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

 1 /**先安装我的nuget包,名字为ZmjConvert(by 钟国庆)*/
 2 /**引入命名空间*/
 3 using ZmjConvert;
 4 
 5 /**这是html源码的序列化*/
 6 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
 7 if (!HtmlElement.TryParse(dts, out var eles, out var err))
 8 {
 9     OnDownloadErrorHappend($"无法序列化url:{surl}");//反序列化失败
10     return;
11 }
12 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
13 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。

 

 1 /**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*/
 2 try
 3 {
 4     var labstr = Gethtmlstr();//获取部分标签的html源码,比如富文本编辑器
 5     var eles = CHtmlElement<HtmlElement>.Parse(htmlstr);//反序列化标签组
 6     return eles;//反序列化成功后返回结构对象
 7 }
 8 catch (Exception e)
 9 {
10     throw e;//反序列化失败
11 }

第二步 获取html文档的标题

1 /**获取文档标题*/
2 var title = eles.GetWebTitle();
3 /**获取文档的keywords*/
4 var keywords = eles.Find("meta", "name", "keywords").FirstOrDefault()?["keywords"];
5 /**获取文档的description*/
6 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

 1 /**这是获取所有img标签的src属性内容*/
 2 var imgs = new List<Uri>();
 3 foreach (var e in eles.Find("img", "src"))
 4 {
 5     var furi = new Uri(srcurl, e["src"]);
 6     imgs.Add(furi);
 7 }
 8 /**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*/
 9 var imgs = new List<Uri>();
10 foreach (var e in eles.Find("img", "data-src"))
11 {
12     var furi = new Uri(srcurl, e["data-src"]);
13     imgs.Add(furi);
14 }

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

1 /**使用我写的方法提取所有a的href*/
2 var links = eles.GetAllLink(new Uri("当前html页面的url"), "a","href");
3 /**使用linq方法提取a的href*/
4 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

 1 /**使用我写的方法提取所有的可视文本*/
 2 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
 3 
 4 /**提取所有的可视文本的代码示例*/
 5 /// <summary>
 6 /// 获取所有可现实的文本内容
 7 /// </summary>
 8 /// <param name="element"></param>
 9 /// <returns></returns>
10 public static string GetText(this IEnumerable<HtmlElement> element, string splittags = "br,div,li", string excepttags = "script,title")
11 {
12     var etgs = excepttags.Split(",".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
13     var tgs = splittags.Split(",".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
14     var tsts = new List<string>();
15     //将所有的文本内容读出
16     var sb = new StringBuilder();
17     foreach (var item in element.Where(x => !etgs.Contains(x.TagName)))
18     {
19         if (tgs.Contains(item.TagName))
20         {
21             sb.Append(HttpUtility.HtmlDecode(item.InnerText));
22             var innt = sb.ToString();
23             tsts.Add(innt);
24             sb.Clear();
25         }
26         else if (item.TagName == "a" && item.Attributes.ContainsKey("href")) sb.Append($"<a href=\"{HttpUtility.HtmlDecode(item.Attributes["href"])}\">{HttpUtility.HtmlDecode(item.InnerText)}</a>");
27         else if (!item.InnerText.Contains('<')) sb.Append(HttpUtility.HtmlDecode(item.InnerText));
28     }
29     return string.Join("\r\n", tsts);
30 }

第六步 找到特定的标签

1 /**查找包含main-content样式类的div*/
2 var e = eles.FirstOrDefault(x => x.TagName == "div" && x.Attributes.ContainsKey("class") && x.Attributes["class"].ToLower().Contains("main-content"));//linq方式
3 var e = eles.Find("div", "class", "main-content").FirstOrDefault();//使用我写的Find方法更简单
4 
5 /**查找id为mainp的p标签*/
6 var e = eles.FirstOrDefault(x => x.TagName == "p" && x.Attributes.ContainsKey("id") && x.Attributes["id"].ToLower() == "mainp");//linq方式
7 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:

