public void TestSpeed() { var html = Html; var times = 1000; var htmlAgilityPack = Time(times, () => { var doc = new HtmlAgilityPack.HtmlDocument(); doc.LoadHtml(html); var input = doc.DocumentNode.Descendants("input").FirstOrDefault(); var value = input.GetAttributeValue("value", string.Empty); value.Should().Equal("*****@*****.**"); }); var xhtmlr = Time(times, () => { var doc = System.Xml.Linq.XDocument.Parse(XHTML.ToXml(html)); var input = doc.Descendants("input").FirstOrDefault(); var value = (string)input.Attribute("value"); value.Should().Equal("*****@*****.**"); }); Console.WriteLine("HTML Agility Pack: {0}ms", htmlAgilityPack); Console.WriteLine(" XHTMLr: {0}ms", xhtmlr); }
private XDocument ParseHtml(ref string html, XHTML.Options options = XHTML.Options.Default) { // html = XHTML.ToXml(html, options); html = XHTML.ToXml(html, XHTML.Options.Default | XHTML.Options.Pretty); return(XDocument.Parse(html)); }
public void TestPage() { using (var web = new System.Net.WebClient()) { var html = web.DownloadString("http://ch.tbe.taleo.net/CH11/ats/careers/requisition.jsp?org=INTERTEK&cws=4&rid=3291&utm_source=linkup&utm_medium=referrer"); var xml = XHTML.ToXml(html, XHTML.Options.Default); var xdoc = XDocument.Parse(xml); xdoc.Descendants() .FirstOrDefault(x => (string)x.Attribute("id") == "taleoContent") .Should().Not.Be.Null(); } }
public void FontFontFont() { var html = @"<SPAN lang=EN> <P dir=ltr align=left>Thank you for choosing <FONT color=#ff0000><FONT color=#ff0000><FONT color=#ff0000>asdf</FONT></FONT></FONT> asdf. </P> <P dir=ltr align=left> </P><B> <P dir=ltr align=left></P></B> <P dir=ltr align=left>Sincerely,</P> <P dir=ltr align=left></P> <P dir=ltr align=left>Customer Service </P> <P dir=ltr align=left>Phone: 1-888-333-4444 </P> <P dir=ltr align=left>Fax: 1-888-333-5555</P> <P dir=ltr align=left>Email: </SPAN><A href=""mailto:[email protected]""><FONT color=#0000ff><FONT color=#0000ff><FONT color=#0000ff><SPAN lang=EN>[email protected]</FONT></FONT></FONT></SPAN></A></P> <P dir=ltr align=left> </P><U><FONT face=Arial><FONT face=Arial><SPAN lang=EN> <P dir=ltr align=left><FONT face=""Times New Roman""></FONT></P> <P dir=ltr align=left><FONT face=""Times New Roman"">Customer Service Hours</FONT></P></U> <P dir=ltr align=left><FONT face=""Times New Roman"">Mon-Fri: 7:00am to 10:00pm CST</FONT></P> <P dir=ltr align=left><FONT face=""Times New Roman"">Sat-Sun: 9:00am to 6:00pm CST</FONT></P></FONT></FONT></SPAN>"; var xhtml = XHTML.ToXml(html); Console.WriteLine(xhtml); }
private XDocument ParseHtml(ref string html, XHTML.Options options = XHTML.Options.Default) { // html = XHTML.ToXml(html, options); html = XHTML.ToXml(html, XHTML.Options.Default | XHTML.Options.Pretty); return XDocument.Parse(html); }