void Process(SgmlReader reader, string uri, bool loadAsStream) {
if (uri == null) {
reader.InputStream = Console.In;
}
else if (loadAsStream) {
Uri location = new Uri(uri);
if (location.IsFile) {
reader.InputStream = new StreamReader(uri);
} else {
WebRequest wr = WebRequest.Create(location);
reader.InputStream = new StreamReader(wr.GetResponse().GetResponseStream());
}
} else {
reader.Href = uri;
}
if (debug) {
Debug(reader);
reader.Close();
return;
}
if (crawl) {
StartCrawl(reader, uri, basify);
return;
}
if (this.encoding == null) {
this.encoding = reader.GetEncoding();
}
XmlTextWriter w = null;
if (output != null) {
w = new XmlTextWriter(output, this.encoding);
}
else {
w = new XmlTextWriter(Console.Out);
}
if (formatted) w.Formatting = Formatting.Indented;
if (!noxmldecl) {
w.WriteStartDocument();
}
if (testdoc) {
XmlDocument doc = new XmlDocument();
try {
doc.Load(reader);
doc.WriteTo(w);
} catch (XmlException e) {
Console.WriteLine("Error:" + e.Message);
Console.WriteLine("at line " + e.LineNumber + " column " + e.LinePosition);
}
} else {
reader.Read();
while (!reader.EOF) {
w.WriteNode(reader, true);
}
}
w.Flush();
w.Close();
}
// Creates XmlDocument from html content and return it with rootitem "<root>".
public static XmlDocument ParseHtml(string sContent)
{
StringReader sr = new StringReader("<root>" + sContent + "</root>");
SgmlReader reader = new SgmlReader();
reader.WhitespaceHandling = WhitespaceHandling.All;
reader.CaseFolding = Sgml.CaseFolding.ToLower;
reader.InputStream = sr;
StringWriter sw = new StringWriter();
XmlTextWriter w = new XmlTextWriter(sw);
w.Formatting = Formatting.Indented;
w.WriteStartDocument();
reader.Read();
while (!reader.EOF)
{
w.WriteNode(reader, true);
}
w.Flush();
w.Close();
sw.Flush();
// create document
XmlDocument doc = new XmlDocument();
doc.PreserveWhitespace = true;
doc.XmlResolver = null;
doc.LoadXml(sw.ToString());
reader.Close();
return(doc);
}
/// <summary>
/// 处理html代码
/// </summary>
/// <param name="input">等处理的字符串</param>
/// <param name="skipHtmlNode">是否跳过html节点</param>
/// <param name="clearTag">是否清除html tag，只输出纯文本</param>
/// <param name="maxCount">copy的文本的字符数，如果maxCount<=0，copy全部文本</param>
/// <param name="endStr">如果只copy了部分文本，部分文本后的附加字符，如...</param>
/// <returns>处理后的html代码</returns>
public static string ProcessHtml(string input, bool skipHtmlNode, bool clearTag, int maxCount, string endStr)
{
if (string.IsNullOrEmpty(input))
{
return(input);
}
StringWriter output = new StringWriter();
XmlTextWriter writer = new XmlTextWriter(output);
writer.Formatting = Formatting.Indented;
SgmlReader reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(input);
WriteXml(writer, reader, true, skipHtmlNode, clearTag, maxCount, endStr);
writer.Flush();
writer.Close();
reader.Close();
return(output.ToString());
}
public static string GetWellFormedHTML(string html, string xpathNavPath)
{
// StreamReader sReader = null;
StringWriter sw = null;
SgmlReader reader = null;
XmlTextWriter writer = null;
try
{
// if (uri == String.Empty) uri = "http://www.XMLforASP.NET";
// HttpWebRequest req = (HttpWebRequest)WebRequest.Create(uri);
// HttpWebResponse res = (HttpWebResponse)req.GetResponse();
// sReader = new StreamReader(res.GetResponseStream());
reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(html);
sw = new StringWriter();
writer = new XmlTextWriter(sw);
writer.Formatting = Formatting.Indented;
//writer.WriteStartElement("Test");
while (reader.Read())
{
