从指定网址读html文件,获取指定网址下的html页面中的图片文件

// 获取指定网址下的html页面中的图片文件路径列表

private static List getImageUrlList(string strSource)

{

Regex reg = new Regex(@"http://\S+\.(gif|bmp|png|jpg)");

MatchCollection mc = reg.Matches(strSource);

List strList = new List();

for (int i = 0; i < mc.Count; i++)

{

strList.Add(String.Format("{0}\r\n", mc[i].Value));

}

List newList = new List();

newList.AddRange(strList.Distinct());

return newList;

}

// 获取指定url路径的图片,保存下来

private static void getUrlImage(string imageUrl)

{

try

{

int lastIndex = imageUrl.LastIndexOf('/');

string fileName = imageUrl.Substring(lastIndex + 1); // 文件名称

HttpWebRequest request = (HttpWebRequest)WebRequest.Create(imageUrl);

HttpWebResponse response = (HttpWebResponse)request.GetResponse();

Stream receiveStream = response.GetResponseStream(); // 网络stream, 不可获取长度

BinaryReader reader = new BinaryReader(receiveStream);

string imagePath = @".\img\";

if (!Directory.Exists(imagePath))

Directory.CreateDirectory(imagePath);

using (FileStream stream = new FileStream( imagePath + fileName, FileMode.Create))

{

byte[] buffer = new byte[256]; // 通过缓存取得数据

int count = reader.Read(buffer, 0, 256);

while (count > 0)

{

stream.Write(buffer, 0, count);

count = reader.Read(buffer, 0, 256);

}

stream.Flush();

}

receiveStream.Close();

}

catch { }

}

// 调用示例

private void captureImageByUrl(string urlStr)

{

string strSource = getUrlHtml(urlStr);

if (strSource == String.Empty) return;

List strList = getImageUrlList(strSource);

StringBuilder sb = new StringBuilder();

foreach (string item in strList)

{

sb.Append(item);

getUrlImage(item.TrimEnd(new char[] { '\r', '\n' }));

}

MessageBox.Show(sb.ToString());

}