Question

我的程序是一个webcrawler。我试图从网站下载图像。在我的webcrawler网站上，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;

            }
        }
    }
}

现在我正在逐行使用断点和步骤，并在执行此行之后：

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

变量imgs为null。然后在下一行检查它的null是否跳到最后并且什么都不做。

我如何解决它，以便能够从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;

            }
        }

Answer 1

如果您查看WebClient返回给您的内部数据，您会看到没有Html页面，但是图像的位数据。

doc.Load(wc.OpenRead(address));
Console.WriteLine(doc.DocumentNode.InnerText);

变量始终返回null

1 个答案: