pdf documentation of qb64 - Printable Version

Code: (Select All)
Const SleepSet = 0 'to sleep between each keyword so we can see them and read them

Const SaveTo = "wiki.txt" '"SCRN:" to display to the screen, or insert a filename to save the list to disk



Screen _NewImage(1024, 720, 256)

Print "DOWNLOAD STARTING"

file$ = "QB64WikiList.txt"

'Increase the 2-second time limit here if you need to.

DownloadRSS "http://qb64.org/wiki/Keyword_Reference_-_Alphabetical", file$, 2

Print "DOWNLOAD FINISHED"

Print





Open file$ For Binary As #1

temp$ = Space$(LOF(1))

Get #1, , temp$

Close #1

l = 0

finish$ = "<div id=" + Chr$(34) + "symbols" + Chr$(34) + "></div>"

finish = InStr(temp$, finish$) 'No need to parse anything after we get down to the symbol section of the wiki page



Open SaveTo For Output As #1





Do

    l = InStr(l, temp$, "<li>")

    If l >= finish Then Exit Do

    If l Then

        l2 = InStr(l + 5, temp$, "</li>"): If l2 = 0 Then l2 = Len(temp$)

        work$ = Mid$(temp$, l + 4, l2 - l - 5)

        li1 = InStr(work$, Chr$(34)): li2 = InStr(li1 + 1, work$, Chr$(34))

        link$ = Mid$(work$, li1 + 1, li2 - li1 - 1)

        If InStr(link$, "&amp") Then link$ = "Page does not exist yet."

        link$ = StripCRLF(link$)

        k1 = InStr(li2 + 1, work$, ">"): k2 = InStr(k1 + 1, work$, "<")

        keyword$ = Mid$(work$, k1 + 1, k2 - k1 - 1)

        keyword$ = StripCRLF(keyword$)

        d = InStr(k2 + 1, work$, "<span"): d1 = InStr(d + 1, work$, ">"): d2 = InStr(d1 + 1, work$, "</span")

        desc$ = Mid$(work$, d1 + 1, d2 - d1 - 1)

        desc$ = StripCRLF(desc$)

        Print #1, keyword$

        Print #1, "         http://qb64.org"; link$

        Print #1, "         "; desc$

        If SleepSet Then Sleep

        l = l2 + 1

    End If

Loop Until l = 0

Close



Sleep

System





Sub DownloadRSS (url$, file$, timelimit)

    link$ = url$

    Dim l As _Integer64, lod As _Integer64



    url2$ = RTrim$(LTrim$(link$))

    url4$ = RTrim$(LTrim$(link$))

    If Left$(UCase$(url2$), 7) = "HTTP://" Then url4$ = Mid$(url2$, 8)

    x = InStr(url4$, "/")

    If x Then url2$ = Left$(url4$, x - 1)

    NewsClient = _OpenClient("TCP/IP:80:" + url2$)

    If NewsClient = 0 Then Exit Sub

    e$ = Chr$(13) + Chr$(10) ' end of line characters

    url3$ = Right$(url4$, Len(url4$) - x + 1)

    x$ = "GET " + url3$ + " HTTP/1.1" + e$

    x$ = x$ + "Host: " + url2$ + e$ + e$

    Put #NewsClient, , x$



    Open file$ For Output As #1: Close #1

    Open file$ For Binary As #1



    t! = Timer ' start time

    head$ = ""

    cont_type$ = ""

    Do

        _Limit 20

        Get #NewsClient, , a$

        If LTrim$(a$) > "" Then Put #1, , a$

    Loop Until Timer > t! + timelimit And timelimit > 0 ' (in seconds)

    Close #NewsClient

    Close #1

End Sub



Function StripCRLF$ (text$)

    'The wiki seems to contain stray CRLF characters at the dangest spots.

    'Why it has them, I don't know, but we need to filter them out so our information will load and display properly.

    li1 = 0

    Do

        li1 = InStr(li1 + 1, text$, Chr$(13) + Chr$(10))

        If li1 Then

            l$ = Left$(text$, li1 - 1)

            r$ = Mid$(text$, li1 + 2)

            text$ = l$ + r$

        End If

    Loop Until li1 = 0



    'Also some of the descriptions and such contain links to different keywords.

    'We want to just strip those links and use a normal word replacement for ease of display, since we're not going to be displaying in

    'an html editor/viewer.



    li1 = 0

    Do

        li1 = InStr(li1 + 1, text$, "<a href")

        If li1 Then

            li2 = InStr(li1 + 1, text$, "</a>")

            li3 = InStr(li1 + 1, text$, ">")

            l$ = Left$(text$, li1 - 1)

            m$ = Mid$(text$, li3 + 1, li2 - li3 - 1)

            r$ = Mid$(text$, li2 + 4)

            text$ = l$ + m$ + r$

        End If

    Loop Until li1 = 0



    StripCRLF$ = text$

End Function