if (reader.NodeType != XmlNodeType.Whitespace)
{
writer.WriteNode(reader, true);
}
}
//writer.WriteEndElement();
if (xpathNavPath == null)
{
string sr = sw.ToString();
sr = sr.Replace("\r", "\n");
sr = sr.Replace("\n\n", "\n");
return(sr);
}
else
{ //Filter out nodes from HTML
StringBuilder sb = new StringBuilder();
XPathDocument doc = new XPathDocument(new StringReader(sw.ToString()));
XPathNavigator nav = doc.CreateNavigator();
XPathNodeIterator nodes = nav.Select(xpathNavPath);
while (nodes.MoveNext())
{
sb.Append(nodes.Current.Value + "\n");
}
string sr = sb.ToString();
sr = sr.Replace("\r", "\n");
sr = sr.Replace("\n\n", "\n");
return(sr);
}
}
catch (Exception exp)
{
writer.Close();
reader.Close();
sw.Close();
// sReader.Close();
return(exp.Message);
}
}
/// <summary>
/// 获取xml中的数据 根据
/// </summary>
/// <param name="htmlString"></param>
/// <param name="xpath"></param>
/// <returns></returns>
public static string GetWellFormedHTML(string htmlString, string xpath)
{
if (htmlString.Trim().Length < 10)
{
return("");
}
htmlString = htmlString.Replace("xmlns", "buyao");
StringWriter sw = null;
SgmlReader reader = null;
XmlTextWriter writer = null;
try
{
reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(htmlString);
sw = new StringWriter();
writer = new XmlTextWriter(sw);
writer.Formatting = Formatting.Indented;
writer.WriteStartDocument();
while (reader.Read())
{
if (reader.NodeType != XmlNodeType.Whitespace)
{
try
{
//如果出错 抛弃此节点
writer.WriteNode(reader, true);
}
catch (Exception e)
{
}
}
}
if (xpath == null)
{
return(sw.ToString());
}
else
{
StringBuilder sb = new StringBuilder();
XPathDocument doc = new XPathDocument(new StringReader(sw.ToString()));
XPathNavigator nav = doc.CreateNavigator();
XPathNodeIterator nodes = nav.Select(xpath);
while (nodes.MoveNext())
{
sb.Append(nodes.Current.OuterXml + " ");
}
return(sb.ToString());
}
}
catch (Exception exp)
{
writer.Close();
reader.Close();
sw.Close();
return("");
}
}
private ResultInfo getDetail(string backstring)
{
SgmlReader reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(backstring);
StringWriter sw = new StringWriter();
XmlTextWriter writer = new XmlTextWriter(sw);
reader.WhitespaceHandling = WhitespaceHandling.None;
writer.Formatting = Formatting.Indented;
while (reader.Read())
{
if (reader.NodeType != XmlNodeType.Whitespace)
{
writer.WriteNode(reader, true);
}
}
XmlDocument doc = new XmlDocument();
doc.Load(new StringReader(sw.ToString()));
XmlNamespaceManager xnm = new XmlNamespaceManager(doc.NameTable);
xnm.AddNamespace("bottum", "http://www.w3.org/1999/xhtml");
XPathNavigator nav = doc.CreateNavigator();
/////////////////根据网页返回结果分析
string xpath = "//bottum:table[@id='ctl00_ContentPlaceHolder1_TrackDetail']/bottum:tr/bottum:td/bottum:div[8]/bottum:table/bottum:tr/bottum:td";
XPathNodeIterator nodes = nav.Select(xpath, xnm);//xpath表达式
ResultInfo backinfo = new ResultInfo(querynum);
if (nodes.Count > 3)
{
nodes.MoveNext();
nodes.MoveNext();
nodes.MoveNext();
}
for (int i = 1; i < nodes.Count / 3; i++)
{
nodes.MoveNext();
string time = nodes.Current.Value;
nodes.MoveNext();
nodes.MoveNext();
string state = nodes.Current.Value;
backinfo.add(time, state);
}
reader.Close();
writer.Close();
sw.Close();
return(backinfo);
}
public ResultInfo getDetail(string backstring)
{
SgmlReader reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(backstring);
StringWriter sw = new StringWriter();
XmlTextWriter writer = new XmlTextWriter(sw);
