HtmlWeb hw = new HtmlWeb();
string url = @"http://xinhua.org";
HtmlDocument doc = hw.Load(url);
doc.Save("output.html");
string url = @"http://xinhua.org";
HtmlDocument doc = hw.Load(url);
doc.Save("output.html");
获得的页面用ie打开,是乱码。
穿越HtmlAgilityPack的代码迷宫,最后发现问题出在HtmlWeb类的Get(Uri uri, string method, string path, HtmlDocument doc)方法中。该方法有以下代码:
HttpWebResponse resp;
try
{
resp = req.GetResponse() as HttpWebResponse;
}
……
if ((resp.ContentEncoding != null) && (resp.ContentEncoding.Length>0))
{
respenc = System.Text.Encoding.GetEncoding(resp.ContentEncoding);
}
else
{
respenc = null;
}
……
Stream s = resp.GetResponseStream();
if (s != null)
{
if (UsingCache)
{
// NOTE: LastModified does not contain milliseconds, so we remove them to the file
SaveStream(s, cachePath, RemoveMilliseconds(resp.LastModified), _streamBufferSize);
// save headers
SaveCacheHeaders(req.RequestUri, resp);
if (path != null)
{
// copy and touch the file
IOLibrary.CopyAlways(cachePath, path);
File.SetLastWriteTime(path, File.GetLastWriteTime(cachePath));
}
}
else
{
// try to work in-memory
if ((doc != null) && (html))
{
if (respenc != null)
{
doc.Load(s, respenc);
}
else
{
doc.Load(s, true);
}
}
}
resp.Close();
}
try
{
resp = req.GetResponse() as HttpWebResponse;
}
……
if ((resp.ContentEncoding != null) && (resp.ContentEncoding.Length>0))
{
respenc = System.Text.Encoding.GetEncoding(resp.ContentEncoding);
}
else
{
respenc = null;
}
……
Stream s = resp.GetResponseStream();
if (s != null)
{
if (UsingCache)
{
// NOTE: LastModified does not contain milliseconds, so we remove them to the file
SaveStream(s, cachePath, RemoveMilliseconds(resp.LastModified), _streamBufferSize);
// save headers
SaveCacheHeaders(req.RequestUri, resp);
if (path != null)
{
// copy and touch the file
IOLibrary.CopyAlways(cachePath, path);
File.SetLastWriteTime(path, File.GetLastWriteTime(cachePath));
}
}
else
{
// try to work in-memory
if ((doc != null) && (html))
{
if (respenc != null)
{
doc.Load(s, respenc);
}
else
{
doc.Load(s, true);
}
}
}
resp.Close();
}
其中resp是http请求的response。设置断点发现resp.ContentEncoding为空。于是最后的加载行为便变成了doc.Load(s, true);而这个load方法也可能出了问题,最后得到的是乱码。
解决方法:
不使用HttpWeb,该类不成熟。自己写http请求,代码如下:
HttpWebRequest req;
req = WebRequest.Create(new Uri(@"http://xinhua.org")) as HttpWebRequest;
req.Method = "GET";
WebResponse rs = req.GetResponse();
Stream rss = rs.GetResponseStream();
String url = @"http://xinhua.org";
try
{
HtmlDocument doc = new HtmlDocument();
doc.Load(rss);
doc.Save("output.html");
}
catch (Exception e)
{
Console.WriteLine(e.Message.ToString());
Console.WriteLine(e.StackTrace);
}
req = WebRequest.Create(new Uri(@"http://xinhua.org")) as HttpWebRequest;
req.Method = "GET";
WebResponse rs = req.GetResponse();
Stream rss = rs.GetResponseStream();
String url = @"http://xinhua.org";
try
{
HtmlDocument doc = new HtmlDocument();
doc.Load(rss);
doc.Save("output.html");
}
catch (Exception e)
{
Console.WriteLine(e.Message.ToString());
Console.WriteLine(e.StackTrace);
}
上面代码中,doc.Load(…) 使用的编码为System.Text.Encoding.Default,在我机器上为gb2312编码。
HtmlDocument也可以指定编码load stream。获得指定编码有两种方法:
(1)在HttpWebResponse 对象中可以获取html代码中设置的charset;
(2)未提供charset的html页面,HtmlDocument提供了自动检测代码的方法DetectEncoding(…)。这一方法俺为测试过,不知道正确性如何.