get text between text

**vb6hacker** · May 24th, 2009, 06:10 AM

my app gets the source from a webpage, the source includes the following info:

Code:

<area id="a_0_1" shape="poly" coords="89, 117, 126, 137, 89, 157, 52, 137" title="" href="karte.php?d=279938&c=7d" />
<area id="a_0_2" shape="poly" coords="125, 97, 162, 117, 125, 137, 88, 117" title="I. Apollo" href="karte.php?d=279137&c=ca" />
<area id="a_0_3" shape="poly" coords="161, 77, 198, 97, 161, 117, 124, 97" title="" href="karte.php?d=278336&c=73" />
<area id="a_0_4" shape="poly" coords="197, 57, 234, 77, 197, 97, 160, 77" title="1)Cegóvia" href="karte.php?d=277535&c=81" />
<area id="a_0_5" shape="poly" coords="233, 37, 270, 57, 233, 77, 196, 57" title="" href="karte.php?d=276734&c=7a" />
<area id="a_0_6" shape="poly" coords="269, 17, 306, 37, 269, 57, 232, 37" title="Lietuvaitis.LtD" href="karte.php?d=275933&c=50" />
<area id="a_1_0" shape="poly" coords="90, 157, 127, 177, 90, 197, 53, 177" title="[1]" href="karte.php?d=280740&c=63" />
<area id="a_1_1" shape="poly" coords="126, 137, 163, 157, 126, 177, 89, 157" title="Ellesmèra" href="karte.php?d=279939&c=51" />
<area id="a_1_2" shape="poly" coords="162, 117, 199, 137, 162, 157, 125, 137" title="" href="karte.php?d=279138&c=f1" />
<area id="a_1_3" shape="poly" coords="198, 97, 235, 117, 198, 137, 161, 117" title="" href="karte.php?d=278337&c=9c" />
<area id="a_1_4" shape="poly" coords="234, 77, 271, 97, 234, 117, 197, 97" title="Zwijnaarde" href="karte.php?d=277536&c=80" />
<area id="a_1_5" shape="poly" coords="270, 57, 307, 77, 270, 97, 233, 77" title="" href="karte.php?d=276735&c=f0" />
<area id="a_1_6" shape="poly" coords="306, 37, 343, 57, 306, 77, 269, 57" title="" href="karte.php?d=275934&c=a6" />
<area id="a_2_0" shape="poly" coords="127, 177, 164, 197, 127, 217, 90, 197" title="" href="karte.php?d=280741&c=37" />
<area id="a_2_1" shape="poly" coords="163, 157, 200, 177, 163, 197, 126, 177" title="shadow alliance" href="karte.php?d=279940&c=01" />
<area id="a_2_2" shape="poly" coords="199, 137, 236, 157, 199, 177, 162, 157" title="" href="karte.php?d=279139&c=c7" />
<area id="a_2_3" shape="poly" coords="235, 117, 272, 137, 235, 157, 198, 137" title="" href="karte.php?d=278338&c=a2" />

