POST 请求:
①输入Well API号
我检查了做出您提到的选择的网页。我使用fiddler 检查了网络流量,并注意到初始请求在您提交 API 编号时由POST request 处理。
② POST 请求:
POST 正文有以下参数:
p_apinum 是键,关联的值是原始 Well API 编号。
使用此信息,我直接制定了 POST 请求,从而避免了您的第一个目标网页。
③点击超链接:
接下来,我注意到你要按下的元素:
查看关联的 HTML,它有一个关联的相对超链接:
我使用辅助函数来解析页面 HTML 以获取此相对链接并构造绝对路径:GetNextURL(page.body.innerHTML)。
④ 提出新请求:
我重新使用我的 HTTPRequest 函数 GetPage 发送第二个请求,主体为空,并从通过 page.getElementsByTagName("table") 返回的 HTML 文档中获取所有表格。
⑤ 将表格写入 Excel 工作表:
我使用辅助函数 AddHeaders 循环页面上的所有表格以写出表格标题,并使用 WriteTables 将当前表格写入工作表。
示例页面内容:
示例代码输出:
VBA:
Option Explicit
Public Sub GetWellInfo()
Dim ws As Worksheet, page As HTMLDocument, targetTable As HTMLTable, apiNumbers(), currNumber As Long
Const PARAM1 As String = "p_apinum"
Const BASESTRING As String = "http://sonlite.dnr.state.la.us/sundown/cart_prod/"
apiNumbers = Array(1708300502, 1708300503)
Application.ScreenUpdating = False
Set ws = ThisWorkbook.Worksheets("Sheet1")
With ws
.Cells.ClearContents
For currNumber = LBound(apiNumbers) To UBound(apiNumbers)
Set page = GetPage(BASESTRING & "cart_con_wellapi2", apiNumbers(currNumber), PARAM1)
Set page = GetPage(BASESTRING & GetNextURL(page.body.innerHTML))
Dim allTables As Object
Set allTables = page.getElementsByTagName("table")
For Each targetTable In allTables
AddHeaders targetTable, GetLastRow(ws, 1) + 2, ws
WriteTables targetTable, GetLastRow(ws, 1), ws
Next targetTable
Next currNumber
End With
Application.ScreenUpdating = True
End Sub
Public Function GetPage(ByVal url As String, Optional ByVal apiNumber As Long, Optional ByVal paramN As String = vbNullString) As HTMLDocument
Dim objHTTP As Object, html As New HTMLDocument
Set objHTTP = CreateObject("WinHttp.WinHttpRequest.5.1")
Dim sBody As String
If Not paramN = vbNullString Then sBody = paramN & "=" & apiNumber
With objHTTP
.SetTimeouts 10000, 10000, 10000, 10000
.Open "POST", url, False
.setRequestHeader "User-Agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)"
.setRequestHeader "Content-type", "application/x-www-form-urlencoded"
On Error Resume Next
.send (sBody)
If Err.Number = 0 Then
If .Status = "200" Then
html.body.innerHTML = .responseText
Set GetPage = html
Else
Debug.Print "HTTP " & .Status & " " & .statusText
Exit Function
End If
Else
Debug.Print "Error " & Err.Number & " " & Err.Source & " " & Err.Description
Exit Function
End If
On Error GoTo 0
End With
End Function
Public Function GetNextURL(ByVal inputString As String)
GetNextURL = Replace$(Replace$(Split(Split(inputString, "href=")(1), ">")(0), Chr$(34), vbNullString), "about:", vbNullString)
End Function
Public Sub AddHeaders(ByVal hTable As Object, ByVal startRow As Long, ByVal ws As Worksheet)
Dim headers As Object, header As Object, columnCounter As Long
Set headers = hTable.getElementsByTagName("th")
For Each header In headers
columnCounter = columnCounter + 1
ws.Cells(startRow, columnCounter) = header.innerText
Next header
End Sub
Public Sub WriteTables(ByVal hTable As HTMLTable, Optional ByVal startRow As Long = 1, Optional ByRef ws As Worksheet)
If ws Is Nothing Then Set ws = ActiveSheet
Dim tRow As Object, tCell As Object, tr As Object, td As Object, r As Long, c As Long
r = startRow
With ActiveSheet
Set tRow = hTable.getElementsByTagName("tr")
For Each tr In tRow
Set tCell = tr.getElementsByTagName("td")
For Each td In tCell
.Cells(r, c).Value = td.innerText
c = c + 1
Next td
r = r + 1: c = 1
Next tr
End With
End Sub
Public Function GetLastRow(ByVal ws As Worksheet, Optional ByVal columnNumber As Long = 1) As Long
With ws
GetLastRow = .Cells(.Rows.Count, columnNumber).End(xlUp).Row
End With
End Function
参考资料:
VBE > 工具 > 参考 > HTML 对象库。