 1 /// <summary>
 2 /// http://yskhd.com/archives
 3 /// </summary>
 4 internal class ArchivesPictureCatcher : HtmlCatcher, IHtmlCatcher
 5 {
 6     public override bool CanApplicableHost(string url)
 7     {
 8         return url.Contains("://yskhd.com/archives/");
 9     }
10     public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
11     {
12         if (string.IsNullOrWhiteSpace(surl)) return;
13         OnProgChanged($"正在抓取url:{surl}", 0);
14         var dts = GetSource.Invoke(surl);
15         if (!HtmlElement.TryParse(dts, out var eles, out var err))
16         {
17             OnDownloadErrorHappend($"无法序列化url:{surl}");
18             return;
19         }
20         var srcurl = new Uri(surl);
21         eles = eles.ListElement();//列出所有的子元素
22         string title = eles.GetWebTitle();
23         var imgs = new List<Uri>();
24         foreach (var e in eles.Find("img", "src").Where(x => x.Attributes["src"].EndsWith("285x285.jpg")))
25         {
26             var furl = e["src"].Replace("285x285", "scaled");
27             var furi = new Uri(srcurl, furl);
28             imgs.Add(furi);
29         }
30         GC.Collect();
31         var ph = GetPathFrom(title, savepath, saveAsNewFolder);
32         foreach (var img in imgs)
33         {
34             var fm = img.Segments.Last().Trim('/');
35             var fp = System.IO.Path.Combine(ph, fm);
36             DownLoadToFile(img.AbsoluteUri, fp);
37         }
38         OnProgChanged($"抓取到{imgs.Count}图片从页面:{title}", 0);
39     }
40     private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
41     {
42         if (!saveAsNewFolder) return savepath;
43         StringTool.GetLastLabel(ref title);
44         title = title.ReplacePathInvalidChars();
45         var ph = System.IO.Path.Combine(savepath, title);
46         if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
47         return ph;
48     }
49 }
 1 /// <summary>
 2 /// 电影天堂网
 3 /// </summary>
 4 internal class Dy2018Catcher : HtmlCatcher, IHtmlCatcher
 5 {
 6     /// <summary>
 7     /// 电影天堂网
 8     /// </summary>
 9     public override bool CanApplicableHost(string url)
10     {
11         return url.Contains("://www.dy2018.com");
12     }
13     public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
14     {
15         if (string.IsNullOrWhiteSpace(surl)) return;
16         OnProgChanged($"正在抓取url:{surl}", 0);
17         var dts = GetSource.Invoke(surl);
18         if (!HtmlElement.TryParse(dts, out var eles, out var err))
19         {
20             OnDownloadErrorHappend($"无法序列化url:{surl}");
21             return;
22         }
23         var srcurl = new Uri(surl);
24         eles = eles.ListElement();//列出所有的子元素
25         string title = eles.GetWebTitle();
26         IEnumerable<HtmlElement> deles = eles.Find("div", "id", "zoom");
27         if (deles is null || deles.Count() < 1)
28         {
29             OnDownloadErrorHappend($"没找到可抓取内容,页面:{title}");
30             return;
31         }
32         deles = deles.ListElement();
33         var imgs = new List<string>();
34         foreach (var e in deles.Find("img", "src"))
35         {//封面图片或者其他图片
36             var furi = new Uri(srcurl, e["src"]);
37             imgs.Add(furi.AbsoluteUri);
38         }
39         var links = new List<string>();
40         foreach (var e in deles.Find("a", "href"))
41         {//所有的下载链接或者外站连接
42             var furi = new Uri(srcurl, e["src"]);
43             var sit = e.InnerText;
44             sit = sit.Length < 50 ? sit : "获取方式";
45             links.Add($"{sit} {furi.AbsoluteUri}");
46         }
47         var txt = deles.GetText();
48         var dir = eles.Find("div", "class", "position");
49         IEnumerable<HtmlElement> dirs = (IEnumerable<HtmlElement>)dir?.ListElement() ?? Array.Empty<HtmlElement>();
50         var tags = dirs.Find("a").Select(x => x.InnerText.Trim('/').Replace("类型:", string.Empty));
51         GC.Collect();
52         var ph = GetPathFrom(title, savepath, saveAsNewFolder);
53         base.TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
