网址:https://mall.datayes.com/datapreview/549?lang=zh
请问怎么采集网页中全部列表内容,网页列表有滚动条。
需要直接采集网页内容,而不是下载文件,最好给出代码
https://gw.wmcloud.com/datamkt/whitelist/datapreview/549?lang=zh
https://gw.wmcloud.com/datamkt/whitelist/datapreview/549?lang=zh 同意楼上
//json对应的类模型,你要其他数据自己建立类模型
public class StockInfo { public System.Collections.Generic.List<System.Collections.Generic.List<string>> previewData;}
public class StockData { public StockInfo data;}
protected void Page_Load(object sender, EventArgs e)
{
Response.Charset = "utf-8";
Response.ContentEncoding = Encoding.UTF8;
WebClient wc = new WebClient();
byte[] data = wc.DownloadData("https://gw.wmcloud.com/datamkt/whitelist/datapreview/549?lang=zh");
wc.Dispose();
MemoryStream ms = new MemoryStream(data);
StreamReader sr = new StreamReader(ms, Encoding.UTF8);
string s = sr.ReadToEnd();
ms.Close(); sr.Close();
StockData stockdata = Newtonsoft.Json.JsonConvert.DeserializeObject<StockData>(s);//序列化为类实例
System.Collections.Generic.List<System.Collections.Generic.List<string>> stocklist = stockdata.data.previewData;
foreach (System.Collections.Generic.List<string> list in stocklist)
Response.Write(String.Join(" ", list.ToArray()) + "<BR>");
}