以对象的方式访问html中的标签，比正则表达式更好用的方式获取html中的内容，linq方式直接获取所有的链接，更加先进的c#版本爬虫开源库

这是我本人自己写的一个开源库，现已经发布到nuget，可以直接在vs的nuget包管理中搜索到，或者可以到nuget官网下载：https://www.nuget.org/packages/ZmjConvert/，也可以到我的个人网站上下载源码：https://www.zhaimaojun.cn/P/C%23%e6%a0%87%e7%ad%be%e7%b1%bb%e6%96%87%e6%9c%ac%e5%ba%8f%e5%88%97%e5%8c%96%e5%ba%93/

本包是.NET standard标准库包，可以在.NET core，.NET，.NET framework等多种项目中直接使用，我本人也是在多种环境中使用这个包，没有任何问题的，我本人主要用来提取网页上的链接，图片，可显示文本等内容。

先安装这个包，然后就可以使用了，下面给出了一些使用方式的模板：

第一步 序列化html

/**先安装我的nuget包，名字为ZmjConvert(by 钟国庆)*/
/**引入命名空间*/
using ZmjConvert;

/**这是html源码的序列化*/
var dts = GetSource();//获取html源码，可以现下或者读取html文件，dts需要是string类型的html内容
if (!HtmlElement.TryParse(dts, out var eles, out var err))
{
    OnDownloadErrorHappend($"无法序列化url:{surl}");//反序列化失败
    return;
}
var srcurl = new Uri(surl);//这是html的源地址的当前文档的url，用于将当前所有节点中相对路径解析为绝对路径时使用
eles = eles.ListElement();//列出所有的子元素，就是将所有的节点提取为一个list，方便使用linq，或者使用foreach循环来遍历，当然原来的标签结构是不会改变的。

 

/**这是部分html标签源码的反序列化，比如富文本编辑器的内容*/
try
{
    var labstr = Gethtmlstr();//获取部分标签的html源码，比如富文本编辑器
    var eles = CHtmlElement<HtmlElement>.Parse(htmlstr);//反序列化标签组
    return eles;//反序列化成功后返回结构对象
}
catch (Exception e)
{
    throw e;//反序列化失败
}

第二步 获取html文档的标题

/**获取文档标题*/
var title = eles.GetWebTitle();
/**获取文档的keywords*/
var keywords = eles.Find("meta", "name", "keywords").FirstOrDefault()?["keywords"];
/**获取文档的description*/
var description = eles.Find("meta", "name", "description").FirstOrDefault()?["description"];

第三步 提取所有的img标签的src，也就是获取所有页面上的图片

/**这是获取所有img标签的src属性内容*/
var imgs = new List<Uri>();
foreach (var e in eles.Find("img", "src"))
{
    var furi = new Uri(srcurl, e["src"]);
    imgs.Add(furi);
}
/**这是提取所有img标签的data-src属性，因为有些网站为了降低流量成本，img标签的src属性中使用的是缩略图，而data-src中使用的才是原图*/
var imgs = new List<Uri>();
foreach (var e in eles.Find("img", "data-src"))
{
    var furi = new Uri(srcurl, e["data-src"]);
    imgs.Add(furi);
}

第四步 提取所有的a标签的href，也就是获取所有页面上的链接

/**使用我写的方法提取所有a的href*/
var links = eles.GetAllLink(new Uri("当前html页面的url"), "a","href");
/**使用linq方法提取a的href*/
var links = eles.Find("a", "href").Select(x => x["href"]).ToList();

第五步 提取所有可视文本，并保持换行，并且保持链接的有效

/**使用我写的方法提取所有的可视文本*/
var txt = eles.GetText("br,div,li","script,title");//其中第一个参数是强制换行的标签名，后一个参数是忽略内容的标签名

