0

我的程序是一个网络爬虫。我试图从网站下载图像。在我的网络爬虫网站中,我做了:

try
{
    HtmlAgilityPack.HtmlDocument doc = TimeOut.getHtmlDocumentWebClient(mainUrl, false, "", 0, "", "");
    if (doc == null)
    {
        if (wccfg.downloadcontent == true)
        {
            retwebcontent.retrieveImages(mainUrl);
        }
        failed = true;
        wccfg.failedUrls++;
        failed = false;
    }

例如,当 doc 为 null 时,mainUrl 包含:

http://members.tripod.com/~VanessaWest/bundybowman2.jpg

现在它跳转到另一个类中的 retrieveImages 方法:

namespace GatherLinks
{
    class RetrieveWebContent
    {
        HtmlAgilityPack.HtmlDocument doc;
        string imgg;
        int images;

        public RetrieveWebContent()
        {
            images = 0;
        }

        public List<string> retrieveImages(string address)
        {
            try
            {
                doc = new HtmlAgilityPack.HtmlDocument();
                System.Net.WebClient wc = new System.Net.WebClient();
                List<string> imgList = new List<string>();
                doc.Load(wc.OpenRead(address));
                HtmlNodeCollection imgs = doc.DocumentNode.SelectNodes("//img[@src]");
                if (imgs == null) return new List<string>();

                foreach (HtmlNode img in imgs)
                {
                    if (img.Attributes["src"] == null)
                        continue;
                    HtmlAttribute src = img.Attributes["src"];

                    imgList.Add(src.Value);
                    if (src.Value.StartsWith("http") || src.Value.StartsWith("https") || src.Value.StartsWith("www"))
                    {
                        images++;
                        string[] arr = src.Value.Split('/');
                        imgg = arr[arr.Length - 1];
                        //imgg = Path.GetFileName(new Uri(src.Value).LocalPath);
                        //wc.DownloadFile(src.Value, @"d:\MyImages\" + imgg);
                        wc.DownloadFile(src.Value, "d:\\MyImages\\" + Guid.NewGuid() + ".jpg");
                    }
                }

                return imgList;
            }
            catch
            {
                Logger.Write("There Was Problem Downloading The Image: " + imgg);
                return null;

            }
        }
    }
}

现在我使用断点并逐行执行此行之后:

HtmlNodeCollection imgs = doc.DocumentNode.SelectNodes("//img[@src]");

变量 imgs 为空。然后在下一行检查它是否为空,它跳到最后并且什么也不做。

我该如何解决它才能从http://members.tripod.com/~VanessaWest/bundybowman2.jpg下载图像?

编辑**

public List<string> retrieveImages(string address)
        {
            try
            {
                doc = new HtmlAgilityPack.HtmlDocument();
                System.Net.WebClient wc = new System.Net.WebClient();
                List<string> imgList = new List<string>();
                doc.Load(wc.OpenRead(address));
                string t = doc.DocumentNode.InnerText;
                HtmlNodeCollection imgs = doc.DocumentNode.SelectNodes("//img//[@src]");
                if (imgs == null) return new List<string>();

                foreach (HtmlNode img in imgs)
                {
                    if (img.Attributes["src"] == null)
                        continue;
                    HtmlAttribute src = img.Attributes["src"];
                    wc.DownloadFile(src.Value, "d:\\MyImages\\" + Guid.NewGuid() + ".jpg");
                    imgList.Add(src.Value);
                    if (src.Value.StartsWith("http") || src.Value.StartsWith("https") || src.Value.StartsWith("www"))
                    {
                        images++;
                        string[] arr = src.Value.Split('/');
                        imgg = arr[arr.Length - 1];
                        //imgg = Path.GetFileName(new Uri(src.Value).LocalPath);
                        //wc.DownloadFile(src.Value, @"d:\MyImages\" + imgg);
                        wc.DownloadFile(src.Value, "d:\\MyImages\\" + Guid.NewGuid() + ".jpg");
                    }
                }

                return imgList;
            }
            catch
            {
                Logger.Write("There Was Problem Downloading The Image: " + imgg);
                return null;

            }
        }
4

1 回答 1

1

如果您查看 WebClient 返回给您的数据,您会看到不是 Html 页面,而是图像的位数据。

doc.Load(wc.OpenRead(address));
Console.WriteLine(doc.DocumentNode.InnerText);
于 2013-08-28T08:20:22.080 回答