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
        var te = new textextractor(sourcefile);
        te.extract();
        sr.close();
        
        //将页面保存为图片
        //await page.screenshotasync(@"d:\1.png",
        //    new screenshotoptions() { fullpage = true, type = screenshottype.png });
    }
}