|
很有意思的一段代码，代码实现对HTML内容中所有图片信息的提取，大家有时间的可以研究一下，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; } } |