/**提取所有的可视文本的代码示例*/
/// <summary>
/// 获取所有可现实的文本内容
/// </summary>
/// <param name="element"></param>
/// <returns></returns>
public static string GetText(this IEnumerable<HtmlElement> element, string splittags = "br,div,li", string excepttags = "script,title")
{
    var etgs = excepttags.Split(",".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
    var tgs = splittags.Split(",".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
    var tsts = new List<string>();
    //将所有的文本内容读出
    var sb = new StringBuilder();
    foreach (var item in element.Where(x => !etgs.Contains(x.TagName)))
    {
        if (tgs.Contains(item.TagName))
        {
            sb.Append(HttpUtility.HtmlDecode(item.InnerText));
            var innt = sb.ToString();
            tsts.Add(innt);
            sb.Clear();
        }
        else if (item.TagName == "a" && item.Attributes.ContainsKey("href")) sb.Append($"<a href=\"{HttpUtility.HtmlDecode(item.Attributes["href"])}\">{HttpUtility.HtmlDecode(item.InnerText)}</a>");
        else if (!item.InnerText.Contains('<')) sb.Append(HttpUtility.HtmlDecode(item.InnerText));
    }
    return string.Join("\r\n", tsts);
}

第六步 找到特定的标签

/**查找包含main-content样式类的div*/
var e = eles.FirstOrDefault(x => x.TagName == "div" && x.Attributes.ContainsKey("class") && x.Attributes["class"].ToLower().Contains("main-content"));//linq方式
var e = eles.Find("div", "class", "main-content").FirstOrDefault();//使用我写的Find方法更简单

/**查找id为mainp的p标签*/
var e = eles.FirstOrDefault(x => x.TagName == "p" && x.Attributes.ContainsKey("id") && x.Attributes["id"].ToLower() == "mainp");//linq方式
var e = eles.Find("p", "id", "mainp").FirstOrDefault();//使用我写的Find方法更简单

第七步 一些网站的抓取方法，已经开源到了网站nuget，版本是:1.1.2，以下是源码：

/// <summary>
/// http://yskhd.com/archives
/// </summary>
internal class ArchivesPictureCatcher : HtmlCatcher, IHtmlCatcher
{
    public override bool CanApplicableHost(string url)
    {
        return url.Contains("://yskhd.com/archives/");
    }
    public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
    {
        if (string.IsNullOrWhiteSpace(surl)) return;
        OnProgChanged($"正在抓取url：{surl}", 0);
        var dts = GetSource.Invoke(surl);
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        string title = eles.GetWebTitle();
        var imgs = new List<Uri>();
        foreach (var e in eles.Find("img", "src").Where(x => x.Attributes["src"].EndsWith("285x285.jpg")))
        {
            var furl = e["src"].Replace("285x285", "scaled");
            var furi = new Uri(srcurl, furl);
            imgs.Add(furi);
        }
        GC.Collect();
        var ph = GetPathFrom(title, savepath, saveAsNewFolder);
        foreach (var img in imgs)
        {
            var fm = img.Segments.Last().Trim('/');
            var fp = System.IO.Path.Combine(ph, fm);
            DownLoadToFile(img.AbsoluteUri, fp);
        }
        OnProgChanged($"抓取到{imgs.Count}图片从页面：{title}", 0);
    }
    private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
    {
        if (!saveAsNewFolder) return savepath;
        StringTool.GetLastLabel(ref title);
        title = title.ReplacePathInvalidChars();
        var ph = System.IO.Path.Combine(savepath, title);
        if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
        return ph;
    }
}