<area id="a_2_4" shape="poly" coords="271, 97, 308, 117, 271, 137, 234, 117" title="" href="karte.php?d=277537&c=93" />
<area id="a_2_5" shape="poly" coords="307, 77, 344, 97, 307, 117, 270, 97" title="" href="karte.php?d=276736&c=f3" />
<area id="a_2_6" shape="poly" coords="343, 57, 380, 77, 343, 97, 306, 77" title="" href="karte.php?d=275935&c=2f" />
<area id="a_3_0" shape="poly" coords="164, 197, 201, 217, 164, 237, 127, 217" title="robskies dorp 1" href="karte.php?d=280742&c=78" />
<area id="a_3_1" shape="poly" coords="200, 177, 237, 197, 200, 217, 163, 197" title="" href="karte.php?d=279941&c=35" />
<area id="a_3_2" shape="poly" coords="236, 157, 273, 177, 236, 197, 199, 177" title="" href="karte.php?d=279140&c=49" />
<area id="a_3_3" shape="poly" coords="272, 137, 309, 157, 272, 177, 235, 157" title="[01] HQ" href="karte.php?d=278339&c=8c" />
<area id="a_3_4" shape="poly" coords="308, 117, 345, 137, 308, 157, 271, 137" title="" href="karte.php?d=277538&c=bb" />
<area id="a_3_5" shape="poly" coords="344, 97, 381, 117, 344, 137, 307, 117" title="Verlaten Vallei" href="karte.php?d=276737&c=55" />
<area id="a_3_6" shape="poly" coords="380, 77, 417, 97, 380, 117, 343, 97" title="" href="karte.php?d=275936&c=65" />
<area id="a_4_0" shape="poly" coords="201, 217, 238, 237, 201, 257, 164, 237" title="Ozymandias I" href="karte.php?d=280743&c=95" />
<area id="a_4_1" shape="poly" coords="237, 197, 274, 217, 237, 237, 200, 217" title="" href="karte.php?d=279942&c=e3" />
<area id="a_4_2" shape="poly" coords="273, 177, 310, 197, 273, 217, 236, 197" title="" href="karte.php?d=279141&c=08" />
<area id="a_4_3" shape="poly" coords="309, 157, 346, 177, 309, 197, 272, 177" title="" href="karte.php?d=278340&c=fc" />
<area id="a_4_4" shape="poly" coords="345, 137, 382, 157, 345, 177, 308, 157" title="" href="karte.php?d=277539&c=3f" />
<area id="a_4_5" shape="poly" coords="381, 117, 418, 137, 381, 157, 344, 137" title="" href="karte.php?d=276738&c=83" />
<area id="a_4_6" shape="poly" coords="417, 97, 454, 117, 417, 137, 380, 117" title="" href="karte.php?d=275937&c=d9" />

<area id="a_5_0" shape="poly" coords="238, 237, 275, 257, 238, 277, 201, 257" title="" href="karte.php?d=280744&c=75" />
<area id="a_5_1" shape="poly" coords="274, 217, 311, 237, 274, 257, 237, 237" title="HayaleT" href="karte.php?d=279943&c=30" />
<area id="a_5_2" shape="poly" coords="310, 197, 347, 217, 310, 237, 273, 217" title="Latium" href="karte.php?d=279142&c=f2" />
<area id="a_5_3" shape="poly" coords="346, 177, 383, 197, 346, 217, 309, 197" title="" href="karte.php?d=278341&c=18" />
<area id="a_5_4" shape="poly" coords="382, 157, 419, 177, 382, 197, 345, 177" title="" href="karte.php?d=277540&c=b8" />
<area id="a_5_5" shape="poly" coords="418, 137, 455, 157, 418, 177, 381, 157" title="spirithoes´s Dorp" href="karte.php?d=276739&c=30" />
<area id="a_5_6" shape="poly" coords="454, 117, 491, 137, 454, 157, 417, 137" title="" href="karte.php?d=275938&c=4f" />
<area id="a_6_0" shape="poly" coords="275, 257, 312, 277, 275, 297, 238, 277" title="" href="karte.php?d=280745&c=f3" />
<area id="a_6_1" shape="poly" coords="311, 237, 348, 257, 311, 277, 274, 257" title="spookieee" href="karte.php?d=279944&c=7a" />
<area id="a_6_2" shape="poly" coords="347, 217, 384, 237, 347, 257, 310, 237" title="" href="karte.php?d=279143&c=ce" />
<area id="a_6_3" shape="poly" coords="383, 197, 420, 217, 383, 237, 346, 217" title="" href="karte.php?d=278342&c=35" />
<area id="a_6_4" shape="poly" coords="419, 177, 456, 197, 419, 217, 382, 197" title="" href="karte.php?d=277541&c=0c" />
<area id="a_6_5" shape="poly" coords="455, 157, 492, 177, 455, 197, 418, 177" title="" href="karte.php?d=276740&c=ac" />

now i want my app to get the numbers between href="karte.php?d= and &c
and put it into text1.text.

how can i do this? i tried with a function called getbetween but this one only gives the first result.

thanks

**some1uk03** · May 24th, 2009, 06:34 AM

Use instr() to get the position of where href begins.. then the rest is simple and straightforward..

