Internet Explorer:
我已经把它比平时更详细一点,这样你就可以看到每个步骤。
关键点:
1) 正确的页面加载等待While .Busy Or .readyState < 4: DoEvents: Wend
2) 尽可能按 id 选择元素。 # 是一个 CSS id selector。 css selectors 由.document 的querySelector 方法应用,并检索页面中与指定模式匹配的第一个元素
3) 需要一个定时循环来等待结果出现
4) 订单数量等信息是换行符分割的字符串。在这些换行符上拆分似乎最容易,然后通过索引从结果数组中访问单个项目
5) 我按照您的规范订购了一个数组中的结果,然后将该数组一次性写入工作表
6) “.”是.order-history__item-descript--min 中的class selector,即返回class 的order-history__item-descript--min 的第一个元素
7) [x=y] 是[data-label=Shipping] 中的attribute = value selector,即返回具有data-label 属性值Shipping 的第一个元素
8) .details-table a 的组合使用descendant combinator, " ", 来指定我想要a 标签元素的父类为.details-table
VBA:
Option Explicit
'VBE > Tools > References:
' Microsoft Internet Controls
Public Sub RetrieveInfo()
Dim ie As InternetExplorer, ele As Object, t As Date
Const MAX_WAIT_SEC As Long = 5
Set ie = New InternetExplorer
With ie
.Visible = True
.Navigate2 "https://www.partstown.com/track-my-order"
While .Busy Or .readyState < 4: DoEvents: Wend
With .document
.querySelector("#orderNo").Value = "4500969111"
.querySelector("#postalCode").Value = "37040"
.querySelector("#orderLookUpForm").submit
End With
While .Busy Or .readyState < 4: DoEvents: Wend
Dim shipping As String, order As String, items() As String
With .document
t = Timer
Do
On Error Resume Next
Set ele = .querySelector("[data-label=Shipping]")
On Error GoTo 0
If Timer - t > MAX_WAIT_SEC Then Exit Do
Loop While ele Is Nothing
If ele Is Nothing Then Exit Sub
shipping = ele.innerText
order = .querySelector(".order-history__item-descript--min").innerText
items = Split(order, vbNewLine)
Dim qtyOrdered As Long, qtyShipped As String, product As String
qtyOrdered = CLng(Replace$(items(0), "Qty Ordered: ", vbNullString))
qtyShipped = CLng(Replace$(items(1), "Qty Shipped: ", vbNullString))
product = .querySelector(".details-table a").Title
Dim results()
results = Array(shipping, qtyOrdered, qtyShipped, product)
ThisWorkbook.Worksheets("Sheet1").Cells(1, 1).Resize(1, UBound(results) + 1) = results
End With
.Quit
End With
End Sub
如果是 HTML 新手,请查看:
https://developer.mozilla.org/en-US/docs/Web/HTML
如果对 css 选择器不熟悉,请查看:
https://flukeout.github.io/
XMLHTTP:
整个事情也可以用XHR 来完成。这比打开浏览器要快得多。
XHR:
使用 XMLHttpRequest (XHR) 对象与服务器交互。你可以
从 URL 中检索数据而无需执行整个页面 [render]
在这种情况下,我向登录页面发出初始 GET 请求以检索
CSRFToken 用于我重新制定POST 当您手动输入数据并按提交时页面向服务器发出的请求。您在服务器响应中获得所需的数据。我在 POST 发送行的正文中传递了一个查询字符串
.send "orderNo=4500969111&postalCode=37040&CSRFToken=" & csrft ;你可以在那里看到你的参数。
Option Explicit
Public Sub GetInfo()
Dim html As HTMLDocument, csrft As String '< VBE > Tools > References > Microsoft HTML Object Library
Set html = New HTMLDocument
With CreateObject("MSXML2.XMLHTTP")
.Open "GET", "https://www.partstown.com", False
.send
html.body.innerHTML = .responseText
csrft = html.querySelector("[name=CSRFToken]").Value
.Open "POST", "https://www.partstown.com/track-my-order", False
.setRequestHeader "Referer", "https://www.partstown.com/track-my-order"
.setRequestHeader "User-Agent", "Mozilla/5.0"
.setRequestHeader "Content-Type", "application/x-www-form-urlencoded"
