风火编程--playwright爬虫

playwright爬虫基本用法

等待加载

page.wait_for_load_state(‘networkidle’)
text = page.content()

点击

demo

 with sync_playwright() as pw:
        browser = pw.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()
        page.goto(url)
        page.wait_for_load_state('networkidle')
        text = page.content()
        page.close()
        context.close()
        browser.close()
    info = parse_info(text)
    title = re.findall('''"Buy now:(.+?)",''', text)[0]
1
2
3
4
5
6
7
8
9
10
11
12

禁止加载图片

    page.route("**/*", lambda route: route.abort()
    if route.request.resource_type == "image"
    else route.continue_())
1
2
3

登录状态
保存

context.storage_state(path='login_data.json')
1

使用

context = browser.new_context(storage_state='login_data.json')
1