Use mid(), right() functions to extract the data...

**edhanz** · May 24th, 2009, 06:38 AM

maybe you can manipulate those string first. you make the string to be href="karte.php?d= 279944 &c=7a" (add spaces) so you can get the string between "href="karte.php?d= " and " &c=7a" using GetBetween function..

**Merri** · May 24th, 2009, 06:41 AM

Code:

Option Explicit

Public Function Between(Text As String, Before As String, After As String, Output() As String) As Long
    Dim lngA As Long, lngB As Long, lngC As Long
    Erase Output
    If (LenB(Before) > 0) And (LenB(After) > 0) And (LenB(Text) > 0) Then
        ' reserve maximum possible items
        ReDim Output(LenB(Text) \ (LenB(Before) + LenB(After)))
        ' find first
        lngA = InStrB(Text, Before)
        Do While lngA
            If lngA And 1 Then
                Do
                    ' find after
                    lngB = InStrB(lngA + LenB(Before), Text, After)
                    If lngB And 1 Then
                        ' found both, store what we got
                        Output(lngC) = MidB$(Text, lngA + LenB(Before), lngB - lngA - LenB(Before))
                        lngC = lngC + 1
                        ' find next
                        lngA = InStrB(lngB + LenB(After), Text, Before)
                        ' exit inner loop
                        Exit Do
                    ElseIf lngB > 0 Then
                        ' invalid position, not beginning of a character, try next
                        lngB = InStrB(lngB + 1, Text, After)
                    Else
                        ' exit both loops
                        lngA = 0
                        Exit Do
                    End If
                Loop While lngB
            ElseIf lngA > 0 Then
                ' invalid position, not beginning of a character, try next
                lngA = InStrB(lngA + 1, Text, Before)
            End If
        Loop
        ' we are done, just need to clean up memory
        If (lngC > 0) Then
            ' remove extra items
            ReDim Preserve Output(lngC - 1)
            ' return number of items found
            Between = lngC
        Else
            ' return empty array (LBound = 0, UBound = -1)
            Output = Split(vbNullString)
        End If
    End If
End Function

Private Sub Form_Load()
    Dim strText As String, strData() As String
    Dim lngA As Long
    ' open data from file
    Open "C:\data.txt" For Input As #1
        strText = Input(LOF(1), #1)
    Close #1
    ' if we get more than none...
    For lngA = 0 To Between(strText, "href=""karte.php?d=", "&c", strData) - 1
        ' print everything we got
        Debug.Print strData(lngA)
    Next lngA
End Sub

Yes, this was easy enough for me to do, otherwise wouldn't have bothered

Edit!
Updated Strings.bas in my public Modules folder.

**anhn** · May 24th, 2009, 08:13 AM

Perhaps use Instr() or InstrB() can save a few miliseconds, but this is a shortest and simple way (7 lines of main code):

Code:

Sub GetArrayBetween()
   Const Tag1 = "href=""karte.php?d="
   Const Tag2 = "&c"
   Dim sItem() As String, i As Long
   
1  Open "C:\VBF\data.txt" For Input As #1
2  sItem = Split(Input(LOF(1), 1), Tag1)
3  Close #1
   '-- extract each number and use
4  For i = 1 To UBound(sItem) '-- (i - 1) is used to remove the first item (0)
5     sItem(i - 1) = Split(sItem(i), Tag2, 2)(0)
6  Next
7  ReDim Preserve sItem(UBound(sItem) - 1) '-- one item short
   