54         System.IO.File.WriteAllLines(TextPath, new[] { surl, "", "", }.Concat(links).Concat(new[] { "", "" }).Concat(tags).Concat(new[] { txt }));
55         foreach (var img in imgs)
56         {
57             var url = new Uri(img);
58             var fm = url.Segments.Last().Trim('/');
59             var fp = System.IO.Path.Combine(ph, fm);
60             if (fm == "dico.jpg") continue;
61             DownLoadToFile(img, fp);
62         }
63         OnProgChanged($"抓取到{imgs.Count}图片{links.Count}连接从页面:{title}", 0);
64     }
65     private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
66     {
67         if (!saveAsNewFolder) return savepath;
68         title = title.Replace("_电影天堂", string.Empty).ReplacePathInvalidChars();
69         var ph = System.IO.Path.Combine(savepath, title.ToUpper());
70         if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
71         return ph;
72     }
73 }
  1 /// <summary>
  2 /// fap
  3 /// </summary>
  4 internal class FapCatcher : HtmlCatcher, IHtmlCatcher
  5 {
  6     public override bool CanApplicableHost(string url)
  7     {
  8         return url.Contains("://fap-nation.com");
  9     }
 10     public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
 11     {
 12         if (string.IsNullOrWhiteSpace(surl)) return;
 13         OnProgChanged($"正在抓取url:{surl}", 0);
 14         //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
 15         var dts = GetSource.Invoke(surl);
 16         if (!HtmlElement.TryParse(dts, out var eles, out var err))
 17         {
 18             OnDownloadErrorHappend($"无法序列化url:{surl}");
 19             return;
 20         }
 21         var srcurl = new Uri(surl);
 22         eles = eles.ListElement();//列出所有的子元素
 23         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;
 24         string title = eles.GetWebTitle();
 25         eles = me.Children.Find("article").ListElement(null, "script,style,!--");
 26         var ph = GetPathFrom(title, savepath, saveAsNewFolder, out var ver);
 27         var imgs = new List<string>();
 28         foreach (var e in eles.Find("img", "src"))
 29         {//封面图片或者其他图片
 30             var furl = e["src"];
 31             if (!furl.StartsWith("http") || furl.Contains("loading")) continue;
 32             var furi = new Uri(srcurl, furl);
 33             imgs.Add(furi.AbsoluteUri);
 34         }
 35         var links = new List<string>();
 36         //提取所有的下载链接
 37         var tags = new List<string>();//从中获取标签
 38         var tgs = eles.Find("div", "class", "tags").ListElement();
 39         foreach (var t in tgs.Find("a"))
 40         {
 41             var tag = t.InnerText.Trim().ToUpper();
 42             if (string.IsNullOrWhiteSpace(tag)) continue;
 43             tags.Add(tag);
 44             //if (Trans(tag, out var tts)) tags.Add(tts);
 45         }
 46         var tsts = new List<string>();
 47         //将所有的文本内容读出
 48         var sb = new StringBuilder();
 49         var os = "";
 50         var ttgs = new[] { "br", "div", "li", };
 51         foreach (var item in eles)
 52         {
 53             var nt = item.InnerText;
 54             if (ttgs.Contains(item.TagName))
 55             {
 56                 sb.Append(nt);
 57                 if (item.TagName == "div" && item.Attributes.ContainsKey("class") && item.Attributes["class"].StartsWith("vc_")) continue;
 58                 var innt = sb.ToString();
 59                 tsts.Add(innt);
 60                 sb.Clear();
 61             }
 62             else if (item.InnerText.StartsWith("Download"))
 63             {
 64                 var itxt = item.InnerText.Trim();
 65                 os = itxt.Substring(itxt.LastIndexOf(' ') + 1);
 66             }
 67             else if (item.TagName == "a" && item.Attributes.ContainsKey("href"))
 68             {
 69                 if (item["href"].IndexOfAny("#?=-".ToArray()) < 0) links.Add($"{item.InnerText} {item["href"]}");
 70                 else if (item.Attributes["href"].StartsWith("https://fap-nation.com/fndlnwd/")) links.Add($"{os}({ver}) {item["href"]}");
