C#通过正则表达式实现提取网页中的图片

2019-12-30 11:30:21丽君

下面写出取得HTML中所有图片地址的类HvtHtmlImage:


using System.Text.RegularExpressions;
namespace HoverTree.HoverTreeFrame.HvtImage
{
public class HvtHtmlImage
{
/// <summary> 
/// 取得HTML中所有图片的 URL。 
/// </summary> 
/// <param name="sHtmlText">HTML代码</param> 
/// <returns>图片的URL列表</returns> 
public static string[] GetHvtImgUrls(string sHtmlText)
{
// 定义正则表达式用来匹配 img 标签 
Regex m_hvtRegImg = new Regex(@"<imgb[^<>]*?bsrc[strn]*=[strn]*[""']?[strn]*(?<imgUrl>[^strn""'<>]*)[^<>]*?/?[strn]*>", RegexOptions.IgnoreCase);

// 搜索匹配的字符串 
MatchCollection matches = m_hvtRegImg.Matches(sHtmlText);
int m_i = 0;
string[] sUrlList = new string[matches.Count];
// 取得匹配项列表 
foreach (Match match in matches)
sUrlList[m_i++] = match.Groups["imgUrl"].Value;
return sUrlList;
}
}
}

下面我们再来看一个例子


public Array MatchHtml(string html,string com)
    {
      List<string> urls = new List<string>();
      html = html.ToLower();
      //获取SRC标签中的URL
      Regex regexSrc = new Regex("src="[^"]*[(.jpg)(.png)(.gif)(.bmp)(.ico)]"");
      foreach(Match m in regexSrc.Matches(html))
      {
        string src = m.Value;
        src = src.Replace("src=","").Replace(""","");
        if (!src.Contains("http"))
          src = com + src;
        if(!urls.Contains(src))
        urls.Add(src);
      }
      //获取HREF标签中URL
      Regex regexHref = new Regex("href="[^"]*[(.jpg)(.png)(.gif)(.bmp)(.ico)]"");
      foreach (Match m in regexHref.Matches(html))
      {
        string href = m.Value;
        href = href.Replace("href=", "").Replace(""", "");
        if (!href.Contains("http"))
          href = com + href;
        if(!urls.Contains(href))
        urls.Add(href);
      }
      return urls.ToArray();
    }

[DllImport("kernel32.dll")]
    static extern bool SetConsoleMode(IntPtr hConsoleHandle, int mode);
    [DllImport("kernel32.dll")]
    static extern bool GetConsoleMode(IntPtr hConsoleHandle, out int mode);
    [DllImport("kernel32.dll")]
    static extern IntPtr GetStdHandle(int handle);
    const int STD_INPUT_HANDLE = -10;
    const int ENABLE_QUICK_EDIT_MODE = 0x40 | 0x80;
    public static void EnableQuickEditMode()
    {
      int mode; IntPtr handle = GetStdHandle(STD_INPUT_HANDLE);
      GetConsoleMode(handle, out mode);
      mode |= ENABLE_QUICK_EDIT_MODE;
      SetConsoleMode(handle, mode);
    }
    static void Main(string[] args)
    {
      EnableQuickEditMode();
      int oldCount = 0;
      Console.Title = "TakeImageFromInternet";
      string path = "E:Downloadloading";
      while (true)
      {
        Console.Clear();
        string countFile = "E:CountFile.txt";//用来计数的文本,以至于文件名不重复
        int cursor = 0;
        if (File.Exists(countFile))
        {
          string text = File.ReadAllText(countFile);
          try
          {
            cursor =oldCount = Convert.ToInt32(text);//次数多了建议使用long
          }
          catch { }
        }
        Console.Write("please input a url:");
        string url = "http://www.easck.com/";
        string temp = Console.ReadLine();
        if (!string.IsNullOrEmpty(temp))
          url = temp;
        Match mcom = new Regex(@"^(?i)http://www.easck.com//获取域名
        string com = mcom.Value;
        //Console.WriteLine(mcom.Value);
        Console.Write("please input a save path:");
        temp = Console.ReadLine();
        if (Directory.Exists(temp))
          path = temp;
        Console.WriteLine();
        WebClient client = new WebClient();
        byte[] htmlData = null;
        htmlData = client.DownloadData(url);
        MemoryStream mstream = new MemoryStream(htmlData);
        string html = "";
        using (StreamReader sr = new StreamReader(mstream))
        {
          html = sr.ReadToEnd();
        }
        Array urls = new MatchHtmlImageUrl().MatchHtml(html,com);
 
        foreach (string imageurl in urls)
        {
         Console.WriteLine(imageurl);
          byte[] imageData = null;
          try
          {
            imageData = client.DownloadData(imageurl);
          }
          catch { }
          if (imageData != null && imageData.Length>0)
            using (MemoryStream ms = new MemoryStream(imageData))
            {
              try
              {
                
                string ext = Aping.Utility.File.FileOpration.ExtendName(imageurl);
                ImageFormat format = ImageFormat.Jpeg;
                switch (ext)
                {
                  case ".jpg":
                    format = ImageFormat.Jpeg;
                    break;
                  case ".bmp":
                    format = ImageFormat.Bmp;
                    break;
                  case ".png":
                    format = ImageFormat.Png;
                    break;
                  case ".gif":
                    format = ImageFormat.Gif;
                    break;
                  case ".ico":
                    format = ImageFormat.Icon;
                    break;
                  default:
                    continue;
                }
                Image image = new Bitmap(ms);
                if (Directory.Exists(path))
                  image.Save(path + "" + cursor + ext, format);
              }
              catch(Exception ex) { Console.WriteLine(ex.Message); }
            }
          cursor++;
        }
        mstream.Close();
        File.WriteAllText(countFile, cursor.ToString(), Encoding.UTF8);
        Console.WriteLine("take done...image count:"+(cursor-oldCount).ToString());
      }      
    }