public void Empty()
{
reader = HtmlReaderFactory.FromString("", parseErrors);
Assert.IsFalse(reader.Read());
Assert.AreEqual(0, parseErrors.Count);
}
/// <summary>
/// Sanitizes the specified HTML, removing scripts, styles, and tags
/// which might pose a security concern
/// </summary>
/// <param name="html">The HTML content to minify. A <see cref="string"/> or <see cref="Stream"/> can also be used.</param>
/// <param name="writer">Writer to which the sanitized HTML is written</param>
/// <param name="settings">Settings controlling what CSS and HTML is permitted in the result</param>
/// <remarks>
/// The goal of sanitization is to prevent XSS patterns
/// described on <a href="https://www.owasp.org/index.php/XSS_Filter_Evasion_Cheat_Sheet">XSS Filter Evasion Cheat Sheet</a>
/// </remarks>
public static void Sanitize(TextSource html, XmlWriter writer, HtmlSanitizeSettings settings = null)
{
using (var reader = new HtmlReader(html, false))
{
reader.Sanitize(settings).ToHtml(writer);
}
}
public void TagDataTagData()
{
reader = HtmlReaderFactory.FromString("<br/>a<p/>b", parseErrors);
Assert.IsTrue(reader.Read());
Assert.AreEqual(HtmlTokenKind.Tag, reader.TokenKind);
Assert.AreEqual("br", reader.Name);
Assert.IsTrue(reader.SelfClosingElement);
Assert.IsTrue(reader.Read());
Assert.AreEqual(HtmlTokenKind.Text, reader.TokenKind);
Assert.AreEqual("a", reader.Text);
Assert.IsTrue(reader.Read());
Assert.AreEqual(HtmlTokenKind.Tag, reader.TokenKind);
Assert.AreEqual("p", reader.Name);
Assert.IsTrue(reader.SelfClosingElement);
Assert.IsTrue(reader.Read());
Assert.AreEqual(HtmlTokenKind.Text, reader.TokenKind);
Assert.AreEqual("b", reader.Text);
Assert.IsFalse(reader.Read());
Assert.AreEqual(0, parseErrors.Count);
}
/// <summary>
/// Compress HTML by removing unnecessary whitespace and comments
/// </summary>
/// <param name="html">The HTML content to minify. A <see cref="string"/> or <see cref="Stream"/> can also be used.</param>
/// <param name="writer">The writer where the HTML output is written. For best results, use a <see cref="HtmlTextWriter"/></param>
/// <param name="settings">Settings to control how the HTML is compressed</param>
public static void Minify(TextSource html, XmlWriter writer, HtmlMinifySettings settings = null)
{
using (var reader = new HtmlReader(html, false))
{
reader.Minify(settings).ToHtml(writer);
}
}
private void buttonConvert_Click(object sender, EventArgs e)
{
bool IsValid = true;
IsValid = this.IsValidOption(ref this.textBoxSourceHtmlFolder, ref this._textBoxSourceHtmlFolderColor) && IsValid;
IsValid = this.IsValidOption(ref this.textBoxXmlTemplate, ref this._textBoxXmlTemplate) && IsValid;
IsValid = this.IsValidOption(ref this.textBoxDestinationXmlFolder, ref this._textBoxDestinationXmlFolder) && IsValid;
if (!IsValid)
return;
this.buttonConvert.Enabled = false;
IEnumerable<string> SupportFiles = Directory.GetFiles(this.textBoxSourceHtmlFolder.Text, "*.*", SearchOption.AllDirectories).Where(s => _SupportedExtensions.Contains(Path.GetExtension(s).ToLower()));
progressBarStatus.Maximum = SupportFiles.Count();
foreach (string ImportDataSourceFile in SupportFiles)
{
XmlTemplateRW XmlTemplateRWObj = new XmlTemplateRW();
XmlTemplateRWObj.LoadXmlTemplate(this.textBoxXmlTemplate.Text);
HtmlReader HtmlReadObj = new HtmlReader();
if (HtmlReadObj.LoadHtml(ImportDataSourceFile))
{
string ImportDataDestinationFile = this.textBoxDestinationXmlFolder.Text + "\\" + Path.GetFileName(ImportDataSourceFile) + ".xml";