   For i = 0 To UBound(sItem)
      Debug.Print sItem(i)
   Next
End Sub

**vb6hacker** · May 24th, 2009, 08:24 AM

Originally Posted by Merri

Code:

Option Explicit

Public Function Between(Text As String, Before As String, After As String, Output() As String) As Long
    Dim lngA As Long, lngB As Long, lngC As Long
    Erase Output
    If (LenB(Before) > 0) And (LenB(After) > 0) And (LenB(Text) > 0) Then
        ' reserve maximum possible items
        ReDim Output(LenB(Text) \ (LenB(Before) + LenB(After)))
        ' find first
        lngA = InStrB(Text, Before)
        Do While lngA
            If lngA And 1 Then
                Do
                    ' find after
                    lngB = InStrB(lngA + LenB(Before), Text, After)
                    If lngB And 1 Then
                        ' found both, store what we got
                        Output(lngC) = MidB$(Text, lngA + LenB(Before), lngB - lngA - LenB(Before))
                        lngC = lngC + 1
                        ' find next
                        lngA = InStrB(lngB + LenB(After), Text, Before)
                        ' exit inner loop
                        Exit Do
                    ElseIf lngB > 0 Then
                        ' invalid position, not beginning of a character, try next
                        lngB = InStrB(lngB + 1, Text, After)
                    Else
                        ' exit both loops
                        lngA = 0
                        Exit Do
                    End If
                Loop While lngB
            ElseIf lngA > 0 Then
                ' invalid position, not beginning of a character, try next
                lngA = InStrB(lngA + 1, Text, Before)
            End If
        Loop
        ' we are done, just need to clean up memory
        If (lngC > 0) Then
            ' remove extra items
            ReDim Preserve Output(lngC - 1)
            ' return number of items found
            Between = lngC
        Else
            ' return empty array (LBound = 0, UBound = -1)
            Output = Split(vbNullString)
        End If
    End If
End Function

Private Sub Form_Load()
    Dim strText As String, strData() As String
    Dim lngA As Long
    ' open data from file
    Open "C:\data.txt" For Input As #1
        strText = Input(LOF(1), #1)
    Close #1
    ' if we get more than none...
    For lngA = 0 To Between(strText, "href=""karte.php?d=", "&c", strData) - 1
        ' print everything we got
        Debug.Print strData(lngA)
    Next lngA
End Sub

Yes, this was easy enough for me to do, otherwise wouldn't have bothered

Edit!
Updated Strings.bas in my public Modules folder.

this worked great for me, thanks

**vb6hacker** · May 24th, 2009, 08:26 AM

Originally Posted by anhn

Perhaps use Instr() or InstrB() can save a few miliseconds, but this is a shortest and simple way (7 lines of main code):

Code:

Sub GetArrayBetween()
   Const Tag1 = "href=""karte.php?d="
   Const Tag2 = "&c"
   Dim sItem() As String, i As Long
   
1  Open "C:\VBF\data.txt" For Input As #1
2  sItem = Split(Input(LOF(1), 1), Tag1)
3  Close #1
   '-- extract each number and use
4  For i = 1 To UBound(sItem) '-- (i - 1) is used to remove the first item (0)
5     sItem(i - 1) = Split(sItem(i), Tag2, 2)(0)
6  Next
7  ReDim Preserve sItem(UBound(sItem) - 1) '-- one item short
   
   For i = 0 To UBound(sItem)
      Debug.Print sItem(i)
   Next
End Sub

thanks for the shorter version

i guess i will use this cause this one also is faster.

**vb6hacker** · May 24th, 2009, 08:30 AM

ive got a new small problem wich i hope you can help me with.
now it gives al the numbers, but it would be better (to make my app faster) if it only gives the numbers where "tilte" is not empty.
hopefully you can also help me with this

Thanks

ps youre great

**Merri** · May 24th, 2009, 08:54 AM

Just to point it out, anhn's code will give invalid results if there are more of the first tag than the last tag. It would need to check whether the UBound of the second tag Split is 1. If it is 0, no second tag was found and thus it should not be added into the array.

