{ "cells": [ { "cell_type": "code", "execution_count": null, "id": "52b6cbd9-5248-4083-94c5-e4d657e44da1", "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\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", "\n", "class Website:\n", " url: str\n", " title: str\n", " text: str\n", "\n", " def __init__(self, url):\n", " self.url = url\n", "\n", " options = Options()\n", "\n", " options.add_argument(\"--no-sandbox\")\n", " options.add_argument(\"--disable-dev-shm-usage\")\n", "\n", " service = Service(PATH_TO_CHROME_DRIVER)\n", " driver = webdriver.Chrome(service=service, options=options)\n", " driver.get(url)\n", "\n", " input(\"Please complete the verification in the browser and press Enter to continue...\")\n", " page_source = driver.page_source\n", " driver.quit()\n", "\n", " soup = BeautifulSoup(page_source, 'html.parser')\n", " self.title = soup.title.string if soup.title else \"No title found\"\n", " for irrelevant in soup([\"script\", \"style\", \"img\", \"input\"]):\n", " irrelevant.decompose()\n", " self.text = soup.get_text(separator=\"\\n\", strip=True)" ] }, { "cell_type": "code", "execution_count": null, "id": "23818353-a2fc-4c2f-be1e-0677399fa1b5", "metadata": {}, "outputs": [], "source": [ "website = Website(\"https://edwarddonner.com\")" ] }, { "cell_type": "code", "execution_count": null, "id": "4452b88b-58aa-4f50-ad39-c5a1c2363025", "metadata": {}, "outputs": [], "source": [ "website = Website(\"https://openai.com\")" ] }, { "cell_type": "code", "execution_count": null, "id": "0250145b-2afb-48d6-b43f-daf64329e7af", "metadata": {}, "outputs": [], "source": [ "print(website.text)" ] }, { "cell_type": "code", "execution_count": null, "id": "97699263-4a06-4e06-905b-9db4a554b75c", "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 }