XmlTemplateRWObj.ExecutePlaceholderReplacement(HtmlReadObj);
XmlTemplateRWObj.Save(ImportDataDestinationFile);
}
progressBarStatus.PerformStep();
Application.DoEvents();
}
progressBarStatus.Value = 0;
this.buttonConvert.Enabled = true;
}
public void ShouldReturnLinkFromATag()
{
var htmlReader = new HtmlReader();
var result = htmlReader.GetLinksFromText(this.GetValidTestHtmlData());
result.First().Should().Be("https://www.orf.at");
}
public override List <TestRunImportResultInfo> GetTestRunImportResults()
{
var result = new List <TestRunImportResultInfo>();
if (Reader != null)
{
var runDate = DateTime.Now;
using (var htmlReader = new HtmlReader(Reader))
{
// move over all theads
while (htmlReader.ReadToFollowing("thead"))
{
if (htmlReader.ReadToFollowing("tr") && htmlReader.Attributes.Count > 0)
{
var classAttribute = htmlReader.Attributes["class"];
if (!string.IsNullOrEmpty(classAttribute) && classAttribute.Contains("status_"))
{
var table = ParseTrTag(htmlReader);
if (table != null)
{
table.RunDate = runDate;
result.Add(table);
}
}
}
}
}
}
return(result);
}
public void RoundTrip_SgmlReader36()
{
var html = @"<html>
<head>
<script language=""JavaScript"">
<!--
--></script>
</head>
<body>
<p>hello</p>
</body>
</html> ";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<html>
<head>
<script language=""JavaScript"">
<!--
--></script>
</head>
<body>
<p>hello</p>
</body>
</html> ", rendered);
}
}
public GameController(Account account, TabPage tabPage)
{
tabPage.Text = account.AccountName + " - Speed: " + account.Speed.ToString();
PlayerAccount = account;
WebBrowser = (WebBrowser)tabPage.Controls.Find("webBrowser", true)[0];
WebBrowser.ScriptErrorsSuppressed = true;
StatusStrip ss = (StatusStrip)tabPage.Controls.Find("statusStrip1", true)[0];
ProgressBar = (ToolStripProgressBar)ss.Items.Find("tspbOpperationProgress", true)[0];
ProgressLabel = (ToolStripStatusLabel)ss.Items.Find("tsslOpperation", true)[0];
ProgressLabel.Text = "Starting up, starting login soon.";
Client = new CustomHttpClient(account);
HtmlReader = new HtmlReader();
WorkerPriorityQueue = new SimplePriorityQueue <IWorker, int>();
var loginWorker = new LoginWorker(PlayerAccount, Client, HtmlReader, WebBrowser, ProgressLabel, ProgressBar);
loginWorker.Worker.RunWorkerCompleted += Worker_RunWorkerCompleted;
WorkerPriorityQueue.Enqueue(loginWorker, 0);
IWorker worker = WorkerPriorityQueue.Dequeue();
worker.StartWork();
}
private static TestRunImportResultInfo ParseTrTag(HtmlReader htmlReader)
{
var parsed = false;
var testCaseName = string.Empty;
var testCaseSucceeded = false;
var attribute = htmlReader.Attributes["class"];
if (attribute != null)
{
var strings = attribute.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries);
foreach (var status in from s in strings where s.StartsWith("status_") select s.Substring("status_".Length))
{
testCaseSucceeded = string.Compare(status, "passed", StringComparison.InvariantCulture) == 0;
break;
}
if (htmlReader.ReadToFollowing("td"))
{
testCaseName = htmlReader.GetInnerTextUpToElement("td", HtmlNodeType.EndElement);
parsed = true;
}
}
return(parsed ? new TestRunImportResultInfo {
Name = testCaseName, IsSuccess = testCaseSucceeded
} : null);
}
public string Render()
{
StringBuilder sb = new StringBuilder();
sb.AppendLine(HtmlReader.Read(Constans.Header));
sb.AppendLine(HtmlReader.Read(Constans.NavLogged));
sb.AppendLine(HtmlReader.Read(Constans.Home));
