SSR vs CSR

# Détection automatique SSR vs CSR et stratégie de scraping adaptée
import httpx
from playwright.async_api import async_playwright
from selectolax.parser import HTMLParser

async def detect_rendering_mode(url: str) -> dict:
    """Détecte si un site utilise SSR ou CSR"""
    
    # 1. Fetch HTML brut (sans JavaScript)
    async with httpx.AsyncClient() as client:
        response = await client.get(url)
        raw_html = response.text
    
    raw_tree = HTMLParser(raw_html)
    raw_text_content = raw_tree.body.text(strip=True) if raw_tree.body else ""
    
    # 2. Fetch avec JavaScript (Playwright)
    async with async_playwright() as p:
        browser = await p.chromium.launch()
        page = await browser.new_page()
        await page.goto(url, wait_until='networkidle')
        rendered_html = await page.content()
        await browser.close()
    
    rendered_tree = HTMLParser(rendered_html)
    rendered_text_content = rendered_tree.body.text(strip=True) if rendered_tree.body else ""
    
    # 3. Comparer les contenus
    raw_length = len(raw_text_content)
    rendered_length = len(rendered_text_content)
    
    content_ratio = raw_length / rendered_length if rendered_length > 0 else 0
    
    # Heuristique : si le HTML brut contient moins de 30% du contenu rendu
    is_csr = content_ratio < 0.3
    
    return {
        'url': url,
        'mode': 'CSR' if is_csr else 'SSR',
        'raw_content_length': raw_length,
        'rendered_content_length': rendered_length,
        'content_ratio': round(content_ratio, 2),
        'recommendation': 'Use headless browser' if is_csr else 'Simple HTTP fetch is sufficient'
    }

async def adaptive_scrape(url: str):
    """Scrape adaptatif selon le mode de rendu détecté"""
    mode_info = await detect_rendering_mode(url)
    
    if mode_info['mode'] == 'SSR':
        # Scraping simple et rapide
        async with httpx.AsyncClient() as client:
            response = await client.get(url)
            return HTMLParser(response.text)
    else:
        # Scraping avec JavaScript rendering
        async with async_playwright() as p:
            browser = await p.chromium.launch()
            page = await browser.new_page()
            await page.goto(url, wait_until='networkidle')
            html = await page.content()
            await browser.close()
            return HTMLParser(html)