + "import asyncio\n", + "from playwright.async_api import async_playwright\n", + "import nest_asyncio\n", + "from bs4 import BeautifulSoup\n", + "import time\n", + "\n", + "nest_asyncio.apply()\n", + "\n", + "class Website:\n", + " title: str\n", + " text: str\n", + " url: str\n", + "\n", + " def __init__(self, url):\n", + " self.url = url\n", + " \n", + " async def run(self, playwright):\n", + " browser = await playwright.chromium.launch(headless=False)\n", + " page = await browser.new_page()\n", + " await page.goto(self.url)\n", + " await page.wait_for_load_state('load')\n", + " \n", + " # Extract data from the page\n", + " self.title = await page.title()\n", + " text = await page.content()\n", + " await browser.close()\n", + " \n", + " soup = BeautifulSoup(text, 'html.parser')\n", + " for irrelevant in soup([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.get_text(separator=\"\\n\", strip=True)\n", + " \n", + " async def main(self):\n", + " async with async_playwright() as playwright:\n", + " await self.run(playwright) \n", + " \n", + "def messages_for(website):\n", + " return [\n", + " {\"role\": \"system\", \"content\": system_prompt},\n", + " {\"role\": \"user\", \"content\": user_prompt_for(website)}\n", + " ]\n", + "\n", + "if __name__ == \"__main__\":\n", + " site = Website('https://openai.com')\n", + " asyncio.run(site.main())\n", + " response = openai.chat.completions.create(\n", + " model = \"gpt-4o-mini\",\n", + " messages = messages_for(site)\n", + " )\n", + "\n", + " web_summary = response.choices[0].message.content\n", + " display(Markdown(web_summary))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "69218dec-749c-412d-84a0-40a10fd80c73", + "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": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}