public static bool IsAllowed(System.Uri url)
{
System.String host = url.Host;
RobotRuleSet robotRules = (RobotRuleSet)CACHE[host];
if (robotRules == null)
{
// cache miss
//UPGRADE_TODO: Class 'java.net.URL' was converted to a 'System.Uri' which does not throw an exception if a URL specifies an unknown protocol. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1132_3"'
HttpResponseMgr response = new HttpResponseMgr(new System.Uri(url, "/robots.txt"));
if (response.Code == 200)
{
// found rules: parse them
robotRules = new RobotRulesParser().ParseRules(response.Content);
}
else if ((response.Code == 403) && (!ALLOW_FORBIDDEN))
{
robotRules = FORBID_ALL_RULES;
}
// use forbid all
else
{
robotRules = EMPTY_RULES; // use default rules
}
CACHE[host] = robotRules; // cache rules for host
}
System.String path = url.AbsolutePath; // check rules
if ((path == null) || "".Equals(path))
{
path = "/";
}
return(robotRules.IsAllowed(path));
}
public static bool IsAllowed(System.Uri url)
{
System.String host = url.Host;
RobotRuleSet robotRules = (RobotRuleSet) CACHE[host];
if (robotRules == null)
{
// cache miss
//UPGRADE_TODO: Class 'java.net.URL' was converted to a 'System.Uri' which does not throw an exception if a URL specifies an unknown protocol. 'ms-help://MS.VSCC.2003/commoner/redir/redirect.htm?keyword="jlca1132_3"'
HttpResponseMgr response = new HttpResponseMgr(new System.Uri(url, "/robots.txt"));
if (response.Code == 200)
// found rules: parse them
robotRules = new RobotRulesParser().ParseRules(response.Content);
else if ((response.Code == 403) && (!ALLOW_FORBIDDEN))
robotRules = FORBID_ALL_RULES;
// use forbid all
else
robotRules = EMPTY_RULES; // use default rules
CACHE[host] = robotRules; // cache rules for host
}
System.String path = url.AbsolutePath; // check rules
if ((path == null) || "".Equals(path))
{
path = "/";
}
return robotRules.IsAllowed(path);
}
/// <summary>
///
/// </summary>
/// <param name="pageUri"></param>
/// <returns></returns>
public HttpProtocolOutput GetProtocolOutput(System.Uri pageUri)
{
this.m_ProtocolOutput = null;
HttpProtocolStatus obStatus = null;
System.String urlString = pageUri.ToString();
try
{
System.Uri url = new System.Uri(urlString);
int redirects = 0;
while(true)
{
if (!RobotRulesParser.IsAllowed(url))
{
if (HttpProtocol.HONOR_ROBOTSTEXT)
{
throw new RobotBlockedException(url);
}
}
System.Net.IPAddress addr = BlockAddr(url);
HttpResponseMgr response;
try
{
response = new HttpResponseMgr(urlString, url); // make a request
}
finally
{
UnblockAddr(addr);
}
int code = response.Code;
if (code == 200)
{
// got a good response
obStatus = HttpProtocolStatus.STATUS_SUCCESS;
m_ProtocolOutput = new HttpProtocolOutput(new HttpProtocolContent(response.Content, response.Headers),obStatus); // return it
m_ProtocolOutput.Cookies = response.Cookies;
m_ProtocolOutput.ProtocolVersion = response.ProtocolVersion;
return m_ProtocolOutput;
}
else if (code == 410)
{
// page is gone
throw new ResourceGoneException(url, "Http: " + code);
}
else if (code >= 300 && code < 400)
{
// handle redirect
if (redirects == MAX_REDIRECTS)
{
throw new System.Web.HttpException("Too many redirects: " + urlString);
}
url = new System.Uri(url, response.GetHeader("Location"));
redirects++;
System.Diagnostics.Trace.WriteLine("redirect to " + url);
}
else
{
// convert to exception
throw new HttpError(code);
}
}
}
catch(RobotBlockedException ex)
{
System.Diagnostics.Trace.WriteLine(ex.Message);
m_ProtocolOutput = new HttpProtocolOutput(null, HttpProtocolStatus.STATUS_ROBOTS_DENIED);
}
catch(HttpError ex)
{
System.Diagnostics.Trace.WriteLine(ex.Message);
obStatus = new HttpProtocolStatus(ex.Code);
m_ProtocolOutput = new HttpProtocolOutput(null, obStatus);
}
catch (System.Exception e)
{
System.Diagnostics.Trace.WriteLine(e.Message);
m_ProtocolOutput = new HttpProtocolOutput(null, HttpProtocolStatus.STATUS_FAILED);
}
return m_ProtocolOutput;
}
/// <summary>
///
/// </summary>
/// <param name="pageUri"></param>
/// <returns></returns>
public HttpProtocolOutput GetProtocolOutput(System.Uri pageUri)
{
this.m_ProtocolOutput = null;
HttpProtocolStatus obStatus = null;
System.String urlString = pageUri.ToString();
try
{
System.Uri url = new System.Uri(urlString);
int redirects = 0;
while (true)
{
if (!RobotRulesParser.IsAllowed(url))
{
if (HttpProtocol.HONOR_ROBOTSTEXT)
{
throw new RobotBlockedException(url);
}
}
System.Net.IPAddress addr = BlockAddr(url);
HttpResponseMgr response;
try
{
response = new HttpResponseMgr(urlString, url); // make a request
}
finally
{
UnblockAddr(addr);
}
int code = response.Code;
if (code == 200)
{
// got a good response
obStatus = HttpProtocolStatus.STATUS_SUCCESS;
m_ProtocolOutput = new HttpProtocolOutput(new HttpProtocolContent(response.Content, response.Headers), obStatus); // return it
m_ProtocolOutput.Cookies = response.Cookies;
m_ProtocolOutput.ProtocolVersion = response.ProtocolVersion;
return(m_ProtocolOutput);
}
else if (code == 410)
{
// page is gone
throw new ResourceGoneException(url, "Http: " + code);
}
else if (code >= 300 && code < 400)
{
// handle redirect
if (redirects == MAX_REDIRECTS)
{
throw new System.Web.HttpException("Too many redirects: " + urlString);
}
url = new System.Uri(url, response.GetHeader("Location"));
redirects++;
System.Diagnostics.Trace.WriteLine("redirect to " + url);
}
else
{
// convert to exception
throw new HttpError(code);
}
}
}
catch (RobotBlockedException ex)
{
System.Diagnostics.Trace.WriteLine(ex.Message);
m_ProtocolOutput = new HttpProtocolOutput(null, HttpProtocolStatus.STATUS_ROBOTS_DENIED);
}
catch (HttpError ex)
{
System.Diagnostics.Trace.WriteLine(ex.Message);
obStatus = new HttpProtocolStatus(ex.Code);
m_ProtocolOutput = new HttpProtocolOutput(null, obStatus);
}
catch (System.Exception e)
{
System.Diagnostics.Trace.WriteLine(e.Message);
m_ProtocolOutput = new HttpProtocolOutput(null, HttpProtocolStatus.STATUS_FAILED);
}
return(m_ProtocolOutput);
}
