主题：获取网页数据

http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2013/index.html

用下面代码慢慢获取。一次性获取会很慢，红色代码慢慢注释掉，理解代码。

 

mark 获取网页数据

 

Dim url As String = "http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2013/"
For i As Integer = 11 To 65
    Dim web As new System.Windows.Forms.WebBrowser
    web.Navigate(url & i & ".html")
    Do While web.ReadyState <> 4
        Application.DoEvents
    Loop
    Dim trs = web.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
    For j As Integer = 1 To trs.count - 1
        Dim tr = trs(j)
        Dim tds = tr.GetElementsByTagName("td")
        output.show(tds(0).innerText)
        output.show(tds(1).innerText)
        output.show(tds(1).GetElementsByTagName("a")(0).GetAttribute("href"))
        Dim web1 As new System.Windows.Forms.WebBrowser
        web1.Navigate(tds(1).GetElementsByTagName("a")(0).GetAttribute("href"))
        Do While web1.ReadyState <> 4
            Application.DoEvents
        Loop
        Dim trs1 = web1.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
        For j1 As Integer = 1 To trs1.count - 1
            Dim tr1 = trs1(j1)
            Dim tds1 = tr1.GetElementsByTagName("td")
            output.show(tds1(0).innerText)
            output.show(tds1(1).GetElementsByTagName("a")(0).GetAttribute("href"))
            Dim web2 As new System.Windows.Forms.WebBrowser
            web2.Navigate(tds1(1).GetElementsByTagName("a")(0).GetAttribute("href"))
            Do While web2.ReadyState <> 4
                Application.DoEvents
            Loop
            Dim trs2 = web2.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
            For j2 As Integer = 1 To trs2.count - 1
                Dim tr2 = trs2(j2)
                Dim tds2 = tr2.GetElementsByTagName("td")
                output.show(tds2(0).innerText)
                output.show(tds2(1).GetElementsByTagName("a")(0).GetAttribute("href"))
                Dim web3 As new System.Windows.Forms.WebBrowser
                web3.Navigate(tds2(1).GetElementsByTagName("a")(0).GetAttribute("href"))
                Do While web3.ReadyState <> 4
                    Application.DoEvents
                Loop
                Dim trs3 = web3.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
                For j3 As Integer = 1 To trs3.count - 1
                    Dim tr3 = trs3(j3)
                    Dim tds3 = tr3.GetElementsByTagName("td")
                    output.show(tds3(0).innerText)
                    output.show(tds3(1).innerText)
                    output.show(tds3(2).innerText)
                Next
                'web3 = Nothing
                web3.Dispose

return ""
            Next
            'web2 = Nothing
            web2.Dispose

return ""
        Next
        'web1 = Nothing
        web1.Dispose

return ""
    Next
    web.Dispose

return ""
Next

 

回复收藏

画个圈圈，备用。

能用得着，好。

请教楼主：获取的数据直接导入到表吗？内部表分别有哪些列表名是什么？上列代码是属于单击按钮事件吗？

 

不是，获取到的数据，只显示在命令窗口里。

 

你要看懂代码，然后把output.show改成增加行和赋值的代码即可。

这个代码我测试了，很好用，只是有一点我不会解决，就是当市辖区没有下级连接的时候，会报错，比如山东省--济南市---市辖区，市辖区是最后一级，就会报错。还望指教！
此主题相关图片如下：bcjt111.png

http://www.foxtable.com/bbs/dispbbs.asp?BoardID=2&ID=87832&skin=0

 

