services/_driver.py

"""
_driver.py  –  Shared Selenium Chrome driver factory.
All scrapers import _create_driver() from here so that Docker env-vars
(CHROME_BIN, CHROMEDRIVER_PATH) are respected in one place.
"""
from __future__ import annotations

import os

from selenium import webdriver
from selenium.webdriver.chrome.service import Service


def _create_driver(mobile: bool = False) -> webdriver.Chrome:
    """
    Return a headless Chrome/Chromium instance tuned for Docker.

    Picks up:
      CHROME_BIN        – path to chromium binary   (default: /usr/bin/chromium)
      CHROMEDRIVER_PATH – path to chromedriver       (default: /usr/bin/chromedriver)
    """
    chrome_bin = os.environ.get("CHROME_BIN", "/usr/bin/chromium")
    driver_bin = os.environ.get("CHROMEDRIVER_PATH", "/usr/bin/chromedriver")

    options = webdriver.ChromeOptions()
    options.binary_location = chrome_bin

    # ── Headless & sandbox flags ──────────────────────────────────────────────
    options.add_argument("--headless=new")
    options.add_argument("--no-sandbox")
    options.add_argument("--disable-dev-shm-usage")
    options.add_argument("--disable-gpu")
    options.add_argument("--disable-software-rasterizer")
    options.add_argument("--disable-extensions")
    options.add_argument("--disable-infobars")
    options.add_argument("--disable-notifications")
    options.add_argument("--disable-popup-blocking")
    options.add_argument("--disable-blink-features=AutomationControlled")
    options.add_argument("--ignore-certificate-errors")
    options.add_argument("--window-size=1920,1080")
    options.add_argument("--remote-debugging-port=0")  # avoid port conflicts

    # ── User-Agent ────────────────────────────────────────────────────────────
    if mobile:
        options.add_argument(
            "--user-agent=Mozilla/5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) "
            "AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Mobile/15E148 Safari/604.1"
        )
    else:
        options.add_argument(
            "--user-agent=Mozilla/5.0 (X11; Linux x86_64) "
            "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
        )

    options.add_experimental_option("excludeSwitches", ["enable-automation", "enable-logging"])
    options.add_experimental_option("useAutomationExtension", False)

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

    # Hide webdriver fingerprint
    driver.execute_cdp_cmd(
        "Page.addScriptToEvaluateOnNewDocument",
        {"source": "Object.defineProperty(navigator,'webdriver',{get:()=>undefined})"},
    )
    return driver