int count = 1;
foreach (var model in this.Model)
{
if (count == 3)
{
sb.AppendLine("</div>");
count = 1;
}
sb.AppendLine("<div class=\"row\"");
sb.Append(model.ToString());
count++;
}
sb.AppendLine(Environment.NewLine);
sb.AppendLine(HtmlReader.Read(Constans.HomeEnd));
sb.AppendLine(HtmlReader.Read(Constans.Footer));
return(sb.ToString());
}
public async Task <IActionResult> ConvertHtmlToPdf()
{
_logger.LogInformation("Serving convert html to pdf");
var htmlContent = await HtmlReader.ReadHtmlFile();
return(await _reportService.ExportToPdf(htmlContent, false));
}
public static HtmlReader FromString(string html, List <HtmlParseErrorEventArgs> parseErrors)
{
var reader = new HtmlReader(new MemoryStream(Encoding.UTF8.GetBytes(html)));
reader.ParseError += (sender, args) => parseErrors.Add(args);
return(reader);
}
public void ShouldReturnNoLinkFromInvalidATag()
{
var htmlReader = new HtmlReader();
var result = htmlReader.GetLinksFromText(this.GetInvalidTestHtmlData());
result.Count().Should().Be(0);
}
public void RoundTrip_Basic()
{
var html = @"<!DOCTYPE html>
<html lang=""en"">
<head>
<meta charset=""utf-8"">
<title>The HTML5 Herald</title>
<meta name=""description"" content=""The HTML5 Herald"">
<meta name=""author"" content=""SitePoint"">
<link rel=""stylesheet"" href=""css/styles.css?v=1.0"">
<!--[if lt IE 9]>
<script src=""https://cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.3/html5shiv.js""></script>
<![endif]-->
</head>
<body>
<input type=""text"" required>
<script src=""js/scripts.js""></script>
</body>
</html>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(html, rendered);
}
}
public static HtmlReader FromStream(Stream stream, List <HtmlParseErrorEventArgs> parseErrors)
{
stream.Seek(0, SeekOrigin.Begin);
var reader = new HtmlReader(stream);
reader.ParseError += (sender, args) => parseErrors.Add(args);
return(reader);
}
private void CheckConversion(string html, string expected)
{
using (var reader = new HtmlReader(html))
{
var actual = reader.ToMarkdown();
Assert.Equal(expected, actual);
}
}
private string Read(string html)
{
using (var stream = new MemoryStream(Encoding.UTF8.GetBytes(html)))
{
var result = ((IEnumerable <HtmlChunk>)HtmlReader.Read(stream).ToList()).ToArray();
return(string.Join(", ", result.Select(x => x.Type + ":" + x.Value).ToArray()));
}
}
private void TestSanitize(string input, string expected, HtmlSanitizeSettings settings = null, HtmlWriterSettings writerSettings = null)
{
using (var reader = new HtmlReader(input))
{
var rendered = reader.Sanitize(settings ?? HtmlSanitizeSettings.Default()).ToHtml(writerSettings);
Assert.Equal(expected, rendered);
}
}
private void TestParser(string data, string expected)
{
using (var reader = new HtmlReader(data))
{
var rendered = reader.ToHtml();
Assert.Equal(expected, rendered);
}
}
public void RoundTrip_EntityName()
{
var html = @"<p>a±b</p>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<p>a±b</p>", rendered);
}
}
public void AttributeValueNamedCharacterReference()
{
reader = HtmlReaderFactory.FromString("<a title=\"<\">", parseErrors);
Assert.IsTrue(reader.Read());
Assert.AreEqual("<", reader.GetAttribute("title"));
Assert.IsFalse(reader.Read());
Assert.AreEqual(0, parseErrors.Count);
}
public void RoundTrip_SgmlReader15()
{
var html = @"<html xmlns=""http://www.w3.org/1999/xhtml""><head /><body><table u1:str="""" x:str=""""></table></body></html>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<html xmlns=""http://www.w3.org/1999/xhtml""><head></head><body><table u1:str x:str></table></body></html>", rendered);
