113 lines
3.4 KiB
Plaintext
113 lines
3.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3ba06289-d17a-4ccd-85f5-2b79956d4e59",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"!pip install selenium"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "eabbbc62-1de1-4883-9b3e-9c90145ea6c5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from selenium import webdriver\n",
|
|
"from selenium.webdriver.chrome.options import Options\n",
|
|
"from selenium.webdriver.chrome.service import Service\n",
|
|
"from bs4 import BeautifulSoup\n",
|
|
"import time\n",
|
|
"import os \n",
|
|
"\n",
|
|
"class Website:\n",
|
|
" def __init__(self, url, driver_path=None, wait_time=3):\n",
|
|
" self.url = url\n",
|
|
" self.wait_time = wait_time\n",
|
|
"\n",
|
|
" # Headless Chrome settings\n",
|
|
" options = Options()\n",
|
|
" # options.add_argument(\"--headless\") \n",
|
|
" # Headless mode runs the browser in the background (invisible).\n",
|
|
" # However, some websites (like openai.com) block headless browsers.\n",
|
|
" # So if this line is active, the page may not load correctly and you may not get the full content.\n",
|
|
" options.add_argument(\"--disable-gpu\")\n",
|
|
" options.add_argument(\"--no-sandbox\")\n",
|
|
" options.add_argument(\"--window-size=1920x1080\")\n",
|
|
"\n",
|
|
" # Driver path\n",
|
|
" if driver_path:\n",
|
|
" service = Service(executable_path=driver_path)\n",
|
|
" else:\n",
|
|
" service = Service() \n",
|
|
"\n",
|
|
" # Start browser\n",
|
|
" driver = webdriver.Chrome(service=service, options=options)\n",
|
|
" driver.get(url)\n",
|
|
"\n",
|
|
" # Wait for the loading page\n",
|
|
" time.sleep(self.wait_time)\n",
|
|
"\n",
|
|
" # Take page source\n",
|
|
" html = driver.page_source\n",
|
|
" driver.quit()\n",
|
|
"\n",
|
|
" # Analysis with BeautifulSoup \n",
|
|
" soup = BeautifulSoup(html, 'html.parser')\n",
|
|
" self.title = soup.title.string if soup.title else \"No title found\"\n",
|
|
"\n",
|
|
" # Clean irrelevant tags\n",
|
|
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
|
|
" irrelevant.decompose()\n",
|
|
"\n",
|
|
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "852c52e2-bd4d-4bb9-94ef-e498c33f1a89",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"site = Website(\"https://openai.com\", driver_path=\"/Users/gizemmervedemir/Downloads/chromedriver-mac-arm64/chromedriver\")\n",
|
|
"print(\"Title:\", site.title)\n",
|
|
"print(\"\\nFirst 500 character:\\n\", site.text[:500])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "7620c685-c35c-4d6b-aaf1-a3da98f19ca7",
|
|
"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
|
|
}
|