httpWebRequest获取流和WebClient的文件抓取
昨天写一个抓取，遇到了一个坑，就是在获取网络流的时候，人为的使用了stream.Length来获取流的长度，获取的时候会抛出错误，查了查文档，原因是某些流是无法获取到数据的长度的，所以不能直接得到。如果是常和stream打交道就能避免这个问题。其实直接使用do-while来获取就行了，代码如下：
int i=0;do{ byte[] buffer = new byte[1024]; i = stream.Read(buffer, 0, 1024); fs.Write(buffer, 0, i);} while (i >0); 其中while后只能写i>0；而不能写成i>=1024;原因可以看MSDN中的一段解释：
仅当流中没有更多数据且预期不会有更多数据（如套接字已关闭或位于文件结尾）时，Read 才返回 0。 即使尚未到达流的末尾，实现仍可以随意返回少于所请求的字节。
一下是httpwebrequest和webClient抓取数据的简短代码：
httpWebRequest
////// /// /// 抓取url/// 保存文件名/// 来源路径///public static bool HttpDown(string url, string filePath, string oldurl){ try { HttpWebRequest req = WebRequest.Create(url) as HttpWebRequest; req.Accept = @"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8 "; req.Referer = oldurl; req.UserAgent = @" Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36 "; req.ContentType = "application/octet-stream"; HttpWebResponse response = req.GetResponse() as HttpWebResponse; Stream stream = response.GetResponseStream(); // StreamReader readStream=new StreamReader FileStream fs = File.Create(filePath); long length = response.ContentLength; int i=0; do { byte[] buffer = new byte[1024]; i = stream.Read(buffer, 0, 1024); fs.Write(buffer, 0, i); } while (i >0); fs.Close(); return true; } catch (Exception ex) { return false; }}
WebClient
public static bool Down(string url, string desc,string oldurl){ try { WebClient wc = new WebClient(); wc.Headers.Add(HttpRequestHeader.Accept, @"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"); wc.Headers.Add(HttpRequestHeader.Referer, oldurl); wc.Headers.Add(HttpRequestHeader.UserAgent, @" Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36"); wc.Headers.Add(HttpRequestHeader.ContentType, "application/octet-stream"); wc.DownloadFile(new Uri(url), desc); Console.WriteLine(url); Console.WriteLine(" "+desc + " yes!"); return true; } catch (Exception ex) { return false; }}