}
}
public void RoundTrip_SgmlReader46()
{
var html = @"blah <b>foo</b>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(html, rendered);
}
}
public static void Initialize()
{
var allContentHtmls = Directory.GetFiles("../../content");
foreach (var htmlPath in allContentHtmls)
{
var htmlName = htmlPath.Substring(htmlPath.LastIndexOf(@"\") + 1);
htmls.Add(htmlName, HtmlReader.ReadHtml(htmlPath));
}
}
public void RoundTrip_SgmlReader22()
{
var html = @"<html><body>do <![if !supportLists]>not<![endif]> lose this text</body></html>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<html><body>do <![if !supportLists]>not<![endif]> lose this text</body></html>", rendered);
}
}
public void RoundTrip_SgmlReader24()
{
var html = @"<html xmlns:n=""http://explicit""><foo attr1=""1"" n:attr2=""2"" /><n:foo attr1=""1"" n:attr2=""2"" /></html>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<html xmlns:n=""http://explicit""><foo attr1=""1"" n:attr2=""2""></foo><n:foo attr1=""1"" n:attr2=""2""></n:foo></html>", rendered);
}
}
public void RoundTrip_SgmlReader28()
{
var html = @"<html xmlns:o=""http://microsoft.com""><body>A<o:p></o:p>B<o:p></o:p></body></html>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<html xmlns:o=""http://microsoft.com""><body>A<o:p></o:p>B<o:p></o:p></body></html>", rendered);
}
}
public void RoundTrip_SgmlReader60()
{
var html = @"<p>&#x;</p>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<p>&#x;</p>", rendered);
}
}
public void RoundTrip_VoidElementCloseTag()
{
var html = @"<p><img src></img></p>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<p><img src></p>", rendered);
}
}
public void RoundTrip_SgmlReader39()
{
var html = @"<html><class=""black"">Text………</html>";
using (var reader = new HtmlReader(html))
{
var rendered = reader.ToHtml();
Assert.Equal(@"<html><class=""black"">Text………</class=""black""></html>", rendered);
}
}
private string GetPlaceholdContent(string PlaceholderName, HtmlReader LoadedHtmlReader)
{
string RetPlaceholderContent = "";
switch (PlaceholderName)
{
case TemplatePlacholderInternal.FileName:
RetPlaceholderContent = Path.GetFileName(LoadedHtmlReader.FullFilePath);
break;
case TemplatePlacholderInternal.FilePath:
RetPlaceholderContent = Path.GetDirectoryName(LoadedHtmlReader.FullFilePath);
break;
default:
string PlaceholderRegex = PlaceholderName.TrimStart(new char[] { '{' }).TrimEnd(new char[] { '}' });
if (PlaceholderName.StartsWith("{{{"))
{
RetPlaceholderContent = LoadedHtmlReader.GetOuterHtmlContent(PlaceholderRegex);
}
else if (PlaceholderName.StartsWith("{{"))
{
RetPlaceholderContent = LoadedHtmlReader.GetInnerHtmlContent(PlaceholderRegex);
}
else if (PlaceholderName.StartsWith("{"))
{
string[] PlaceholderRegexArray = PlaceholderRegex.Split(',');
if (PlaceholderRegexArray.Length == 1)
{
RetPlaceholderContent = LoadedHtmlReader.GetCSVInnerHtmlContent(PlaceholderRegexArray[0]);
}
else if (PlaceholderRegexArray.Length == 2)
{
RetPlaceholderContent = LoadedHtmlReader.GetAttributeHtmlContent(PlaceholderRegexArray[0], PlaceholderRegexArray[1]);
string[] RetPlaceholderContentArray = RetPlaceholderContent.Split(',');
for (int i = 0; i < RetPlaceholderContentArray.Length; i++)
{
RetPlaceholderContentArray[i] = Path.GetFileName(RetPlaceholderContentArray[i]);
}
RetPlaceholderContent = String.Join(",", RetPlaceholderContentArray);