 71                 else if (!string.IsNullOrWhiteSpace(nt) && !item.Attributes["href"].Contains("tab-") && !item.Attributes["href"].Contains("#copy")) sb.Append($"<a href=\"{item["href"]}\" target=\"_blank\">{nt}</a>");
 72                 else sb.Append(nt);
 73             }
 74             else if (!nt.Contains('<')) sb.Append(nt);
 75         }
 76         var txt = string.Join("\r\n", tsts);
 77         GC.Collect();
 78         TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
 79         System.IO.File.WriteAllLines(TextPath, new[] { surl, "", }.Concat(links).Concat(new[] { "", }).Concat(tags).Concat(new[] { "", txt }));
 80         foreach (var img in imgs)
 81         {
 82             var url = new Uri(img);
 83             var fm = url.Segments.Last().Trim('/');
 84             var fp = System.IO.Path.Combine(ph, fm);
 85             DownLoadToFile(img, fp);
 86         }
 87         OnProgChanged($"抓取到{imgs.Count}图片从页面:{title}", 0);
 88     }
 89     protected string GetPathFrom(string title, string savepath, bool saveAsNewFolder, out string ver)
 90     {
 91         ver = string.Empty;
 92         if (!saveAsNewFolder) return savepath;
 93         StringTool.GetLastLabel(ref title, "  ");
 94         var lbs = StringTool.GetLabels1(ref title);
 95         ver = lbs[0];
 96         title = $"[][{lbs[1]}][{lbs[1]}][][][]{title}".ReplacePathInvalidChars();
 97         string ph = null;
 98         ph = ph ?? System.IO.Path.Combine(savepath, title.ToUpper());
 99         if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
100         return ph;
101     }
102 }
 1 /// <summary>
 2 /// https://pcgamestorrents.com/?s=
 3 /// </summary>
 4 internal class PcgamestorrentsCatcher : HtmlCatcher, IHtmlCatcher
 5 {
 6     /// <summary>
 7     /// 游戏下载网站的内容
 8     /// </summary>
 9     public override bool CanApplicableHost(string url)
10     {
11         return url.Contains("//pcgamestorrents.com/");
12     }
13     public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
14     {
15         if (string.IsNullOrWhiteSpace(surl)) return;
16         OnProgChanged($"正在抓取url:{surl}", 0);
17         //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
18         var dts = GetSource.Invoke(surl);
19         if (!HtmlElement.TryParse(dts, out var eles, out var err))
20         {
21             OnDownloadErrorHappend($"无法序列化url:{surl}");
22             return;
23         }
24         var srcurl = new Uri(surl);
25         eles = eles.ListElement();//列出所有的子元素
26         string title = eles.GetWebTitle();
27         var contente = eles.Find("div", "class", "uk-margin-medium-top");
28         eles = contente.ListElement();
29         var imgs = new List<string>();
30         foreach (var e in eles.Find("img", "class", "igg-image-content"))
31         {//封面图片或者其他图片
32             var furl = e["src"];
33             var furi = new Uri(srcurl, furl);
34             imgs.Add(furi.AbsoluteUri);
35         }
36         var tsts = new List<string>();
37         //将所有的文本内容读出
38         var sb = new StringBuilder();
39         foreach (var item in eles)
40         {
41             var tgs = new[] { "br", "button", "div", "li", "p", };
42             if (tgs.Contains(item.TagName))
43             {
44                 sb.Append(item.InnerText);
45                 tsts.Add(sb.ToString());
46                 sb.Clear();
47             }
48             else sb.Append(item.InnerText);
49         }
50         var tags = new List<string>();//从文本中获取标签
51         var tgstr = tsts.First(x => x.Trim().ToUpper().StartsWith("GENRE")).ToUpper().Replace("GENRE", "").Replace(":", "").Trim().Split(',') ?? new string[0];
52         foreach (var t in tgstr.Where(x => x.Length < 25))
53         {
54             var tag = HttpUtility.HtmlDecode(t);
55             tag = Regex.Replace(tag, @"[^ \/\w]", "").Trim().ToUpper();
56             tags.Add(tag);
57             //if (Trans(tag, out var tts)) tags.Add(tts);
58         }
59         var dev = tsts.First(x => x.Trim().ToUpper().StartsWith("DEVELOPER")).ToUpper().Replace("DEVELOPER", "").Replace(":", "").Trim();
60         var pub = tsts.First(x => x.Trim().ToUpper().StartsWith("PUBLISHER")).ToUpper().Replace("PUBLISHER", "").Replace(":", "").Trim();
