Web Scraping & Browser Automation

# Web Scraping & HTML DOM Parsing Simulation:
from html.parser import HTMLParser

raw_html_mock = """

    

        
Mechanical Keyboard
        ₹2,499.00
        In Stock
    
    

        
4K Monitor 27-inch
        ₹28,999.00
        Out of Stock
    

"""

class SimpleDOMScraper(HTMLParser):
    """Parses HTML mock text into structured product dictionaries."""
    def __init__(self):
        super().__init__()
        self.products = []
        self.current_tag = None
        self.current_item = {}

    def handle_starttag(self, tag, attrs):
        self.current_tag = tag
        attr_dict = dict(attrs)
        if attr_dict.get("class") == "product-card":
            self.current_item = {"id": attr_dict.get("data-id")}

    def handle_data(self, data):
        text = data.strip()
        if text:
            if self.current_tag == "h2":
                self.current_item["title"] = text
            elif self.current_tag == "span" and "₹" in text:
                self.current_item["price"] = text
            elif self.current_tag == "span" and ("Stock" in text):
                self.current_item["status"] = text
                if "title" in self.current_item:
                    self.products.append(self.current_item.copy())

# Execute Scraper:
scraper = SimpleDOMScraper()
scraper.feed(raw_html_mock)

print("--- 🛒 Scraped Product Catalog Output ---")
for p in scraper.products:
    print(f"• ID #{p['id']}: {p['title']:22} | Price: {p['price']:>10} | Availability: {p['status']}")

# Playwright & Selenium Headless Automation Pattern Reference:
"""
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

# 1. Configure Headless Chrome Browser:
chrome_options = Options()
chrome_options.add_argument("--headless=new") # Run in background without window
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument("--no-sandbox")

# 2. Launch WebDriver:
driver = webdriver.Chrome(options=chrome_options)

try:
    # 3. Navigate to dynamic web page:
    driver.get("https://example.com/login")

    # 4. Explicit Wait: Wait up to 10 seconds for dynamic element to render:
    username_input = WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.NAME, "username"))
    )

    # 5. Type credentials and click login:
    username_input.send_keys("balaji_dev")
    driver.find_element(By.NAME, "password").send_keys("SecretPass2026")
    driver.find_element(By.CSS_SELECTOR, "button[type='submit']").click()

    # 6. Capture full rendered page source or take screenshot:
    driver.save_screenshot("dashboard_verified.png")
    print("✅ Successfully logged in and captured screenshot!")

finally:
    driver.quit() # Always close browser process to free RAM!
"""
print("Browser Automation Blueprint Configured.")