.setRequestHeader "Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
.setRequestHeader "Accept-Encoding", "gzip, deflate"
.setRequestHeader "Accept-Language", "en-US,en;q=0.9"
.send "orderNo=4500969111&postalCode=37040&CSRFToken=" & csrft
html.body.innerHTML = .responseText
End With
Dim shipping As String, order As String, items() As String
shipping = html.querySelector("[data-label=Shipping]").innerText
order = html.querySelector(".order-history__item-descript--min").innerText
items = Split(order, vbNewLine)
Dim qtyOrdered As Long, qtyShipped As String, product As String
qtyOrdered = CLng(Replace$(items(0), "Qty Ordered: ", vbNullString))
qtyShipped = CLng(Replace$(items(1), "Qty Shipped: ", vbNullString))
product = html.querySelector(".details-table a").Title
Dim results()
results = Array(shipping, qtyOrdered, qtyShipped, product)
ThisWorkbook.Worksheets("Sheet1").Cells(1, 1).Resize(1, UBound(results) + 1) = results
End Sub
循环示例:
Option Explicit
Public Sub GetInfo()
Dim html As HTMLDocument, csrft As String, lastRow As Long, sourceValues() '< VBE > Tools > References > Microsoft HTML Object Library
Set html = New HTMLDocument
Dim ws As Worksheet, i As Long
Set ws = ThisWorkbook.Worksheets("Sheet4")
lastRow = ws.Cells(ws.rows.Count, "B").End(xlUp).Row
sourceValues = ws.Range("B2:D" & lastRow).Value
Dim results()
ReDim results(1 To UBound(sourceValues, 1), 1 To 4)
With CreateObject("MSXML2.XMLHTTP")
.Open "GET", "https://www.partstown.com", False
.send
html.body.innerHTML = .responseText
csrft = html.querySelector("[name=CSRFToken]").Value
Stop
For i = LBound(sourceValues, 1) To UBound(sourceValues, 1)
If sourceValues(i, 1) <> vbNullString And sourceValues(i, 3) <> vbNullString Then
DoEvents
.Open "POST", "https://www.partstown.com/track-my-order", False
.setRequestHeader "Referer", "https://www.partstown.com/track-my-order"
.setRequestHeader "User-Agent", "Mozilla/5.0"
.setRequestHeader "Content-Type", "application/x-www-form-urlencoded"
.setRequestHeader "Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8"
.setRequestHeader "Accept-Encoding", "gzip, deflate"
.setRequestHeader "Accept-Language", "en-US,en;q=0.9"
.send "orderNo=" & sourceValues(i, 1) & "&postalCode=" & sourceValues(i, 3) & "&CSRFToken=" & csrft
html.body.innerHTML = .responseText
Dim shipping As String, order As String, items() As String
shipping = html.querySelector("[data-label=Shipping]").innerText
order = html.querySelector(".order-history__item-descript--min").innerText
items = Split(order, vbNewLine)
Dim qtyOrdered As Long, qtyShipped As String, product As String
qtyOrdered = CLng(Replace$(items(0), "Qty Ordered: ", vbNullString))
qtyShipped = CLng(Replace$(items(1), "Qty Shipped: ", vbNullString))
product = html.querySelector(".details-table a").Title
results(i, 1) = shipping
results(i, 2) = qtyOrdered
results(i, 3) = qtyShipped
results(i, 4) = product
End If
'Application.Wait Now + TimeSerial(0, 0, 1)
Next
End With
'results written out from row 2 column E
ws.Cells(2, 5).Resize(UBound(results, 1), UBound(results, 2)) = results
End Sub