/// <summary> /// 獲得HTML中所有圖片的src地址 /// </summary> /// <param name="sHtmlText">HTML代碼</param> /// <returns>圖片的URL列表</returns> public static string[] GetHtmlImageUrlList(string sHtmlText) { // 定義正則表達式用來匹配 img 標簽 Regex regImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase); // 搜索匹配的字符串 MatchCollection matches = regImg.Matches(sHtmlText); int i = 0; string[] sUrlList = new string[matches.Count]; // 取得匹配項列表 foreach (Match match in matches) sUrlList[i++] = match.Groups["imgUrl"].Value; return sUrlList; }
