獲取文本中全部的標籤的位置,獲取全部img標籤的src

        public static int[] GetImagePos(string str)
        {
            str = str.Replace("$", " ");
            str = Regex.Replace(str, @"(?!<img.+?>)<.+?>", "");
            str = Regex.Replace(str, @"<img\b[^>]*>", "$");
            int startPos = 0;
            int foundPos = -1;
            int count = 0;
            List<int> foundItems = new List<int>();

            do
            {
                foundPos = str.IndexOf("$", startPos);
                if (foundPos > -1)
                {
                    startPos = foundPos + 1;
                    count++;
                    foundItems.Add(foundPos);
                }
            } while (foundPos > -1 && startPos < str.Length);

            return ((int[])foundItems.ToArray());
        }

  

        /// <summary>  
        /// 獲取Img的路徑  
        /// </summary>  
        /// <param name="htmlText">Html字符串文本</param>  
        /// <returns>以數組形式返回圖片路徑</returns>  
        public static string[] GetHtmlImageUrlList(string htmlText)
        {
            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);
            //新建一個matches的MatchCollection對象 保存 匹配對象個數(img標籤)  
            MatchCollection matches = regImg.Matches(htmlText);
            int i = 0;
            string[] sUrlList = new string[matches.Count];
            //遍歷全部的img標籤對象  
            foreach (Match match in matches)
            {
                //獲取全部Img的路徑src,並保存到數組中  
                sUrlList[i++] = match.Groups["imgUrl"].Value;
            }
            return sUrlList;
        }
相關文章
相關標籤/搜索