您好我正在阅读一些关于如何从阅读网站源代码的网站获取数据的文章。据说我创建了一个例程来获取纽约和匹兹堡的计算机演出的Craigslist数据,如下所示。出于某种原因(可能是我在这方面缺乏知识)我只为匹兹堡和纽约分别收到25条记录。是否有可能获得今天的整个列表,甚至可能是数据范围
Friend Shared Function GetCraigslist() As DataTable
Dim dt As New DataTable
dt.Columns.Add("description")
dt.Columns.Add("Title")
dt.Columns.Add("link")
Dim XMLDoc As System.Xml.XmlDocument = New System.Xml.XmlDocument
Dim list As New List(Of String)
list.Add("https://pittsburgh.craigslist.org/cpg/index.rss")
list.Add("http://newyork.craigslist.org/cpg/index.rss")
For Each link In list
XMLDoc.Load(link)
Dim nTable As NameTable = XMLDoc.NameTable
Dim nsManager As XmlNamespaceManager = New XmlNamespaceManager(nTable)
nsManager.AddNamespace("rdf", "http://www.w3.org/1999/02/22-rdf-syntax-ns#")
nsManager.AddNamespace("item", "http://purl.org/rss/1.0/")
nsManager.AddNamespace("dc", "http://purl.org/dc/elements/1.1/")
Dim XMLItems As System.Xml.XmlNodeList = XMLDoc.DocumentElement.SelectNodes("//rdf:RDF/item:item", nsManager)
XMLDoc.Save("C:\development\data.xml")
For Each currentItem As Xml.XmlNode In XMLItems
Dim R As DataRow = dt.NewRow
R("Title") &= currentItem.SelectSingleNode("item:title", nsManager).InnerText
R("description") &= currentItem.SelectSingleNode("item:description", nsManager).InnerText
R("link") &= currentItem.SelectSingleNode("item:link", nsManager).InnerText
dt.Rows.Add(R)
Next
Next
Return dt
End Function