playwright的使用


1 安裝playwright

# 安裝
pip install playwright
# 安裝 Chromium、Firefox 和 WebKit瀏覽器命令
playwright install

2 啟動瀏覽器

from playwright.sync_api import sync_playwright
with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page()
    page.goto("http://playwright.dev")
    print(page.title())
    browser.close()

3 帶參數和代理啟動瀏覽器

chrome 參數說明網站 https://blog.csdn.net/mimishy2000/article/details/88315347

firefox 參數說明網站 https://blog.huati365.com/3ad5f64ade276769

from playwright.sync_api import sync_playwright
from playwright_stealth import stealth_sync

# playwright_stealth  這個第三方模塊可執行
p = sync_playwright().start()
chrome_path = r"C:\Chrome\chrome.exe"
user_data = r"C:\test"

chrome_param = [
    '--disable-popup-blocking',
    '--disable-blink-features=AutomationControlled',
    '--disable-bundled-ppapi-flash',
    '--ignore-ssl-errors',
    '--ignore-certificate-errors',
    '--disable-gpu',
    '--disable-webrtc-encryption',
    '--disable_non_proxied_udp',
    'lang=en-us'
]

proxy = {"server": "socks5://192.168.50.115:5000"}

browser = p.chromium.launch_persistent_context(headless=False,
                                               args=chrome_param,  # 瀏覽器參數列表 chrome,firefox,webkit都可以通過這個來設定參數
                                               executable_path=chrome_path,# 設置瀏覽器的可執行文件
                                               user_data_dir=user_data, # 設置瀏覽器緩存路徑
                                               
                                               user_agent="Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",
                                               ignore_default_args=['--enable-automation'],  # 這個可以直接看函數內的列表參數說明
                                               chromium_sandbox=False,  # 禁用chrome的方式 
                                               ignore_https_errors=True,
                                               proxy=proxy  # 設置代理
                                               )

# 這里不要用new_page的方法 它在打開瀏覽器的時候會多打開新的標簽頁
page = browser.pages[0]
# page = browser.new_page()
stealth_sync(page)
page.goto('https://ip.voidsec.com/')

page.wait_for_timeout(600)
# 關閉瀏覽器
bbrowser.close()
p.stop()

4 火狐瀏覽器啟動

from playwright.sync_api import sync_playwright
import time
from playwright_stealth import stealth_sync

user_data = r"C:\test_f"
firefox_path = r"C:\firefox\firefox.exe"

p = sync_playwright().start()


firefox_arg = [
    "intl.accept_languages=zh-CN",
]

proxy = {"server": "socks5://192.168.50.115:5000"}

# 這里重新打開一次會出現打不開頁面的情況 需要把firefox的緩存清掉在打開
browser = p.firefox.launch_persistent_context(headless=False, user_data_dir=user_data, executable_path=firefox_path,
                                              ignore_https_errors=True, 
                                              args=firefox_arg   # 此參數未生效
                                             )
page = browser.pages[0]
stealth_sync(page)
page.goto("https://bot.sannysoft.com/")

page.wait_for_timeout(30000)

browser.close()
p.stop()


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM