python-selenium-spider/main.py

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import time
import run

download_dir = r'E:\Repository\python-selenium-spider\download'

proxies = {
    "http": "socks5://127.0.0.1:1080",
    "https": "socks5://127.0.0.1:1080",
}

if __name__ == '__main__':
    options = webdriver.ChromeOptions()
    options.add_argument('lang=zh-CN')
    options.add_argument(
        'user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36')
    options.add_argument(r'--user-data-dir=E:\Repository\python-selenium-spider\tmp\UserData')
    options.add_argument('--disable-gpu')  # 如果不加这个选项，有时定位会出现问题
    # options.add_argument('--headless')  # 增加无界面选项

    options.add_experimental_option("prefs", {
        "download.default_directory": download_dir
    })

    service = webdriver.ChromeService(r"./driver/chromedriver.exe")
    driver = webdriver.Chrome(service=service,options=options)
    # driver.maximize_window()
    # driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
    #     "source": """
    #             Object.defineProperty(navigator, 'webdriver', {
    #               get: () => undefined
    #             })
    #             """
    # })

    try:
        with open("./stealth.min.js") as f:
            driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
                "source": f.read()
            })

        run.main(driver=driver, download_dir=download_dir, proxies=proxies)
        time.sleep(86400)
    finally:
        pass
        # driver.quit()