61         GC.Collect();
62         var ph = GetPathFrom(title, dev, pub, savepath, saveAsNewFolder, out var ver);
63         TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
64         System.IO.File.WriteAllLines(TextPath, new[] { surl, "", $"Win({ver.Replace("« PCGamesTorrents", "").Replace("-", "").Trim()})(磁力) ", "", "破解版", }.Concat(tags).Concat(new[] { "", }).Concat(tsts));
65         foreach (var img in imgs)
66         {
67             var url = new Uri(img);
68             var fm = url.Segments.Last().Trim('/');
69             var fp = System.IO.Path.Combine(ph, fm);
70             DownLoadToFile(img, fp);
71         }
72         OnProgChanged($"抓取到{imgs.Count}图片从页面:{title}", 0);
73     }
74     private string GetPathFrom(string title, string dev, string pub, string savepath, bool saveAsNewFolder, out string ver)
75     {
76         ver = Regex.Match(title, " - .*?$").Value;
77         if (!string.IsNullOrWhiteSpace(ver)) title = title.Replace(ver, "");
78         if (!saveAsNewFolder) return savepath;
79         var ed = title.IndexOf(HttpUtility.HtmlDecode(" &laquo; "));
80         title = ed <= 0 ? title : title.Substring(0, ed);
81         title = $"[][{pub}][{dev}][][][完结]{title}".ReplacePathInvalidChars();
82         var ph = System.IO.Path.Combine(savepath, title);
83         if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
84         return ph;
85     }
86 }
 1 /// <summary>
 2 /// http://www.mfsft.com/
 3 /// </summary>
 4 internal class XiuRenPictureCatcher : HtmlCatcher, IHtmlCatcher
 5 {
 6     public override bool CanApplicableHost(string url)
 7     {
 8         return url.Contains("://www.mfsft.com/");
 9     }
10     public override async void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
11     {
12         if (string.IsNullOrWhiteSpace(surl)) return;
13         OnProgChanged($"正在抓取url:{surl}", 0);
14         //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
15         var dts = GetSource.Invoke(surl);
16         if (!HtmlElement.TryParse(dts, out var eles, out var err))
17         {
18             OnDownloadErrorHappend($"无法序列化url:{surl}");
19             return;
20         }
21         var srcurl = new Uri(surl);
22         eles = eles.ListElement();//列出所有的子元素
23         string title = eles.GetWebTitle();
24         var imgs = new List<Uri>();
25         foreach (var e in eles.Find("img", "src").Where(x => x.Attributes.ContainsKey("alt")))
26         {
27             var furl = e["src"];
28             var furi = new Uri(srcurl, furl);
29             imgs.Add(furi);
30         }
31         var lsted = srcurl.PathAndQuery.LastIndexOfAny(new[] { '.', '_' });
32         var lstst = srcurl.PathAndQuery.LastIndexOf('/');
33         var ststr = srcurl.PathAndQuery.Substring(lstst, lsted - lstst).Trim('/');
34         var others = new List<string>();
35         others.AddRange(eles.Find("a", "href").Where(x => x.Attributes["href"].StartsWith(ststr)).Select(x => x.Attributes["href"]));
36         foreach (var e in others.Distinct())
37         {//抓取其他的页面
38             var furi = new Uri(srcurl, e);
39             await Task.Run(() => Catch(furi.AbsoluteUri, imgs));
40         }
41         GC.Collect();
42         //browser.GetCookieManager().VisitUrlCookies(main.Url, true,vt);
43         var ph = GetPathFrom(title, savepath, saveAsNewFolder);
44         foreach (var img in imgs)
45         {
46             var fm = img.Segments.Last().Trim('/').Replace("_gzip.aspx", "");
47             var fp = System.IO.Path.Combine(ph, fm);
48             DownLoadToFile(img.AbsoluteUri, fp);
49         }
50         OnProgChanged($"抓取到{imgs.Count}图片从页面:{title}", 0);
51         //main.Browser.ShowDevTools();
52     }
53     private void Catch(string surl, List<Uri> array)
54     {
55         var dts = Encoding.UTF8.GetString(DownloadDatas(surl));
56         if (!HtmlElement.TryParse(dts, out var eles, out var err))
57         {
58             OnDownloadErrorHappend($"无法序列化url:{surl}");
59             return;
60         }
61         var srcurl = new Uri(surl);
62         eles = eles.ListElement();//列出所有的子元素
