今天在我的代码中,我从这样的网站下载图像:
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;
}
}
}
}
但有时在许多情况下,图像在 java 脚本后面或下面,无法正常下载。我如何获取/下载图像和/或整个完整的网站内容,包括图像和所有内容,以便稍后在我的硬盘中我将拥有完整的网站及其所有内容树,以便我可以离线浏览它。