358 lines
12 KiB
Plaintext
358 lines
12 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"id": "53211323-6a09-452a-b471-98e22d92bfc2",
|
|
"metadata": {},
|
|
"source": [
|
|
"# 🌐 WebPage Summarizer\n",
|
|
"---\n",
|
|
"- 🌍 **Task:** Summarizing webpage content using AI. \n",
|
|
"- 🧠 **Model:** OpenAI's ``gpt-4o-mini`` and ``llama3.2:3b`` for text summarization. \n",
|
|
"- 🕵️♂️ **Data Extraction:** Selenium for handling both static and JavaScript-rendered websites. \n",
|
|
"- 📌 **Output Format:** Markdown-formatted summaries. \n",
|
|
"- 🔗 **Scope:** Processes only the given webpage URL (not the entire site). \n",
|
|
"- 🚀 **Tools:** Python, Requests, Selenium, BeautifulSoup, OpenAI API, Ollama. \n",
|
|
"- 🧑💻 **Skill Level:** Beginner.\n",
|
|
"\n",
|
|
"🛠️ Requirements\n",
|
|
"- ⚙️ Hardware: ✅ CPU is sufficient — no GPU required\n",
|
|
"- 🔑 OpenAI API Key (for GPT model)\n",
|
|
"- Install Ollama and pull llama3.2:3b or another lightweight model\n",
|
|
"- Google Chrome browser installed\n",
|
|
"\n",
|
|
"**✨ This script handles both JavaScript and non-JavaScript websites using Selenium with Chrome WebDriver for reliable content extraction from modern web applications.**\n",
|
|
"\n",
|
|
"Let's get started and automate website summarization! 🚀\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"---\n",
|
|
"📢 Find more LLM notebooks on my [GitHub repository](https://github.com/lisekarimi/lexo)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "d70aa4b0",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 🛠️ Environment Setup & Dependencies"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ebf2fa36",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%pip install selenium webdriver-manager"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "1dcf1d9d-c540-4900-b14e-ad36a28fc822",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# ===========================\n",
|
|
"# System & Environment\n",
|
|
"# ===========================\n",
|
|
"import os\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"\n",
|
|
"# ===========================\n",
|
|
"# Web Scraping\n",
|
|
"# ===========================\n",
|
|
"import time\n",
|
|
"from bs4 import BeautifulSoup\n",
|
|
"from selenium import webdriver\n",
|
|
"from selenium.webdriver.chrome.options import Options\n",
|
|
"from selenium.webdriver.common.by import By\n",
|
|
"from selenium.webdriver.support.ui import WebDriverWait\n",
|
|
"from selenium.webdriver.support import expected_conditions as EC\n",
|
|
"\n",
|
|
"# ===========================\n",
|
|
"# AI-related\n",
|
|
"# ===========================\n",
|
|
"from IPython.display import Markdown, display\n",
|
|
"from openai import OpenAI\n",
|
|
"import ollama"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "cc20642b",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 🔐 Model Configuration & Authentication"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8598c299-05ca-492e-b085-6bcc2f7dda0d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"load_dotenv(override=True)\n",
|
|
"api_key = os.getenv('OPENAI_API_KEY')\n",
|
|
"\n",
|
|
"if not api_key:\n",
|
|
" raise ValueError(\"OPENAI_API_KEY not found in environment variables\")\n",
|
|
"\n",
|
|
"print(\"✅ API key loaded successfully!\")\n",
|
|
"openai = OpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8098defb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"MODEL_OPENAI = \"gpt-4o-mini\"\n",
|
|
"MODEL_OLLAMA = \"llama3.2:3b\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "2bd1d83f",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 🌐 Web Scraping Infrastructure"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c6fe5114",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class WebsiteCrawler:\n",
|
|
" def __init__(self, url):\n",
|
|
" self.url = url\n",
|
|
" self.title = \"\"\n",
|
|
" self.text = \"\"\n",
|
|
" self.scrape()\n",
|
|
"\n",
|
|
" def scrape(self):\n",
|
|
" try:\n",
|
|
" # Chrome options\n",
|
|
" chrome_options = Options()\n",
|
|
" chrome_options.add_argument(\"--headless\")\n",
|
|
" chrome_options.add_argument(\"--no-sandbox\")\n",
|
|
" chrome_options.add_argument(\"--disable-dev-shm-usage\")\n",
|
|
" chrome_options.add_argument(\"--disable-gpu\")\n",
|
|
" chrome_options.add_argument(\"--window-size=1920,1080\")\n",
|
|
" chrome_options.add_argument(\"--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36\")\n",
|
|
"\n",
|
|
" # Try to find Chrome\n",
|
|
" chrome_paths = [\n",
|
|
" r\"C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe\",\n",
|
|
" r\"C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe\",\n",
|
|
" r\"C:\\Users\\{}\\AppData\\Local\\Google\\Chrome\\Application\\chrome.exe\".format(os.getenv('USERNAME')),\n",