reader.WhitespaceHandling = WhitespaceHandling.None;
writer.Formatting = Formatting.Indented;
while (reader.Read())
{
if (reader.NodeType != XmlNodeType.Whitespace)
{
writer.WriteNode(reader, true);
}
}
XmlDocument doc = new XmlDocument();
doc.Load(new StringReader(sw.ToString()));
reader.Close();
writer.Close();
sw.Close();
XmlNamespaceManager xnm = new XmlNamespaceManager(doc.NameTable);
xnm.AddNamespace("bottum", "http://www.w3.org/1999/xhtml");
XPathNavigator nav = doc.CreateNavigator();
string xpath = "//bottum:table[@id='GridView1']/bottum:tr/bottum:td";
XPathNodeIterator nodes = nav.Select(xpath, xnm);//xpath表达式
if (nodes != null)
{
int count = nodes.Count;
int k = count / 3;
ResultInfo backinfo = new ResultInfo(queryNumber);
for (int i = 0; i < k; i++)
{
nodes.MoveNext();
nodes.MoveNext();
string time = nodes.Current.Value;
nodes.MoveNext();
string state = nodes.Current.Value;
backinfo.add(time, state);
}
return(backinfo);
}
else
{
return(new ResultInfo(queryNumber));
}
}
private ResultInfo getDetail(string backstring)
{
SgmlReader reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(backstring);
StringWriter sw = new StringWriter();
XmlTextWriter writer = new XmlTextWriter(sw);
reader.WhitespaceHandling = WhitespaceHandling.None;
writer.Formatting = Formatting.Indented;
while (reader.Read())
{
if (reader.NodeType != XmlNodeType.Whitespace)
{
writer.WriteNode(reader, true);
}
}
XmlDocument doc = new XmlDocument();
doc.Load(new StringReader(sw.ToString()));
XmlNamespaceManager xnm = new XmlNamespaceManager(doc.NameTable);
XPathNavigator nav = doc.CreateNavigator();
/////////////////根据网页返回结果分析
string xpath = "//table[1]/tr/td";
string str = "";
XPathNodeIterator nodes = nav.Select(xpath, xnm);//xpath表达式
ResultInfo backinfo = new ResultInfo(querynum);
if (nodes.Count >= 4)
{
nodes.MoveNext();
nodes.MoveNext();
nodes.MoveNext();
nodes.MoveNext();
}
for (int i = 4; i < nodes.Count / 2; i++)
{
nodes.MoveNext();
string time = nodes.Current.Value;
nodes.MoveNext();
string state = nodes.Current.Value;
backinfo.add(time, state);
nodes.MoveNext();
}
reader.Close();
writer.Close();
sw.Close();
return(backinfo);
}
public ResultInfo getDetail(string backstring)
{
backstring = backstring.Replace("xmlns=\"http://www.w3.org/1999/xhtml\"", "");
SgmlReader reader = new SgmlReader();
reader.DocType = "HTML";
reader.InputStream = new StringReader(backstring);
StringWriter sw = new StringWriter();
XmlTextWriter writer = new XmlTextWriter(sw);
reader.WhitespaceHandling = WhitespaceHandling.None;
writer.Formatting = Formatting.Indented;
while (reader.Read())
{
if (reader.NodeType != XmlNodeType.Whitespace)
{
writer.WriteNode(reader, true);
}
}
XmlDocument doc = new XmlDocument();
doc.Load(new StringReader(sw.ToString()));
XmlNamespaceManager xnm = new XmlNamespaceManager(doc.NameTable);
xnm.AddNamespace("bottum", "http://www.w3.org/1999/xhtml");
XPathNavigator nav = doc.CreateNavigator();
string xpath = "/html/body/table[8]/tr/td";
XPathNodeIterator nodes = nav.Select(xpath, xnm);//xpath表达式
if (nodes.Count >= 2)
{
nodes.MoveNext();
nodes.MoveNext();
}
ResultInfo backinfo = new ResultInfo(querynum);
for (int i = 1; i < nodes.Count / 2; i++)
{
nodes.MoveNext();
string time = nodes.Current.Value;
nodes.MoveNext();
string state = nodes.Current.Value;
backinfo.add(time, state);
}
reader.Close();
writer.Close();
sw.Close();
return(backinfo);
}
/***************************************************************************
* Useful debugging code...
