很有意思的一段代碼，代碼實(shí)現(xiàn)對(duì)HTML內(nèi)容中所有圖片信息的提取，大家有時(shí)間的可以研究一下，完善一下程序。 protected ArrayList GetAList(string HtmlContent)
{
try
{
ArrayList arr = new ArrayList();
HtmlContent = content.Replace(\"\\r\\n\",\"\");
HtmlContent = content.Trim();
string partern = @\"\\<img(.*?)\\>\";//@\"<a (.*)>.*</a> \";//\"＜a.*(?=Headline)(.|\\n)*?＜/a＞\";//@\"/<a (.*)>.*<\\/\\a>/ \";
System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(partern, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.MatchCollection mc = regex.Matches(HtmlContent);
if(mc.Count <= 0)
return arr;
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@\"(\'|\"\"|/)?[\\w_()]*(.jpg|.bmp|.gif|.png|.jpeg)\",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
foreach(Match m in mc)
{
System.Text.RegularExpressions.MatchCollection m2 = regex2.Matches(m.ToString());
if( m2.Count > 0 )
{
arr.Add( m2[0].ToString().Substring(1) );
}
}
return arr;
}
catch(Exception ex)
{
throw ex;
}
} |
