legacy_scraper.py

"""
Legacy scraper implementation for performance comparison
"""

import chromedriver_autoinstaller
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By 
from selenium.common.exceptions import StaleElementReferenceException
import json
import time

chromedriver_autoinstaller.install()

def create_legacy_options():
    """Create legacy Chrome options"""
    options = Options()
    options.binary_location = "/usr/bin/chromium-browser"
    options.add_argument("--headless")
    options.add_argument("--no-sandbox")
    options.add_argument("--disable-dev-shm-usage")
    return options

def safe_get_attribute(elements, attr):
    """Legacy safe attribute extraction"""
    values = []
    for e in elements:
        try:
            value = e.get_attribute(attr)
            if value:
                values.append(value)
        except StaleElementReferenceException:
            continue  # Skip stale elements
    return values

def legacy_scraper(link: str):
    """Legacy scraper implementation - creates new driver each time"""
    options = create_legacy_options()
    driver = webdriver.Chrome(options=options)
    
    try:
        driver.get(link)
        time.sleep(2)  # Fixed delay for dynamic content
        
        try:
            page_text = driver.find_element(By.TAG_NAME, "body").text
        except StaleElementReferenceException:
            page_text = ""
        
        scripts = driver.find_elements(By.TAG_NAME, "script")
        links = driver.find_elements(By.TAG_NAME, "link")
        
        script_sources = safe_get_attribute(scripts, "src")
        link_sources = safe_get_attribute(links, "href")
        
        return {
            "page_text": page_text,
            "script_sources": script_sources,
            "link_sources": link_sources,
        }
    
    finally:
        driver.quit()