* **************************************************************************/
void StartCrawl(SgmlReader reader, string uri, bool basify)
{
Console.WriteLine("Loading '" + reader.BaseURI + "'");
XmlDocument doc = new XmlDocument();
try {
doc.XmlResolver = null; // don't do any downloads!
doc.Load(reader);
}
catch (Exception e) {
Console.WriteLine("Error loading document\n" + e.Message);
}
reader.Close();
if (basify)
{
// html and head are option, if they are there use them otherwise not.
XmlElement be = (XmlElement)doc.SelectSingleNode("//base");
if (be == null)
{
be = doc.CreateElement("base");
be.SetAttribute("href", doc.BaseURI);
XmlElement head = (XmlElement)doc.SelectSingleNode("//head");
if (head != null)
{
head.InsertBefore(be, head.FirstChild);
}
else
{
XmlElement html = (XmlElement)doc.SelectSingleNode("//html");
if (html != null)
{
html.InsertBefore(be, html.FirstChild);
}
else
{
doc.DocumentElement.InsertBefore(be, doc.DocumentElement.FirstChild);
}
}
}
}
try {
Crawl(reader.Dtd, doc, reader.ErrorLog);
}
catch (Exception e) {
Console.WriteLine("Uncaught exception: " + e.Message);
}
}
XmlDocument FetchXmlDocument(Uri url)
{
var sr = FetchWebText(url);
var xr = new SgmlReader()
{
InputStream = sr
};
var doc = new XmlDocument();
doc.Load(xr);
sr.Close();
xr.Close();
return(doc);
}
private void ParsePageText()
{
// DateTime startTime;
// DateTime endTime;
SgmlReader reader = new SgmlReader();
try
{
reader.InputStream = new StringReader(FixHtmlToAvoidParseErrors(pageText));
// startTime = DateTime.Now;
reader.Dtd = ParseDtd(reader.NameTable); // note: this is last-found performance bottleneck; not yet fixed. Retest before fixing.
// endTime = DateTime.Now;
reader.ErrorLog = Console.Error;
reader.DocType = "HTML";
document = new XhtmlDocument(reader.NameTable);
try
{
document.Load(reader);
}
catch (WebException e)
{
throw new DoctypeDtdException(e);
}
ParseForms();
// totalParseTime += endTime - startTime;
// Console.WriteLine("parser: " + totalParseTime);
}
catch (XmlException e)
{
Console.WriteLine("vvvvvv The following HTML could not be parsed by NUnitAsp vvvvvv");
Console.WriteLine(pageText);
Console.WriteLine("^^^^^^ The preceding HTML could not be parsed by NUnitAsp ^^^^^^");
throw new ParseException("Could not parse HTML. See standard out for the HTML and use a validator (such as the one at validator.w3.org) to troubleshoot. Parser error was: " + e.Message);
}
finally
{
reader.Close();
}
}
private ResultInfo getDetail(string backstring)
{
//////////////用sgml库分析网页，转换成xml文件
SgmlReader readern = new SgmlReader();
readern.DocType = "HTML";
readern.InputStream = new StringReader(backstring);
StringWriter sw = new StringWriter();
XmlTextWriter writer = new XmlTextWriter(sw);
readern.WhitespaceHandling = WhitespaceHandling.None;
writer.Formatting = Formatting.Indented;
while (!readern.EOF)
{
readern.Read();
if (readern.NodeType != XmlNodeType.Whitespace)
{
writer.WriteNode(readern, true);
}
}
XmlDocument doc = new XmlDocument();
doc.Load(new StringReader(sw.ToString()));
XmlNamespaceManager xnm = new XmlNamespaceManager(doc.NameTable);
XPathNavigator nav = doc.CreateNavigator();
string xpath = "//div[@id='ess_ctr1579_TrackResult_DivBill']/table[2]/tr[@class='font_c']/td";
XPathNodeIterator nodes = nav.Select(xpath, xnm);//xpath表达式
ResultInfo backinfo = new ResultInfo(queryNumber);
for (int i = 0; i < nodes.Count / 2; i++)
{
nodes.MoveNext();
string time = nodes.Current.Value;
nodes.MoveNext();
string state = nodes.Current.Value;
backinfo.add(time, state);
}
readern.Close();
writer.Close();
sw.Close();
return(backinfo);
}
/// <summary>
/// 转换成Xhtml
/// </summary>
/// <param name="html">html代码</param>
/// <returns>Xhtml代码</returns>
public static string ToXhtml(string html)
{
SgmlReader reader = new SgmlReader();
reader.CaseFolding = CaseFolding.ToLower;
reader.DocType = "HTML";
reader.InputStream = new StringReader(html);
StringWriter sw = new StringWriter(CultureInfo.InvariantCulture);
XmlTextWriter writer = new XmlTextWriter(sw);
writer.Formatting = Formatting.Indented;
reader.WhitespaceHandling = WhitespaceHandling.None;
while (!reader.EOF)
{
writer.WriteNode(reader, true);
}
reader.Close();
sw.Close();
writer.Close();
return(sw.ToString());
}
private void ParsePageText()
{
SgmlReader reader = new SgmlReader();
try
{
reader.InputStream = new StringReader(FixHtmlToAvoidParseErrors(pageText));
reader.Dtd = ParseDtd(reader.NameTable);
// EP 02/01/07 - Don't output the errors, there are too many of them!