/// <summary>
/// 电影天堂网
/// </summary>
internal class Dy2018Catcher : HtmlCatcher, IHtmlCatcher
{
    /// <summary>
    /// 电影天堂网
    /// </summary>
    public override bool CanApplicableHost(string url)
    {
        return url.Contains("://www.dy2018.com");
    }
    public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
    {
        if (string.IsNullOrWhiteSpace(surl)) return;
        OnProgChanged($"正在抓取url：{surl}", 0);
        var dts = GetSource.Invoke(surl);
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        string title = eles.GetWebTitle();
        IEnumerable<HtmlElement> deles = eles.Find("div", "id", "zoom");
        if (deles is null || deles.Count() < 1)
        {
            OnDownloadErrorHappend($"没找到可抓取内容，页面:{title}");
            return;
        }
        deles = deles.ListElement();
        var imgs = new List<string>();
        foreach (var e in deles.Find("img", "src"))
        {//封面图片或者其他图片
            var furi = new Uri(srcurl, e["src"]);
            imgs.Add(furi.AbsoluteUri);
        }
        var links = new List<string>();
        foreach (var e in deles.Find("a", "href"))
        {//所有的下载链接或者外站连接
            var furi = new Uri(srcurl, e["src"]);
            var sit = e.InnerText;
            sit = sit.Length < 50 ? sit : "获取方式";
            links.Add($"{sit} {furi.AbsoluteUri}");
        }
        var txt = deles.GetText();
        var dir = eles.Find("div", "class", "position");
        IEnumerable<HtmlElement> dirs = (IEnumerable<HtmlElement>)dir?.ListElement() ?? Array.Empty<HtmlElement>();
        var tags = dirs.Find("a").Select(x => x.InnerText.Trim('/').Replace("类型：", string.Empty));
        GC.Collect();
        var ph = GetPathFrom(title, savepath, saveAsNewFolder);
        base.TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
        System.IO.File.WriteAllLines(TextPath, new[] { surl, "", "", }.Concat(links).Concat(new[] { "", "" }).Concat(tags).Concat(new[] { txt }));
        foreach (var img in imgs)
        {
            var url = new Uri(img);
            var fm = url.Segments.Last().Trim('/');
            var fp = System.IO.Path.Combine(ph, fm);
            if (fm == "dico.jpg") continue;
            DownLoadToFile(img, fp);
        }
        OnProgChanged($"抓取到{imgs.Count}图片{links.Count}连接从页面：{title}", 0);
    }
    private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
    {
        if (!saveAsNewFolder) return savepath;
        title = title.Replace("_电影天堂", string.Empty).ReplacePathInvalidChars();
        var ph = System.IO.Path.Combine(savepath, title.ToUpper());
        if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
        return ph;
    }
}

