2.使用 HtmlAgilityPack 解析 HTML 文档
2.HtmlAgilityPack
private static string GetHtml(string url) { ChromeOptions options = new ChromeOptions(); // 不显示浏览器 options.AddArgument("--headless"); // GPU加速可能会导致Chrome出现黑屏及CPU占用率过高 options.AddArgument("--nogpu"); // 设置chrome启动时size大小 options.AddArgument("--window-size=10,10"); // 堆代码 duidaima.com using (var driver = new ChromeDriver(options)) { try { driver.Manage().Window.Minimize(); driver.Navigate().GoToUrl(url); // 等待页面动态加载完成 Thread.Sleep(5000); // 返回页面源码 return driver.PageSource; } catch (NoSuchElementException) { Console.WriteLine("找不到该元素"); return string.Empty; } } }解析 HTML 文档
class VideoInfo { public string Title { get; set; } public string Href { get; set; } public string ImgUrl { get; set; } }定义解析函数,返回视频信息列表:
private static List<VideoInfo> GetVideoInfos(string url) { List<VideoInfo> videoInfos = new List<VideoInfo>(); // 加载文档 var html = GetHtml(url); var htmlDoc = new HtmlDocument(); htmlDoc.LoadHtml(html); // 解析文档,先定位到视频列表标签 var xpath = "/html/body/div[2]/div[4]/div/div/div[1]/div[2]/div/div"; var htmlNodes = htmlDoc.DocumentNode.SelectNodes(xpath); // 循环解析它的子节点视频信息 foreach (var node in htmlNodes) { var titleNode = node.SelectSingleNode("a[2]"); var imgNode = node.SelectSingleNode("a[1]/div[1]/picture/source[1]"); var title = titleNode.InnerText; var href = titleNode.Attributes["href"].Value.Trim('/'); var imgUrl = imgNode.Attributes["srcset"].Value.Split('@')[0].Trim('/'); videoInfos.Add(new VideoInfo { Title = title, Href = href, ImgUrl = imgUrl }); } return videoInfos; }视频列表标签的 XPath 路径是通过浏览器调试工具,在指定标签上右键 复制完整的XPath 得到:
static void Main(string[] args) { var url = @"https://space.bilibili.com/401315430"; var videoInfos = GetVideoInfos(url); foreach (var videoInfo in videoInfos) { Console.WriteLine(videoInfo.Title); Console.WriteLine(videoInfo.Href); Console.WriteLine(videoInfo.ImgUrl); Console.WriteLine(); } Console.ReadKey(); }结果如下:
等一下,好妹妹 www.bilibili.com/video/BV1uyxLeJEM9 i0.hdslb.com/bfs/archive/46a15065d1b6722a04696ffaaa2235287ceaa452.jpg 一口一个?你的超甜辣椒 www.bilibili.com/video/BV1AQsDeiEn1 i0.hdslb.com/bfs/archive/d93d47d67323ee284483e963ffed34fb9884cf61.jpg这里只是演示爬取动态页面的方法,如果想获取B站UP主的视频信息,建议直接使用 API 请求数据。