//reader.ErrorLog = Console.Error;
reader.DocType = "HTML";
document = new XhtmlDocument(reader.NameTable);
try
{
document.Load(reader);
}
catch (WebException e)
{
throw new DoctypeDtdException(e);
}
ParseInitialFormValues();
}
catch (XmlException e)
{
Console.WriteLine("vvvvvv The following HTML could not be parsed by NUnitAsp vvvvvv");
Console.WriteLine(pageText);
Console.WriteLine("^^^^^^ The preceding HTML could not be parsed by NUnitAsp ^^^^^^");
throw new ParseException("Could not parse HTML. See standard out for the HTML and use a validator (such as the one at validator.w3.org) to troubleshoot. Parser error was: " + e.Message);
}
finally
{
reader.Close();
}
}
/// <summary>
/// Run the SgmlReader command line tool with the given command line arguments.
/// </summary>
/// <param name="args"></param>
public void Run(string[] args)
{
SgmlReader reader = new SgmlReader();
string inputUri = null;
for (int i = 0; i < args.Length; i++)
{
string arg = args[i];
if (arg[0] == '-' || arg[0] == '/')
{
switch (arg.Substring(1))
{
case "e":
string errorlog = args[++i];
if ("$stderr".Equals(errorlog, StringComparison.OrdinalIgnoreCase))
{
reader.ErrorLog = Console.Error;
}
else
{
reader.ErrorLog = new StreamWriter(errorlog);
}
break;
case "html":
reader.DocType = "HTML";
break;
case "dtd":
reader.SystemLiteral = args[++i];
break;
case "proxy":
proxy = args[++i];
reader.WebProxy = new WebProxy(proxy);
break;
case "encoding":
encoding = Encoding.GetEncoding(args[++i]);
break;
case "nobom":
noUtf8Bom = true;
break;
case "f":
formatted = true;
reader.WhitespaceHandling = WhitespaceHandling.None;
break;
case "trimtext":
reader.TextWhitespace = TextWhitespaceHandling.TrimBoth;
break;
case "noxml":
noxmldecl = true;
break;
case "doctype":
reader.StripDocType = false;
break;
case "lower":
reader.CaseFolding = CaseFolding.ToLower;
break;
case "upper":
reader.CaseFolding = CaseFolding.ToUpper;
break;
default:
string exeName = Environment.GetCommandLineArgs()[0];
string exeVersion = typeof(CommandLine).Assembly.GetName().Version?.ToString();
Console.WriteLine("{0} - version {1}", exeName, exeVersion);
Console.WriteLine(" https://github.com/lovettchris/SgmlReader");
Console.WriteLine();
Console.WriteLine("Usage: {0} <options> [InputUri] [OutputFile]", exeName);
Console.WriteLine();
Console.WriteLine("<options>:");
Console.WriteLine(" -help Prints this list of command-line options");
Console.WriteLine(" -e log Optional log file name, name of '$STDERR' will write errors to stderr");
Console.WriteLine(" -f Whether to pretty print the output.");
Console.WriteLine(" -html Specify the built in HTML dtd");
Console.WriteLine(" -dtd url Specify other SGML dtd to use");
Console.WriteLine(" -base Add base tag to output HTML");
Console.WriteLine(" -noxml Do not add XML declaration to the output");
Console.WriteLine(" -proxy svr:80 Proxy server to use for http requests");
Console.WriteLine(" -encoding name Specify an encoding for the output file (default UTF-8)");
Console.WriteLine(" -nobom Prevents output of the BOM when using UTF-8");
Console.WriteLine(" -f Produce indented formatted output");
Console.WriteLine(" -trimtext SGML `#text` nodes will be trimmed of outer whitespace");
Console.WriteLine(" -lower Convert input tags to lower case");
Console.WriteLine(" -upper Convert input tags to UPPER CASE");
