PuppeteerSharp读取页面完整HTML(.NetCore)

1.使用NUGET安装PuppeteerSharp

通过工具或者命令方式安装

2.初始化浏览器

await new BrowserFetcher().DownloadAsync(BrowserFetcher.DefaultRevision);

3.具体代码

using (Browser browser = await Puppeteer.LaunchAsync(new LaunchOptions { Headless = true }))

{

    using (var page = await browser.NewPageAsync())

    {

        //设置浏览器的页面大小

        await page.SetViewportAsync(new ViewPortOptions

        {

            Width = 1024,

            Height = 768

        });

        await page.GoToAsync("http://www.baidu.com");

        var html = await page.GetContentAsync();

        var sourceFile = "";

        var memoryStream = new MemoryStream(Encoding.Default.GetBytes(html));

        var sr = new StreamReader(memoryStream);

        sourceFile = sr.ReadToEnd();

        //针对源代码进行分析

        sr.Close();

        //将页面保存为图片

        //await page.ScreenshotAsync(@"D:\1.png",

        //    new ScreenshotOptions() { FullPage = true, Type = ScreenshotType.Png });

    }

}