Edit!
Updating for the title parsing:

Code:

Private Sub Form_Load()
    Dim strText As String, strData() As String, strRow() As String
    Dim lngA As Long
    ' open data from file
    Open "C:\data.txt" For Input As #1
        strText = Input(LOF(1), #1)
    Close #1
    ' if we get more than none...
    For lngA = 0 To Between(strText, " title=""", "&c", strData) - 1
        strRow = Split(strData(lngA), """ href=""karte.php?d=", 2)
        If LenB(strRow(0)) Then Debug.Print strRow(1), strRow(0)
    Next lngA
End Sub

Edit #2!
anhn's suggestion functionalized and fixed the issue:

Code:

Public Function Between(Text As String, Before As String, After As String, Output() As String) As Long
    Dim lngA As Long, strBetween() As String
    Output = Split(Text, Before)
    For lngA = 1 To UBound(Output)
        strBetween = Split(Output(lngA), After, 2)
        If UBound(strBetween) = 1 Then
            Output(Between) = strBetween(0)
            Between = Between + 1
        End If
    Next lngA
    If Between > 0 Then
        ReDim Preserve Output(Between - 1)
    Else
        Output = Split(vbNullString)
    End If
End Function

**anhn** · May 24th, 2009, 09:10 AM

Originally Posted by Merri

Just to point it out, anhn's code will give invalid results if there are more of the first tag than the last tag. It would need to check whether the UBound of the second tag Split is 1. If it is 0, no second tag was found and thus it should not be added into the array.

Have you actually test that?
With the second Split(), you always pick the first item (0) so you never have problem even Tag2 is missing. If Tag2 is missing, the full item will be picked.

**Merri** · May 24th, 2009, 09:12 AM

I consider the tag2 missing an error, because the result isn't between two tags if the second tag is missing.

Edit!
Not to say that would be a problem in this case when both tags always exist, but I also think it needs to be pointed out just in case someone will use the same code in their own program after reading this thread

**vb6hacker** · May 24th, 2009, 10:11 AM

Originally Posted by Merri

Just to point it out, anhn's code will give invalid results if there are more of the first tag than the last tag. It would need to check whether the UBound of the second tag Split is 1. If it is 0, no second tag was found and thus it should not be added into the array.

Edit!
Updating for the title parsing:

Code:

Private Sub Form_Load()
    Dim strText As String, strData() As String, strRow() As String
    Dim lngA As Long
    ' open data from file
    Open "C:\data.txt" For Input As #1
        strText = Input(LOF(1), #1)
    Close #1
    ' if we get more than none...
    For lngA = 0 To Between(strText, " title=""", "&c", strData) - 1
        strRow = Split(strData(lngA), """ href=""karte.php?d=", 2)
        If LenB(strRow(0)) Then Debug.Print strRow(1), strRow(0)
    Next lngA
End Sub

Edit #2!
anhn's suggestion functionalized and fixed the issue:

Code:

Public Function Between(Text As String, Before As String, After As String, Output() As String) As Long
    Dim lngA As Long, strBetween() As String
    Output = Split(Text, Before)
    For lngA = 1 To UBound(Output)
        strBetween = Split(Output(lngA), After, 2)
        If UBound(strBetween) = 1 Then
            Output(Between) = strBetween(0)
            Between = Between + 1
        End If
    Next lngA
    If Between > 0 Then
        ReDim Preserve Output(Between - 1)
    Else
        Output = Split(vbNullString)
    End If
End Function

thanks for your code again

a new problem is that i cant get the results into text1.text
how can i do this?

thanks

Thread: get text between text

Thread Tools

Display

get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Re: get text between text

Posting Permissions