Console.WriteLine();
Console.WriteLine(" InputUri The input file or http URL (defaults to stdin if not specified)");
Console.WriteLine(" Supports wildcards for local file names.");
Console.WriteLine(" OutputFile Output file name (defaults to stdout if not specified)");
Console.WriteLine(" If input file contains wildcards then this just specifies the output file extension (default .xml)");
return;
}
}
else
{
if (inputUri == null)
{
inputUri = arg;
string ext = Path.GetExtension(arg).ToLower();
if (ext == ".htm" || ext == ".html")
{
reader.DocType = "HTML";
}
}
else if (output == null)
{
output = arg;
}
}
}
if (inputUri != null && !inputUri.StartsWith("http://") && inputUri.IndexOfAny(new char[] { '*', '?' }) >= 0)
{
// wild card processing of a directory of files.
string path = Path.GetDirectoryName(inputUri);
if (path == "")
{
path = ".\\";
}
string ext = ".xml";
if (output != null)
{
ext = Path.GetExtension(output);
}
foreach (string uri in Directory.GetFiles(path, Path.GetFileName(inputUri)))
{
Console.WriteLine("Processing: " + uri);
string file = Path.GetFileName(uri);
output = Path.GetDirectoryName(uri) + Path.DirectorySeparatorChar + Path.GetFileNameWithoutExtension(file) + ext;
Process(reader, uri);
reader.Close();
}
return;
}
Process(reader, inputUri);
reader.Close();
return;
}
bool Crawl(SgmlDtd dtd, XmlDocument doc, TextWriter log) {
depth++;
StringBuilder indent = new StringBuilder();
for (int i = 0; i < depth; i++)
indent.Append(" ");
count++;
Uri baseUri = new Uri(doc.BaseURI);
XmlElement baseElmt = (XmlElement)doc.SelectSingleNode("/html/head/base");
if (baseElmt != null) {
string href = baseElmt.GetAttribute("href");
if (href != "") {
try {
baseUri = new Uri(href);
}
catch (Exception ) {
Console.WriteLine("### Error parsing BASE href '"+href+"'");
}
}
}
foreach (XmlElement a in doc.SelectNodes("//a")) {
string href = a.GetAttribute("href");
if (href != "" && href != null && depth<5) {
Uri local = new Uri(baseUri, href);
if (domain && baseUri.Host != local.Host)
continue;
string ext = Path.GetExtension(local.AbsolutePath).ToLower();
if (ext == ".jpg" || ext == ".gif" || ext==".mpg")
continue;
string url = local.AbsoluteUri;
if (!visited.ContainsKey(url)) {
visited.Add(url, url);
log.WriteLine(indent+"Loading '"+url+"'");
log.Flush();
StreamReader stm = null;
try {
HttpWebRequest wr = (HttpWebRequest)WebRequest.Create(url);
wr.Timeout = 10000;
if (proxy != null) wr.Proxy = new WebProxy(proxy);
wr.PreAuthenticate = false;
// Pass the credentials of the process.
wr.Credentials = CredentialCache.DefaultCredentials;
WebResponse resp = wr.GetResponse();
Uri actual = resp.ResponseUri;
if (actual.AbsoluteUri != url) {
local = new Uri(actual.AbsoluteUri);
log.WriteLine(indent+"Redirected to '"+actual.AbsoluteUri+"'");
log.Flush();
}
if (resp.ContentType != "text/html") {
log.WriteLine(indent+"Skipping ContentType="+resp.ContentType);
log.Flush();
resp.Close();
}
else {
stm = new StreamReader(resp.GetResponseStream());
}
}
catch (Exception e) {
log.WriteLine(indent+"### Error opening URL: " + e.Message);
log.Flush();
}
if (stm != null) {
SgmlReader reader = new SgmlReader();
reader.Dtd = dtd;
reader.SetBaseUri(local.AbsoluteUri);
reader.InputStream = stm;
reader.WebProxy = proxy;
XmlDocument d2 = new XmlDocument();
d2.XmlResolver = null; // don't do any downloads!
