1)价格
(?<=<strong\\s+[^>]*\"J_StrPrice\"\\s+>)(?<1>[^<]*)(?=</strong>)
2)描述
分为2步,先获取描述地址,后获取地址内容。
(?<=')(?<1>http://dsc.taobaocdn.com.*)(?=')
取得地址后url 后,请求 http://dsc.taobaocdn.com/url
(?<=desc=')(?<1>.*)(?=';)
代码
1 Regex reg = new Regex(regExpGoodsDescString);
2 string tbdescUrl = GetMatchString(reg);
3 HttpWebRequest request = (HttpWebRequest)HttpWebRequest.Create(tbdescUrl);
4
5 HttpWebResponse req = (HttpWebResponse)request.GetResponse();
6 Stream stream = req.GetResponseStream();
7 StreamReader sr = new StreamReader(stream, Encoding.Default);
8 string desc = sr.ReadToEnd();
9
10 reg = new Regex("(?<=desc=')(?<1>.*)(?=';)", RegexOptions.Singleline | RegexOptions.Compiled);
11 return GetMatchString(reg, desc);
2 string tbdescUrl = GetMatchString(reg);
3 HttpWebRequest request = (HttpWebRequest)HttpWebRequest.Create(tbdescUrl);
4
5 HttpWebResponse req = (HttpWebResponse)request.GetResponse();
6 Stream stream = req.GetResponseStream();
7 StreamReader sr = new StreamReader(stream, Encoding.Default);
8 string desc = sr.ReadToEnd();
9
10 reg = new Regex("(?<=desc=')(?<1>.*)(?=';)", RegexOptions.Singleline | RegexOptions.Compiled);
11 return GetMatchString(reg, desc);