Time is enough.C #Write a paragraphRegular ExpressionTo delete the code in the pageHTML TagThis is useful in collecting information and eliminating HTML.
The following is a reference clip:
Public String checkstr (string HTML)
{
System. text. regularexpressions. regEx regex1 = new system. text. regularexpressions. regEx (@ "<SCRIPT [\ s] + </script *>", system. text. regularexpressions. regexoptions. ignorecase );
System. text. regularexpressions. regEx regex2 = new system. text. regularexpressions. regEx (@ "href * = * [\ s] * script *:", system. text. regularexpressions. regexoptions. ignorecase );
System. text. regularexpressions. regEx regex3 = new system. text. regularexpressions. regEx (@ "No [\ s] * =", system. text. regularexpressions. regexoptions. ignorecase );
System. text. regularexpressions. regEx regex4 = new system. text. regularexpressions. regEx (@ "<IFRAME [\ s] + </iframe *>", system. text. regularexpressions. regexoptions. ignorecase );
System. text. regularexpressions. regEx regex5 = new system. text. regularexpressions. regEx (@ "<frameset [\ s] + </frameset *>", system. text. regularexpressions. regexoptions. ignorecase );
System. text. regularexpressions. regEx regex6 = new system. text. regularexpressions. regEx (@ "\ ] + \>", system. text. regularexpressions. regexoptions. ignorecase );
System. Text. regularexpressions. RegEx regex7 = new system. Text. regularexpressions. RegEx (@ "</P>", system. Text. regularexpressions. regexoptions. ignorecase );
System. Text. regularexpressions. RegEx regex8 = new system. Text. regularexpressions. RegEx (@ "<p>", system. Text. regularexpressions. regexoptions. ignorecase );
System. Text. regularexpressions. RegEx regex9 = new system. Text. regularexpressions. RegEx (@ "<[^>] *>", system. Text. regularexpressions. regexoptions. ignorecase );
Html = regex1.replace (HTML, ""); // filter <SCRIPT> </SCRIPT> tags
Html = regex2.replace (HTML, ""); // filter href = javascript: (<A>) attributes
Html = regex3.replace (HTML, "_ disibledevent ="); // filter events of other controls.
Html = regex4.replace (HTML, ""); // filter IFRAME
Html = regex5.replace (HTML, ""); // filter frameset
Html = regex6.replace (HTML, ""); // filter frameset
Html = regex7.replace (HTML, ""); // filter frameset
Html = regex8.replace (HTML, ""); // filter frameset
Html = regex9.replace (HTML ,"");
Html = html. Replace ("","");
Html = html. Replace ("</strong> ","");
Html = html. Replace ("<strong> ","");
Return HTML;
}