try {
d2.Load(reader);
reader.Close();
stm.Close();
if (!Crawl(dtd, d2, log))
return false;
}
catch (Exception e) {
log.WriteLine(indent+"### Error parsing document '"+local.AbsoluteUri+"', "+e.Message);
log.Flush();
reader.Close();
}
}
}
}
}
depth--;
return true;
}
public void Run(string[] args)
{
SgmlReader reader = new SgmlReader();
string inputUri = null;
for (int i = 0; i < args.Length; i++)
{
string arg = args[i];
if (arg[0] == '-' || arg[0] == '/')
{
switch (arg.Substring(1))
{
case "e":
string errorlog = args[++i];
if (errorlog.ToLower() == "$stderr")
{
reader.ErrorLog = Console.Error;
}
else
{
reader.ErrorLogFile = errorlog;
}
break;
case "html":
reader.DocType = "HTML";
break;
case "dtd":
reader.SystemLiteral = args[++i];
break;
case "proxy":
proxy = args[++i];
reader.WebProxy = proxy;
break;
case "encoding":
encoding = Encoding.GetEncoding(args[++i]);
break;
case "f":
formatted = true;
reader.WhitespaceHandling = WhitespaceHandling.None;
break;
case "noxml":
noxmldecl = true;
break;
case "doctype":
reader.StripDocType = false;
break;
case "lower":
reader.CaseFolding = CaseFolding.ToLower;
break;
case "upper":
reader.CaseFolding = CaseFolding.ToUpper;
break;
default:
Console.WriteLine("Usage: SgmlReader <options> [InputUri] [OutputFile]");
Console.WriteLine("-e log Optional log file name, name of '$STDERR' will write errors to stderr");
Console.WriteLine("-f Whether to pretty print the output.");
Console.WriteLine("-html Specify the built in HTML dtd");
Console.WriteLine("-dtd url Specify other SGML dtd to use");
Console.WriteLine("-base Add base tag to output HTML");
Console.WriteLine("-noxml Do not add XML declaration to the output");
Console.WriteLine("-proxy svr:80 Proxy server to use for http requests");
Console.WriteLine("-encoding name Specify an encoding for the output file (default UTF-8)");
Console.WriteLine("-lower Convert input tags to lower case");
Console.WriteLine("-upper Convert input tags to upper case");
Console.WriteLine();
Console.WriteLine("InputUri The input file or http URL (default stdin). ");
Console.WriteLine(" Supports wildcards for local file names.");
Console.WriteLine("OutputFile Output file name (default stdout)");
Console.WriteLine(" If input file contains wildcards then this just specifies the output file extension (default .xml)");
return;
}
}
else
{
if (inputUri == null)
{
inputUri = arg;
string ext = Path.GetExtension(arg).ToLower();
if (ext == ".htm" || ext == ".html")
{
reader.DocType = "HTML";
}
}
else if (output == null)
{
output = arg;
}
}
}
if (inputUri != null && !inputUri.StartsWith("http://") && inputUri.IndexOfAny(new char[] { '*', '?' }) >= 0)
{
// wild card processing of a directory of files.
string path = Path.GetDirectoryName(inputUri);
if (path == "")
{
path = ".\\";
}
string ext = ".xml";
if (output != null)
{
ext = Path.GetExtension(output);
}
foreach (string uri in Directory.GetFiles(path, Path.GetFileName(inputUri)))
{
Console.WriteLine("Processing: " + uri);
string file = Path.GetFileName(uri);
output = Path.GetDirectoryName(uri) + Path.DirectorySeparatorChar + Path.GetFileNameWithoutExtension(file) + ext;
Process(reader, uri);
reader.Close();
}
return;
}
Process(reader, inputUri);
reader.Close();
return;
}