/// <summary>
/// fap
/// </summary>
internal class FapCatcher : HtmlCatcher, IHtmlCatcher
{
    public override bool CanApplicableHost(string url)
    {
        return url.Contains("://fap-nation.com");
    }
    public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
    {
        if (string.IsNullOrWhiteSpace(surl)) return;
        OnProgChanged($"正在抓取url：{surl}", 0);
        //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
        var dts = GetSource.Invoke(surl);
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        if (!(eles.FirstOrDefault(x => x.TagName == "main" && x.Attributes.ContainsKey("class") && x.Attributes["class"].Contains("col-md-9") && x.Attributes["class"].Contains("col-md-push-3")) is HtmlElement me)) return;
        string title = eles.GetWebTitle();
        eles = me.Children.Find("article").ListElement(null, "script,style,!--");
        var ph = GetPathFrom(title, savepath, saveAsNewFolder, out var ver);
        var imgs = new List<string>();
        foreach (var e in eles.Find("img", "src"))
        {//封面图片或者其他图片
            var furl = e["src"];
            if (!furl.StartsWith("http") || furl.Contains("loading")) continue;
            var furi = new Uri(srcurl, furl);
            imgs.Add(furi.AbsoluteUri);
        }
        var links = new List<string>();
        //提取所有的下载链接
        var tags = new List<string>();//从中获取标签
        var tgs = eles.Find("div", "class", "tags").ListElement();
        foreach (var t in tgs.Find("a"))
        {
            var tag = t.InnerText.Trim().ToUpper();
            if (string.IsNullOrWhiteSpace(tag)) continue;
            tags.Add(tag);
            //if (Trans(tag, out var tts)) tags.Add(tts);
        }
        var tsts = new List<string>();
        //将所有的文本内容读出
        var sb = new StringBuilder();
        var os = "";
        var ttgs = new[] { "br", "div", "li", };
        foreach (var item in eles)
        {
            var nt = item.InnerText;
            if (ttgs.Contains(item.TagName))
            {
                sb.Append(nt);
                if (item.TagName == "div" && item.Attributes.ContainsKey("class") && item.Attributes["class"].StartsWith("vc_")) continue;
                var innt = sb.ToString();
                tsts.Add(innt);
                sb.Clear();
            }
            else if (item.InnerText.StartsWith("Download"))
            {
                var itxt = item.InnerText.Trim();
                os = itxt.Substring(itxt.LastIndexOf(' ') + 1);
            }
            else if (item.TagName == "a" && item.Attributes.ContainsKey("href"))
            {
                if (item["href"].IndexOfAny("#?=-".ToArray()) < 0) links.Add($"{item.InnerText} {item["href"]}");
                else if (item.Attributes["href"].StartsWith("https://fap-nation.com/fndlnwd/")) links.Add($"{os}({ver}) {item["href"]}");
                else if (!string.IsNullOrWhiteSpace(nt) && !item.Attributes["href"].Contains("tab-") && !item.Attributes["href"].Contains("#copy")) sb.Append($"<a href=\"{item["href"]}\" target=\"_blank\">{nt}</a>");
                else sb.Append(nt);
            }
            else if (!nt.Contains('<')) sb.Append(nt);
        }
        var txt = string.Join("\r\n", tsts);
        GC.Collect();
        TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
        System.IO.File.WriteAllLines(TextPath, new[] { surl, "", }.Concat(links).Concat(new[] { "", }).Concat(tags).Concat(new[] { "", txt }));
        foreach (var img in imgs)
        {
            var url = new Uri(img);
            var fm = url.Segments.Last().Trim('/');
            var fp = System.IO.Path.Combine(ph, fm);
            DownLoadToFile(img, fp);
        }
        OnProgChanged($"抓取到{imgs.Count}图片从页面：{title}", 0);
    }
    protected string GetPathFrom(string title, string savepath, bool saveAsNewFolder, out string ver)
    {
        ver = string.Empty;
        if (!saveAsNewFolder) return savepath;
        StringTool.GetLastLabel(ref title, "  ");
        var lbs = StringTool.GetLabels1(ref title);
        ver = lbs[0];
        title = $"[][{lbs[1]}][{lbs[1]}][][][]{title}".ReplacePathInvalidChars();
        string ph = null;
        ph = ph ?? System.IO.Path.Combine(savepath, title.ToUpper());
        if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
        return ph;
    }
}

