scraper.py

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from bs4 import BeautifulSoup
import os
from shutil import which


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

    chrome_driver_path = which("chromedriver")
    chrome_binary_path = which("chromium-browser") or which("chromium")

    if not chrome_driver_path or not chrome_binary_path:
        raise EnvironmentError("chromedriver or chromium-browser not found in PATH")

    options = webdriver.ChromeOptions()
    options.binary_location = chrome_binary_path
    options.add_argument("--headless")
    options.add_argument("--no-sandbox")
    options.add_argument("--disable-dev-shm-usage")

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

    try:
        driver.get(website)
        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
    return str(body_content) if body_content else ""

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")
    return "\n".join(line.strip() for line in cleaned_content.splitlines() if line.strip())

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)]