Automatización de Navegador con Playwright

#!/usr/bin/env python3
"""
Auto-generated Playwright scraping script.
Target: https://www.infojobs.net/empresas
Generated: 2026-06-12T18:11:22
Client: LeadFlow CRM — extraccion de leads para SDRs
"""

import asyncio, json, random, csv, os
from playwright.async_api import async_playwright

# ── Configuración ──────────────────────────────────────────
URL       = "https://www.infojobs.net/empresas"
CONTAINER = ".company-card"
FIELDS    = {
    "company_name":   ".company-name",
    "company_sector": ".company-sector",
    "company_city":   ".company-city",
    "company_size":   ".company-size",
    "company_url":    ".company-url a[href]",
}
NEXT_SELECTOR = "button[aria-label='Siguiente página']"
MAX_PAGES     = 100

USER_AGENTS = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/120.0.0.0",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 Chrome/120.0.0.0",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 Chrome/120.0.0.0",
]

# ── Extracción de items por página ─────────────────────────
async def extract_items(page, container_sel, field_map):
    items = []
    cards = await page.query_selector_all(container_sel)
    for card in cards:
        item = {}
        for name, selector in field_map.items():
            el = await card.query_selector(selector)
            if el:
                item[name] = (await el.text_content() or "").strip()
            else:
                item[name] = None
        items.append(item)
    return items

# ── Paginación con delay humano ────────────────────────────
async def scrape_all_pages(page, max_pages=MAX_PAGES):
    all_items = []
    for page_num in range(max_pages):
        print(f"Scraping página {page_num + 1}...")
        items = await extract_items(page, CONTAINER, FIELDS)
        all_items.extend(items)

        next_btn = page.locator(NEXT_SELECTOR)
        if await next_btn.count() == 0 or await next_btn.is_disabled():
            break

        await next_btn.click()
        await page.wait_for_load_state("networkidle")
        await asyncio.sleep(random.uniform(0.8, 2.5))  # delay humano

    return all_items

# ── Main ───────────────────────────────────────────────────
async def main():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(
            viewport={"width": 1920, "height": 1080},
            user_agent=random.choice(USER_AGENTS),
        )
        page = await context.new_page()

        # Eliminar flag navigator.webdriver
        await page.add_init_script(
            "Object.defineProperty(navigator,'webdriver',{get:()=>undefined});"
        )

        await page.goto(URL, wait_until="networkidle")
        data = await scrape_all_pages(page)

        # Exportar JSON
        with open("leads.json", "w", encoding="utf-8") as f:
            json.dump(data, f, indent=2, ensure_ascii=False)

        # Exportar CSV para LeadFlow CRM import
        if data:
            with open("leads.csv", "w", newline="", encoding="utf-8") as f:
                writer = csv.DictWriter(f, fieldnames=data[0].keys())
                writer.writeheader()
                writer.writerows(data)

        print(f"✓ {len(data)} empresas extraídas → leads.json + leads.csv")
        await browser.close()

if __name__ == "__main__":
    asyncio.run(main())