0

编码：

using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using HtmlAgilityPack;
using System.IO;
using System.Text.RegularExpressions;
using System.Xml.Linq;
using System.Net;
using System.Web;
using System.Threading;
using DannyGeneral;
using GatherLinks;

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];
                        wc.DownloadFile(src.Value, @"d:\MyImages\" + imgg);
                    }
                }

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

            }
        }
    }
}

例如给出此异常的链接：

http://vanessawest.tripod.com/bundybowman.jpg

经过几次迭代后，它进入了 foreach 循环。

现在，如果链接来自另一个站点，例如：

www.walla.co.il

因此，它进入 foreach 循环并获取所有图像是没有问题的。

这是链接的完整异常消息：

http://vanessawest.tripod.com/bundybowman.jpg

System.Net.WebException was caught
  HResult=-2146233079
  Message=An exception occurred during a WebClient request.
  Source=System
  StackTrace:
       at System.Net.WebClient.DownloadFile(Uri address, String fileName)
       at System.Net.WebClient.DownloadFile(String address, String fileName)
       at GatherLinks.RetrieveWebContent.retrieveImages(String address) in d:\C-Sharp\GatherLinks\GatherLinks-2\GatherLinks\GatherLinks\RetrieveWebContent.cs:line 55
  InnerException: System.ArgumentException
       HResult=-2147024809
       Message=Illegal characters in path.
       Source=mscorlib
       StackTrace:
            at System.IO.Path.CheckInvalidPathChars(String path, Boolean checkAdditional)
            at System.IO.FileStream.Init(String path, FileMode mode, FileAccess access, Int32 rights, Boolean useRights, FileShare share, Int32 bufferSize, FileOptions options, SECURITY_ATTRIBUTES secAttrs, String msgPath, Boolean bFromProxy, Boolean useLongPath, Boolean checkHost)
            at System.IO.FileStream..ctor(String path, FileMode mode, FileAccess access)
            at System.Net.WebClient.DownloadFile(Uri address, String fileName)
       InnerException:

我不知道为什么在 walla link 上它的工作没有问题，而在三脚架上它的异常。

4

1 回答 1

0

http://vanessawest.tripod.com/bundybowman.jpg

你确定这是导致问题的原因吗？我的猜测是，由于要获取文件名的字符串拆分逻辑，您在本地文件名中得到了一些不需要的字符。

string[] arr = src.Value.Split('/');
imgg = arr[arr.Length - 1];

相反，试试这个：

imgg = Path.GetFileName(new Uri(src.Value).LocalPath);
于 2013-08-25T09:27:16.610 回答