|
|
" ]\n",
|
|
"\n",
|
|
" chrome_binary = None\n",
|
|
" for path in chrome_paths:\n",
|
|
" if os.path.exists(path):\n",
|
|
" chrome_binary = path\n",
|
|
" break\n",
|
|
"\n",
|
|
" if chrome_binary:\n",
|
|
" chrome_options.binary_location = chrome_binary\n",
|
|
"\n",
|
|
" # Create driver\n",
|
|
" driver = webdriver.Chrome(options=chrome_options)\n",
|
|
" driver.set_page_load_timeout(30)\n",
|
|
"\n",
|
|
" print(f\"🔍 Loading: {self.url}\")\n",
|
|
" driver.get(self.url)\n",
|
|
"\n",
|
|
" # Wait for page to load\n",
|
|
" time.sleep(5)\n",
|
|
"\n",
|
|
" # Try to wait for main content\n",
|
|
" try:\n",
|
|
" WebDriverWait(driver, 10).until(\n",
|
|
" EC.presence_of_element_located((By.TAG_NAME, \"main\"))\n",
|
|
" )\n",
|
|
" except Exception:\n",
|
|
" try:\n",
|
|
" WebDriverWait(driver, 10).until(\n",
|
|
" EC.presence_of_element_located((By.TAG_NAME, \"body\"))\n",
|
|
" )\n",
|
|
" except Exception:\n",
|
|
" pass # Continue anyway\n",
|
|
"\n",
|
|
" # Get title and page source\n",
|
|
" self.title = driver.title\n",
|
|
" page_source = driver.page_source\n",
|
|
" driver.quit()\n",
|
|
"\n",
|
|
" print(f\"✅ Page loaded: {self.title}\")\n",
|
|
"\n",
|
|
" # Parse with BeautifulSoup\n",
|
|
" soup = BeautifulSoup(page_source, 'html.parser')\n",
|
|
"\n",
|
|
" # Remove unwanted elements\n",
|
|
" for element in soup([\"script\", \"style\", \"img\", \"input\", \"button\", \"nav\", \"footer\", \"header\"]):\n",
|
|
" element.decompose()\n",
|
|
"\n",
|
|
" # Get main content\n",
|
|
" main = soup.find('main') or soup.find('article') or soup.find('.content') or soup.find('body')\n",
|
|
" if main:\n",
|
|
" self.text = main.get_text(separator=\"\\n\", strip=True)\n",
|
|
" else:\n",
|
|
" self.text = soup.get_text(separator=\"\\n\", strip=True)\n",
|
|
"\n",
|
|
" # Clean up text\n",
|
|
" lines = [line.strip() for line in self.text.split('\\n') if line.strip() and len(line.strip()) > 2]\n",
|
|
" self.text = '\\n'.join(lines[:200]) # Limit to first 200 lines\n",
|
|
"\n",
|
|
" print(f\"📄 Extracted {len(self.text)} characters\")\n",
|
|
"\n",
|
|
" except Exception as e:\n",
|
|
" print(f\"❌ Error occurred: {e}\")\n",
|
|
" self.title = \"Error occurred\"\n",
|
|
" self.text = \"Could not scrape website content\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "d727feff",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 🧠 Prompt Engineering & Templates"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "02e3a673-a8a1-4101-a441-3816f7ab9e4d",
|
|
"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.\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "86bb80f9-9e7c-4825-985f-9b83fe50839f",
|
|
"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 a short summary of this website in markdown. 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": "89998b18-77aa-4aaf-a137-f0d078d61f75",
|
|
"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": "cde36d4f",
|
|
"metadata": {},
|
|
"source": [
|
|
"## 📝 Summarization "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5636affe",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def summarize_gpt(url):\n",
|
|
" \"\"\"Scrape website and summarize with GPT\"\"\"\n",
|
|
" site = WebsiteCrawler(url)\n",
|
|
"\n",
|
|
" if \"Error occurred\" in site.title or len(site.text) < 50:\n",
|
|
" print(f\"❌ Failed to scrape meaningful content from {url}\")\n",
|
|
" return\n",
|
|
"\n",
|
|
" print(\"🤖 Creating summary...\")\n",
|
|
"\n",
|
|
" # Create summary\n",
|
|
" response = openai.chat.completions.create(\n",
|
|
" model=MODEL_OPENAI,\n",
|
|
" messages=[\n",
|
|
" {\"role\": \"system\", \"content\": system_prompt},\n",
|
|
" {\"role\": \"user\", \"content\": user_prompt_for(site)}\n",
|
|
" ]\n",
|
|
" )\n",
|
|
"\n",
|
|
" web_summary = response.choices[0].message.content\n",
|
|
" display(Markdown(web_summary))\n",
|
|
"\n",
|
|
"summarize_gpt('https://openai.com')\n",
|
|
"# summarize_gpt('https://stripe.com')\n",
|
|
"# summarize_gpt('https://vercel.com')\n",
|
|
"# summarize_gpt('https://react.dev')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "90b9a8f8-0c1c-40c8-a4b3-e8e1fcd29df5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def summarize_ollama(url):\n",
|
|
" website = WebsiteCrawler(url)\n",
|
|
" response = ollama.chat(\n",
|
|
" model=MODEL_OLLAMA,\n",
|
|
" messages=messages_for(website))\n",
|
|
" display(Markdown(response['message']['content'])) # Generate and display output\n",
|
|
"\n",
|
|
"summarize_ollama('https://github.com')\n",
|
|
"# summarize_ollama('https://nextjs.org')"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.11.13"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|