/// <summary>
/// https://pcgamestorrents.com/?s=
/// </summary>
internal class PcgamestorrentsCatcher : HtmlCatcher, IHtmlCatcher
{
    /// <summary>
    /// 游戏下载网站的内容
    /// </summary>
    public override bool CanApplicableHost(string url)
    {
        return url.Contains("//pcgamestorrents.com/");
    }
    public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
    {
        if (string.IsNullOrWhiteSpace(surl)) return;
        OnProgChanged($"正在抓取url：{surl}", 0);
        //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
        var dts = GetSource.Invoke(surl);
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        string title = eles.GetWebTitle();
        var contente = eles.Find("div", "class", "uk-margin-medium-top");
        eles = contente.ListElement();
        var imgs = new List<string>();
        foreach (var e in eles.Find("img", "class", "igg-image-content"))
        {//封面图片或者其他图片
            var furl = e["src"];
            var furi = new Uri(srcurl, furl);
            imgs.Add(furi.AbsoluteUri);
        }
        var tsts = new List<string>();
        //将所有的文本内容读出
        var sb = new StringBuilder();
        foreach (var item in eles)
        {
            var tgs = new[] { "br", "button", "div", "li", "p", };
            if (tgs.Contains(item.TagName))
            {
                sb.Append(item.InnerText);
                tsts.Add(sb.ToString());
                sb.Clear();
            }
            else sb.Append(item.InnerText);
        }
        var tags = new List<string>();//从文本中获取标签
        var tgstr = tsts.First(x => x.Trim().ToUpper().StartsWith("GENRE")).ToUpper().Replace("GENRE", "").Replace(":", "").Trim().Split(',') ?? new string[0];
        foreach (var t in tgstr.Where(x => x.Length < 25))
        {
            var tag = HttpUtility.HtmlDecode(t);
            tag = Regex.Replace(tag, @"[^ \/\w]", "").Trim().ToUpper();
            tags.Add(tag);
            //if (Trans(tag, out var tts)) tags.Add(tts);
        }
        var dev = tsts.First(x => x.Trim().ToUpper().StartsWith("DEVELOPER")).ToUpper().Replace("DEVELOPER", "").Replace(":", "").Trim();
        var pub = tsts.First(x => x.Trim().ToUpper().StartsWith("PUBLISHER")).ToUpper().Replace("PUBLISHER", "").Replace(":", "").Trim();
        GC.Collect();
        var ph = GetPathFrom(title, dev, pub, savepath, saveAsNewFolder, out var ver);
        TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
        System.IO.File.WriteAllLines(TextPath, new[] { surl, "", $"Win({ver.Replace("« PCGamesTorrents", "").Replace("-", "").Trim()})(磁力) ", "", "破解版", }.Concat(tags).Concat(new[] { "", }).Concat(tsts));
        foreach (var img in imgs)
        {
            var url = new Uri(img);
            var fm = url.Segments.Last().Trim('/');
            var fp = System.IO.Path.Combine(ph, fm);
            DownLoadToFile(img, fp);
        }
        OnProgChanged($"抓取到{imgs.Count}图片从页面：{title}", 0);
    }
    private string GetPathFrom(string title, string dev, string pub, string savepath, bool saveAsNewFolder, out string ver)
    {
        ver = Regex.Match(title, " - .*?$").Value;
        if (!string.IsNullOrWhiteSpace(ver)) title = title.Replace(ver, "");
        if (!saveAsNewFolder) return savepath;
        var ed = title.IndexOf(HttpUtility.HtmlDecode(" &laquo; "));
        title = ed <= 0 ? title : title.Substring(0, ed);
        title = $"[][{pub}][{dev}][][][完结]{title}".ReplacePathInvalidChars();
        var ph = System.IO.Path.Combine(savepath, title);
        if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
        return ph;
    }
}

/// <summary>
/// http://www.mfsft.com/
/// </summary>
internal class XiuRenPictureCatcher : HtmlCatcher, IHtmlCatcher
{
    public override bool CanApplicableHost(string url)
    {
        return url.Contains("://www.mfsft.com/");
    }
    public override async void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
    {
        if (string.IsNullOrWhiteSpace(surl)) return;
        OnProgChanged($"正在抓取url：{surl}", 0);
        //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
        var dts = GetSource.Invoke(surl);
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        string title = eles.GetWebTitle();
        var imgs = new List<Uri>();
        foreach (var e in eles.Find("img", "src").Where(x => x.Attributes.ContainsKey("alt")))
        {
            var furl = e["src"];
            var furi = new Uri(srcurl, furl);
            imgs.Add(furi);
        }
        var lsted = srcurl.PathAndQuery.LastIndexOfAny(new[] { '.', '_' });
        var lstst = srcurl.PathAndQuery.LastIndexOf('/');
        var ststr = srcurl.PathAndQuery.Substring(lstst, lsted - lstst).Trim('/');
        var others = new List<string>();
        others.AddRange(eles.Find("a", "href").Where(x => x.Attributes["href"].StartsWith(ststr)).Select(x => x.Attributes["href"]));
        foreach (var e in others.Distinct())
        {//抓取其他的页面
            var furi = new Uri(srcurl, e);
            await Task.Run(() => Catch(furi.AbsoluteUri, imgs));
        }
        GC.Collect();
        //browser.GetCookieManager().VisitUrlCookies(main.Url, true,vt);
        var ph = GetPathFrom(title, savepath, saveAsNewFolder);
        foreach (var img in imgs)
        {
            var fm = img.Segments.Last().Trim('/').Replace("_gzip.aspx", "");
            var fp = System.IO.Path.Combine(ph, fm);
            DownLoadToFile(img.AbsoluteUri, fp);
        }
        OnProgChanged($"抓取到{imgs.Count}图片从页面：{title}", 0);
        //main.Browser.ShowDevTools();
    }
    private void Catch(string surl, List<Uri> array)
    {
        var dts = Encoding.UTF8.GetString(DownloadDatas(surl));
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        string title = eles.GetWebTitle();
        foreach (var e in eles.Find("img", "src").Where(x => x.Attributes.ContainsKey("alt")))
        {
            var furl = e["src"];
            var furi = new Uri(srcurl, furl);
            array.Add(furi);
        }
    }
    private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
    {
        if (!saveAsNewFolder) return savepath;
        title = title.Substring(0, title.LastIndexOfAny(new[] { ' ', ',', '-' }));
        title = title.ReplacePathInvalidChars();
        var ph = System.IO.Path.Combine(savepath, title);
        if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
        return ph;
    }
}

