我在一个新类中有以下代码:
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;
}
}
}
}
上面的代码是我的 WebCrawler 的一部分。此代码将仅从网站下载图像文件。
例如,我有这个网站: http ://web.archive.org/web/20131216195236/http://open-hardware-monitor.googlecode.com/svn/trunk/
上述站点中包含一个名为App
. 如果我右键单击它save as
,然后我看到它是一个配置文件。如果我单击该Hardware/
链接,我会看到许多 *.CS 文件。
如何制作和/或更新我的代码,以便它可以下载各种文件类型,而不仅仅是下载图像?