我创建了一个vba脚本来解析title
个不同帖子以及来自网站的editing status
个帖子。我现在想做的是让我的脚本从其着陆页解析title
,但在打印title
的同时打印editing status
。我不希望为该任务创建两个子。我什至不知道在vba中是否有可能。但是,如果不清楚,请查看我脚本中的注释。
Sub ImportTitleFromAnotherLocation()
Const LINK$ = "https://stackoverflow.com/questions/tagged/web-scraping"
Const prefix$ = "https://stackoverflow.com"
Dim Http As New XMLHTTP60, Html As New HTMLDocument
Dim editInfo As Object, I&, targetUrl$, postTile$
With Http
.Open "GET", LINK, False
.send
Html.body.innerHTML = .responseText
End With
With Html.querySelectorAll(".summary .question-hyperlink")
For I = 0 To .Length - 1
postTitle = .item(I).innerText 'I like this line to be transferred to the location below
targetUrl = Replace(.item(I).getAttribute("href"), "about:", prefix)
With Http
.Open "GET", targetUrl, False
.send
Html.body.innerHTML = .responseText
End With
R = R + 1: Cells(R, 1) = postTitle 'here I wish to use the above line like this
Set editInfo = Html.querySelector(".user-action-time > a")
If Not editInfo Is Nothing Then
Cells(R, 2) = editInfo.innerText
End If
Next I
End With
End Sub
答案 0 :(得分:1)
您正在循环中覆盖html文档。一种简单的方法是使用第二个htmldocument变量。一种更详细的方法是在循环之前存储标题,例如在附加循环中将其存储在数组中,然后使用i变量将其索引到其中以在现有循环中检索每个标题。
Sub ImportTitleFromAnotherLocation()
Const LINK$ = "https://stackoverflow.com/questions/tagged/web-scraping"
Const prefix$ = "https://stackoverflow.com"
Dim Http As New XMLHTTP60, Html As New HTMLDocument, Html2 As New HTMLDocument
Dim editInfo As Object, I&, targetUrl$, postTile$
Dim postTitle As String, r As Long
With Http
.Open "GET", LINK, False
.send
Html.body.innerHTML = .responseText
End With
With Html.querySelectorAll(".summary .question-hyperlink")
For I = 0 To .Length - 1
postTitle = .item(I).innerText 'I like this line to be transferred to the location below
targetUrl = Replace$(.item(I).getAttribute("href"), "about:", prefix)
With Http
.Open "GET", targetUrl, False
.send
Html2.body.innerHTML = .responseText
End With
r = r + 1: ActiveSheet.Cells(r, 1) = postTitle 'here I wish to use the above line like this
Set editInfo = Html2.querySelector(".user-action-time > a")
If Not editInfo Is Nothing Then
ActiveSheet.Cells(r, 2) = editInfo.innerText
End If
Next I
End With
End Sub