/// <summary>
/// https://www.xpiaohua.com
/// </summary>
internal class XpiaohuaCatcher : HtmlCatcher, IHtmlCatcher
{
    /// <summary>
    /// 游戏下载网站的内容
    /// </summary>
    public override bool CanApplicableHost(string url)
    {
        return url.Contains("://www.xpiaohua.com");
    }
    public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
    {
        if (string.IsNullOrWhiteSpace(surl)) return;
        OnProgChanged($"正在抓取url：{surl}", 0);
        //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
        var dts = GetSource.Invoke(surl);
        if (!HtmlElement.TryParse(dts, out var eles, out var err))
        {
            OnDownloadErrorHappend($"无法序列化url:{surl}");
            return;
        }
        var srcurl = new Uri(surl);
        eles = eles.ListElement();//列出所有的子元素
        string title = eles.GetWebTitle();
        IEnumerable<HtmlElement> deles = eles.Find("div", "id", "showinfo");
        if (deles is null || deles.Count() < 1)
        {
            OnDownloadErrorHappend($"没找到可抓取内容，页面:{title}");
            return;
        }
        deles = deles.ListElement();
        var imgs = new List<string>();
        foreach (var e in deles.Find("img", "src"))
        {//封面图片或者其他图片
            var furl = e["src"];
            var furi = new Uri(srcurl, furl);
            imgs.Add(furi.AbsoluteUri);
        }
        var links = new List<string>();
        foreach (var e in deles.Find("a", "href"))
        {//所有的下载链接或者外站连接
            var furl = e["href"];
            Uri furi = null;
            try { furi = new Uri(srcurl, furl); } catch { continue; }
            links.Add($"{e.InnerText}: {furi.AbsoluteUri}");
        }
        var txts = deles.GetText();
        var ststr = "◎类　　别　";
        var st = txts.IndexOf(ststr);
        var ed = txts.IndexOf("◎语　　言　");
        var tagstr = txts.Substring(st + ststr.Length, ed - st - ststr.Length);
        var tags = tagstr.Split("/".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
        GC.Collect();
        var ph = GetPathFrom(title, savepath, saveAsNewFolder);
        TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
        System.IO.File.WriteAllLines(TextPath, new[] { surl, "", }.Concat(links).Concat(new[] { "", }).Concat(tags).Concat(new[] { "", txts }));
        foreach (var img in imgs)
        {
            var url = new Uri(img);
            var fm = url.Segments.Last().Trim('/');
            var fp = System.IO.Path.Combine(ph, fm);
            if (fm == "dico.jpg") continue;
            DownLoadToFile(img, fp);
        }
        OnProgChanged($"抓取到{imgs.Count}图片{links.Count}连接从页面：{title}", 0);
    }
    private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
    {
        if (!saveAsNewFolder) return savepath;
        title = title.Replace("_新飘花电影网", string.Empty).ReplacePathInvalidChars();
        var ph = System.IO.Path.Combine(savepath, title.ToUpper());
        if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
        return ph;
    }
}

还有的htmlCatcher在我的包里~

有需求的也可以找我代写catcher