scraper.py

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
import time
from bs4 import BeautifulSoup
import tempfile



def scrape_website(website):
    print("Launching chrome browser...")

    chrome_driver_path = "/usr/bin/chromedriver"
    options = webdriver.ChromeOptions()

    # Essential arguments for headless environments like Hugging Face
    options.add_argument("--headless")
    options.add_argument("--no-sandbox")
    options.add_argument("--disable-dev-shm-usage")

    # Use a unique user data directory to prevent session conflicts
    unique_user_data_dir = tempfile.mkdtemp()
    options.add_argument(f"--user-data-dir={unique_user_data_dir}")

    driver = webdriver.Chrome(service=Service(chrome_driver_path), options=options)

    try:
        driver.get(website)
        print("Page Loaded...")
        html = driver.page_source

        return html

    finally:
        driver.quit()


def extract_body_content(html_content):
    soup = BeautifulSoup(html_content,"html.parser")
    body_content = soup.body
    if body_content:
        return str(body_content)
    return ""

def clean_body_content(body_content):
    soup = BeautifulSoup(body_content,"html.parser")

    for script_or_style in soup(["script","style"]):
        script_or_style.extract()
    
    cleaned_content = soup.get_text(separator="\n")
    cleaned_content = "\n".join(
        line.strip() for line in cleaned_content.splitlines() if line.strip()
    )

    return cleaned_content

def split_dom_content(dom_content,max_length=60000):
    return [
        dom_content[i:i+max_length] for i in range(0,len(dom_content),max_length)
    ]