读取图片地址
0
最佳答案
0
private void DownLoadPic2() { WebRequest request = WebRequest.Create("http://gz.o.cn/youhui/mdl"); request.Credentials = CredentialCache.DefaultCredentials; HttpWebResponse response = (HttpWebResponse)request.GetResponse(); Stream dataStream = response.GetResponseStream(); StreamReader reader = new StreamReader(dataStream, Encoding.Default); string bigString = reader.ReadToEnd(); reader.Close(); dataStream.Close(); response.Close(); ArrayList imgUrl = new ArrayList(); foreach (Match match in Regex.Matches(bigString, "original=\".*\" alt")) { imgUrl.Add(match.Value.Substring(10, match.Value.Length - 15)); } //删除重复数据 for (int i = 0; i < imgUrl.Count; i++) { for (int j = i + 1; j < imgUrl.Count; j++) { if (imgUrl[i].Equals(imgUrl[j])) { imgUrl.RemoveAt(j); if (i > 0) { i--; } } } } for (int i = 0; i < imgUrl.Count; i++) { var uri = WebRequest.Create(imgUrl[i].ToString()); var res = uri.GetResponse(); string filename = Application.StartupPath + "\\Images\\" + i + ".jpg"; Bitmap aa = new Bitmap(res.GetResponseStream()); aa.Save(filename); } }
其他回答(2)
1
public static StringBuilder GetImgUrl(string text) { StringBuilder str = new StringBuilder(); string pat = @"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>"; Regex r = new Regex(pat, RegexOptions.Compiled); Match m = r.Match(text); //int matchCount = 0; if (m.Success) { Group g = m.Groups[2]; str.Append(g); m = m.NextMatch(); } ...... }
省略号代表一些个性化的处理 比如截取出来多了 /或者多了.什么的 你可以使用字符串的replace等方法给干掉
实际开发中远比楼主你这个要复杂，我这个是爬电商的图片正则，如果下载的源文件之有一个img 一个src 那么就简单许多了，楼主自己多试试吧。
0
不知道楼主是怎么取操作这个的，webrequest读取的，还是js端的操作 ？
http://htmlagilitypack.codeplex.com/
