C#爬蟲獲取網頁中表格數據

        /// <summary>

        /// C#爬蟲獲取網頁中表格的數據

        /// </summary>

        public void GetDataFromNet() {

            //爬取的網頁地址

            string url="http://www.sse.net.cn/index/singleIndex?indexType=cbcfi";

            //若是POST請求，下面一行代碼解註釋

            //request.Method = "POST";

            WebRequest request = WebRequest.Create(url);

            WebResponse response = (WebResponse)request.GetResponse();

            Stream dataStream = response.GetResponseStream();

            StreamReader reader = new StreamReader(dataStream, Encoding.UTF8);

            //此處將爬取到的內容轉換爲HTML

            string strHTML = reader.ReadToEnd();

            //也可以將HTML直接轉換爲dynamic對象，按需選擇

            //dynamic Datas = JsonConvert.DeserializeObject(strHTML);

            var list = new List<string>();

            //正則表達式獲取table所有行==>mc

            Regex reg = new Regex("(?is)(?<=<table[^>]*?[^>]*?>(?:(?!</?table).)*)(?is)<tr[^>]*?[^>]*?>(?:\\s*<td[^>]*>(.*?)</td>)*\\s*</tr>");

            MatchCollection mc = reg.Matches(strHTML);

            foreach (Match mat in mc)

            {

                //正則表達式獲取每行所有的td

                Regex reg1 = new Regex(@"<td.*?>(?<value>.*?)</td>");

                //mat.Value是表格中每一行的HTML字符串

                bool abc = false;

                foreach (Match m in reg1.Matches(mat.Value))//類似循環一行的每個td

                {

                    string val = m.Groups["value"].Value;

                    if (val.IndexOf("本期") != -1)

                    {

                        list.Add(val.Substring(6));

                    }

                    if (val == "秦皇島-廣州（6-7萬DWT）")

                        abc = true;

                    if (abc)

                        list.Add(m.Groups["value"].Value);

                        //後續處理，保存到數據庫

                }

            }

            reader.Close();

            dataStream.Close();

            response.Close();

        }