Dim url As String = "http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2013/"
For i As Integer = 13 To 14
    Dim web As new System.Windows.Forms.WebBrowser
    web.Navigate(url & i & ".html")
    Do While web.ReadyState <> 4
        Application.DoEvents
    Loop
    Dim trs = web.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
    For j As Integer = 1 To trs.count - 1
        Dim tr = trs(j)
        Dim tds = tr.GetElementsByTagName("td")
        output.show(tds(0).innerText) '二级ID
        output.show(tds(1).innerText) '二级
        ' output.show(tds(1).GetElementsByTagName("a")(0).GetAttribute("href"))
        Dim web1 As new System.Windows.Forms.WebBrowser
        web1.Navigate(tds(1).GetElementsByTagName("a")(0).GetAttribute("href"))
        Do While web1.ReadyState <> 4
            Application.DoEvents
        Loop
        Dim trs1 = web1.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
        For j1 As Integer = 1 To trs1.count - 1
            Dim tr1 = trs1(j1)
            Dim tds1 = tr1.GetElementsByTagName("td")
            output.show(tds1(0).innerText) '三级ID
            output.show(tds1(1).innerText) '三级
            ' output.show(tds1(1).GetElementsByTagName("a")(0).GetAttribute("href"))
            If tds1(1).GetElementsByTagName("a").Count > 0 Then
                Dim web2 As new System.Windows.Forms.WebBrowser
                web2.Navigate(tds1(1).GetElementsByTagName("a")(0).GetAttribute("href"))
                Do While web2.ReadyState <> 4
                    Application.DoEvents
                Loop
                Dim trs2 = web2.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
                For j2 As Integer = 1 To trs2.count - 1
                    Dim tr2 = trs2(j2)
                    Dim tds2 = tr2.GetElementsByTagName("td")
                    output.show(tds2(0).innerText) '四级ID
                    output.show(tds2(1).innerText) '四级
                    '  output.show(tds2(1).GetElementsByTagName("a")(0).GetAttribute("href"))
                    If tds2(1).GetElementsByTagName("a").Count > 0 Then
                        Dim web3 As new System.Windows.Forms.WebBrowser
                        web3.Navigate(tds2(1).GetElementsByTagName("a")(0).GetAttribute("href"))
                        Do While web3.ReadyState <> 4
                            Application.DoEvents
                        Loop
                        Dim trs3 = web3.Document.GetElementsByTagName("table")(4).GetElementsByTagName("tr")
                        For j3 As Integer = 1 To trs3.count - 1
                            Dim tr3 = trs3(j3)
                            Dim tds3 = tr3.GetElementsByTagName("td")
                            Dim r As Row = Tables("全国行政区").AddNew
                            r("省级ID") = i
                            r("二级ID") = tds(0).innerText
                            r("三级ID") = tds1(0).innerText
                            r("四级ID") = tds2(0).innerText
                            r("五级ID") = tds3(0).innerText
                            r("二级") = tds(1).innerText
                            r("三级") = tds1(1).innerText
                            r("四级") = tds2(1).innerText
                            r("五级") = tds3(2).innerText
                            output.show(tds3(0).innerText) '五级ID
                            '   output.show(tds3(1).innerText) '五级
                            output.show(tds3(2).innerText)
                        Next
                        'web3 = Nothing
                        web3.Dispose
                       
             '           Return ""
                    Else
                        Dim r As Row = Tables("全国行政区").AddNew
                        r("省级ID") = i
                        r("二级ID") = tds(0).innerText
                        r("三级ID") = tds1(0).innerText
                        r("四级ID") = tds2(0).innerText
                        r("二级") = tds(1).innerText
                        r("三级") = tds1(1).innerText
                        r("四级") = tds2(1).innerText
                    End If
                Next
                'web2 = Nothing
                web2.Dispose
               
           '     Return ""
            Else
                Dim r As Row = Tables("全国行政区").AddNew
                r("省级ID") = i
                r("二级ID") = tds(0).innerText
                r("三级ID") = tds1(0).innerText
                r("二级") = tds(1).innerText
                r("三级") = tds1(1).innerText
            End If
        Next
        'web1 = Nothing
        web1.Dispose
       
    '    Return ""
    Next
    web.Dispose
   
 '   Return ""
Next

 

 

 

 

此主题相关图片如下：微信截图_20180115181346.png


此主题相关图片如下：qq截图20180115173841.png

 

正常的五级分类为什么会报错，哪位老师帮忙看下。。。