261 lines
9.4 KiB
Plaintext
261 lines
9.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "2588fbba",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Website Analysis and Summarization with Selenium and OpenAI\n",
|
|
"\n",
|
|
"> This notebook demonstrates how to extract and summarize the main content of any website using Selenium for dynamic extraction and OpenAI for generating concise summaries in Mexican Spanish.\n",
|
|
"\n",
|
|
"## Overview\n",
|
|
"This notebook provides a workflow to automatically analyze websites, extract relevant text, and generate a short summary using a language model. Navigation elements are ignored, focusing on news, announcements, and main content.\n",
|
|
"\n",
|
|
"## Features\n",
|
|
"- Extracts relevant text from web pages using Selenium and BeautifulSoup.\n",
|
|
"- Generates automatic summaries using OpenAI's language models.\n",
|
|
"- Presents results in markdown format.\n",
|
|
"\n",
|
|
"## Requirements\n",
|
|
"- Python 3.8+\n",
|
|
"- Google Chrome browser installed\n",
|
|
"- The following Python packages:\n",
|
|
" - selenium\n",
|
|
" - webdriver-manager\n",
|
|
" - beautifulsoup4\n",
|
|
" - openai\n",
|
|
" - python-dotenv\n",
|
|
" - requests\n",
|
|
"- An OpenAI API key (project key, starting with `sk-proj-`)\n",
|
|
"- Internet connection\n",
|
|
"\n",
|
|
"## How to Use\n",
|
|
"1. Install the required packages:\n",
|
|
" ```bash\n",
|
|
" pip install selenium webdriver-manager undetected-chromedriver beautifulsoup4 openai python-dotenv requests\n",
|
|
" ```\n",
|
|
"2. Add your OpenAI API key to a `.env` file as `OPENAI_API_KEY`.\n",
|
|
"3. Run the notebook cells in order. You can change the target website URL in the code to analyze different sites.\n",
|
|
"4. The summary will be displayed in markdown format below the code cell.\n",
|
|
"\n",
|
|
"**Note:** Some websites may block automated access. The notebook includes options to simulate a real user and avoid bot detection, but results may vary depending on the site's protections.\n",
|
|
"\n",
|
|
"---"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "dc7c2ade",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Imports\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",
|
|
"from selenium import webdriver\n",
|
|
"from selenium.webdriver.chrome.service import Service\n",
|
|
"from selenium.webdriver.common.by import By\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 webdriver_manager.chrome import ChromeDriverManager\n",
|
|
"import undetected_chromedriver as uc"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a2d21987",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Load the environment variables from .env\n",
|
|
"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(\"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": "bbb3a8ed",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"openai = OpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5313aa64",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class Website:\n",
|
|
" def __init__(self, url, headless=True, wait_time=10):\n",
|
|
" self.url = url # Website URL to analyze\n",
|
|
" self.title = None # Title of the website\n",
|
|
" self.text = None # Extracted text from the website\n",
|
|
" \n",
|
|
" # Chrome options configuration for Selenium\n",
|
|
" options = Options()\n",
|
|
" if headless:\n",
|
|
" options.add_argument(\"--headless=new\") # Run Chrome in headless mode (no window)\n",
|
|
" options.add_argument(\"--disable-gpu\") # Disable GPU acceleration\n",
|
|
" options.add_argument(\"--no-sandbox\") # Disable Chrome sandbox (required for some environments)\n",
|
|
" options.add_argument(\"--window-size=1920,1080\") # Set window size to simulate a real user\n",
|
|
" # Simulate a real user-agent to avoid bot detection\n",
|
|
" options.add_argument(\"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36\")\n",
|
|
" \n",
|
|
" # Initialize Chrome WebDriver\n",
|
|
" self.driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)\n",
|
|
" self.driver.get(url) # Open the URL in the browser\n",
|
|
" \n",
|
|
" try:\n",
|
|
" # Wait until the <body> element is present in the page\n",
|
|
" WebDriverWait(self.driver, wait_time).until(EC.presence_of_element_located((By.TAG_NAME, \"body\")))\n",
|
|
" html = self.driver.page_source # Get the full HTML of the page\n",
|
|
" soup = BeautifulSoup(html, 'html.parser') # Parse HTML with BeautifulSoup\n",
|
|
" self.title = soup.title.string if soup.title else 'No title found' # Extract the title\n",
|
|
" if soup.body:\n",
|
|
" # Remove irrelevant elements from the body\n",
|
|
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
|
|
" irrelevant.decompose()\n",
|
|
" # Extract clean text from the body\n",
|
|
" self.text = soup.body.get_text(separator='\\n', strip=True)\n",
|
|
" else:\n",
|
|
" self.text = \"No body found\" # If no body is found, indicate it\n",
|
|
" except Exception as e:\n",
|
|
" print(f\"Error accessing the site: {e}\") # Print error to console\n",
|
|
" self.text = \"Error accessing the site\" # Store error in the attribute\n",
|
|
" finally:\n",
|
|
" self.driver.quit() # Always close the browser, whether or not an error occurred"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e902c6b2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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 in Mexican Spanish.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "eaee8f36",
|
|
"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": "code",
|
|
"execution_count": null,
|
|
"id": "9ac4ed8b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Creates messages for the OpenAI API\n",
|
|
"def messages_for(website):\n",
|
|
" return [\n",
|
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": user_prompt_for(website)}\n",
|
|
" ]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "1536d537",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Creates a summary for the given URL\n",
|
|
"def summarize(url):\n",
|
|
" website = Website(url)\n",
|
|
" response = openai.chat.completions.create(\n",
|
|
" model = \"gpt-4o-mini\",\n",
|
|
" messages = messages_for(website)\n",
|
|
" )\n",
|
|
" return response.choices[0].message.content"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "fe135339",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Shows the summary for the given URL\n",
|
|
"def display_summary(url):\n",
|
|
" summary = summarize(url)\n",
|
|
" display(Markdown(summary))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a301ab4e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"display_summary(\"https://openai.com/\")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "venv",
|
|
"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": "3.11.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|