63         string title = eles.GetWebTitle();
64         foreach (var e in eles.Find("img", "src").Where(x => x.Attributes.ContainsKey("alt")))
65         {
66             var furl = e["src"];
67             var furi = new Uri(srcurl, furl);
68             array.Add(furi);
69         }
70     }
71     private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
72     {
73         if (!saveAsNewFolder) return savepath;
74         title = title.Substring(0, title.LastIndexOfAny(new[] { ' ', ',', '-' }));
75         title = title.ReplacePathInvalidChars();
76         var ph = System.IO.Path.Combine(savepath, title);
77         if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
78         return ph;
79     }
80 }
 1 /// <summary>
 2 /// https://www.xpiaohua.com
 3 /// </summary>
 4 internal class XpiaohuaCatcher : HtmlCatcher, IHtmlCatcher
 5 {
 6     /// <summary>
 7     /// 游戏下载网站的内容
 8     /// </summary>
 9     public override bool CanApplicableHost(string url)
10     {
11         return url.Contains("://www.xpiaohua.com");
12     }
13     public override void CatchHtml(string surl, string savepath, bool saveAsNewFolder = true)
14     {
15         if (string.IsNullOrWhiteSpace(surl)) return;
16         OnProgChanged($"正在抓取url:{surl}", 0);
17         //var dts = Encoding.UTF8.GetString(DownloadDatas(main, surl));
18         var dts = GetSource.Invoke(surl);
19         if (!HtmlElement.TryParse(dts, out var eles, out var err))
20         {
21             OnDownloadErrorHappend($"无法序列化url:{surl}");
22             return;
23         }
24         var srcurl = new Uri(surl);
25         eles = eles.ListElement();//列出所有的子元素
26         string title = eles.GetWebTitle();
27         IEnumerable<HtmlElement> deles = eles.Find("div", "id", "showinfo");
28         if (deles is null || deles.Count() < 1)
29         {
30             OnDownloadErrorHappend($"没找到可抓取内容,页面:{title}");
31             return;
32         }
33         deles = deles.ListElement();
34         var imgs = new List<string>();
35         foreach (var e in deles.Find("img", "src"))
36         {//封面图片或者其他图片
37             var furl = e["src"];
38             var furi = new Uri(srcurl, furl);
39             imgs.Add(furi.AbsoluteUri);
40         }
41         var links = new List<string>();
42         foreach (var e in deles.Find("a", "href"))
43         {//所有的下载链接或者外站连接
44             var furl = e["href"];
45             Uri furi = null;
46             try { furi = new Uri(srcurl, furl); } catch { continue; }
47             links.Add($"{e.InnerText}: {furi.AbsoluteUri}");
48         }
49         var txts = deles.GetText();
50         var ststr = "◎类  别 ";
51         var st = txts.IndexOf(ststr);
52         var ed = txts.IndexOf("◎语  言 ");
53         var tagstr = txts.Substring(st + ststr.Length, ed - st - ststr.Length);
54         var tags = tagstr.Split("/".ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
55         GC.Collect();
56         var ph = GetPathFrom(title, savepath, saveAsNewFolder);
57         TextPath = System.IO.Path.Combine(ph, "新建文本文档.txt");
58         System.IO.File.WriteAllLines(TextPath, new[] { surl, "", }.Concat(links).Concat(new[] { "", }).Concat(tags).Concat(new[] { "", txts }));
59         foreach (var img in imgs)
60         {
61             var url = new Uri(img);
62             var fm = url.Segments.Last().Trim('/');
63             var fp = System.IO.Path.Combine(ph, fm);
64             if (fm == "dico.jpg") continue;
65             DownLoadToFile(img, fp);
66         }
67         OnProgChanged($"抓取到{imgs.Count}图片{links.Count}连接从页面:{title}", 0);
68     }
69     private string GetPathFrom(string title, string savepath, bool saveAsNewFolder)
70     {
71         if (!saveAsNewFolder) return savepath;
72         title = title.Replace("_新飘花电影网", string.Empty).ReplacePathInvalidChars();
73         var ph = System.IO.Path.Combine(savepath, title.ToUpper());
74         if (!System.IO.Directory.Exists(ph)) System.IO.Directory.CreateDirectory(ph);
75         return ph;
76     }
77 }

还有的htmlCatcher在我的包里~

有需求的也可以找我代写catcher

posted @ 2024-03-15 00:20  宅猫君  阅读(327)  评论(0编辑  收藏  举报