}
}
break;
}
return RetPlaceholderContent;
}
public void ExecutePlaceholderReplacement(HtmlReader LoadedHtmlReader)
{
XmlNodeList FoundNodes = _LoadedXmlDoc.DocumentElement.SelectNodes("//*");
foreach (XmlNode FoundNode in FoundNodes)
{
foreach (XmlNode ChildNode in FoundNode.ChildNodes)
{
if (ChildNode.NodeType == XmlNodeType.Text || ChildNode.NodeType == XmlNodeType.CDATA)
{
List<String> FoundPlaceholderNames = this.ParseForPlaceholder(ChildNode);
foreach (string FoundPlaceholderName in FoundPlaceholderNames)
{
string PlaceholderValue = this.GetPlaceholdContent(FoundPlaceholderName, LoadedHtmlReader);
ChildNode.InnerText = ChildNode.InnerText.Replace(FoundPlaceholderName, PlaceholderValue);
}
}
}
}
}
public void loops()
{
var webClient = new WebClient();
const string buy = "/buy/";
const string loops = "{0}/loops/{1}";
const string api = "{0}/api/loopdetails.aspx?loopname={1}";
var all = new Dictionary<string, Dictionary<string, IEnumerable<string>>>();
all.Add("premiumcollection", null);
all.Add("standardcollection", null);
all.Add("classiccollection", null);
// get loop pages
foreach (string collection in all.Keys.ToArray())
{
string url = string.Format(loops, host, collection);
// load HTML page
string source = webClient.DownloadString(url);
Assert.IsTrue(!String.IsNullOrEmpty(source), collection + " access denied");
// read url "Add to Cart"
all[collection] = new HtmlReader<Tags.A>().Read(source)
.Distinct()
.Where(i => !string.IsNullOrEmpty(i.Url) && i.Url.StartsWith(buy))
.Select(i => i.Url.Replace(buy, string.Empty))
.ToArray()
.GroupBy(x => x, x => string.Empty)
.ToDictionary(x => x.Key, x => Enumerable.Empty<string>());
Assert.IsNotNull(all[collection], collection + " links not found");
}
// get mp3 links
foreach (string collection in all.Keys.ToArray())
{
foreach (string loopname in all[collection].Keys.ToArray())
{
string url = string.Format(api, host, loopname);
string source = string.Empty;
try
{
// load HTML page
source = webClient.DownloadString(url);
}
catch (WebException)
{
continue;
}
string[] addresses = null;
if (!string.IsNullOrEmpty(source))
{
all[collection][loopname]
= new HtmlReader<Tags.Div>().Read(source)
.Where(i => string.CompareOrdinal(i.Class, "hide") == 0)
.Distinct()
.Select(i => i.Text.Trim())
.ToArray();
}
}
}
// save links
foreach (string collection in all.Keys.ToArray())
{
using (StreamWriter file =
new StreamWriter(Path.Combine(Directory.GetCurrentDirectory(), collection + "-links.txt")))
{
foreach (string link in all[collection].SelectMany(i => i.Value).Select(i => i))
file.WriteLine(string.Format("{0}{1}", host, link));
}
}
}
public void productionmusic()
{
var webClient = new WebClient();
string url = string.Format("{0}/productionmusic/ambient", host);
var all = new Dictionary<string, string[]>();
all.Add("genre",null);
all.Add("use", null);
all.Add("mood", null);
all.Add("inst", null);
Regex split = new Regex(@"'[\s\S][^']*'",RegexOptions.Compiled);
// load HTML page
string page = webClient.DownloadString(url);
var source = new HtmlReader<Tags.Input>().Read(page)
.Where(i => i.OnChange != null && i.Type != null && string.CompareOrdinal(i.Type, "checkbox") == 0)
.ToArray();
foreach (var list in all.Keys.ToArray())
{
all[list] = source.Where(i => i.OnChange.Contains(list + "_list"))
.Distinct()
.Select(i => split.Matches(i.OnChange)[2].Value.Replace("'", string.Empty))
.OrderBy(i => i)
.ToArray();
Assert.IsNotNull(list, list + " not found");
}
}
