Data update

Task/Web-scraping/Ada/web-scraping.adb

@@ -0,0 +1,34 @@
+with AWS.Client, AWS.Response, AWS.Resources, AWS.Messages;
+with Ada.Text_IO, Ada.Strings.Fixed;
+use  Ada, AWS, AWS.Resources, AWS.Messages;
+
+procedure Get_UTC_Time is
+
+   Page           : Response.Data;
+   File           : Resources.File_Type;
+   Buffer         : String (1 .. 1024);
+   Position, Last : Natural := 0;
+   S              : Messages.Status_Code;
+begin
+   Page := Client.Get ("http://tycho.usno.navy.mil/cgi-bin/timer.pl");
+   S    := Response.Status_Code (Page);
+   if S not  in Success then
+      Text_IO.Put_Line
+        ("Unable to retrieve data => Status Code :" & Image (S) &
+         " Reason :" & Reason_Phrase (S));
+      return;
+   end if;
+
+   Response.Message_Body (Page, File);
+   while not End_Of_File (File) loop
+      Resources.Get_Line (File, Buffer, Last);
+      Position :=
+         Strings.Fixed.Index
+           (Source  => Buffer (Buffer'First .. Last),
+            Pattern => "UTC");
+      if Position > 0 then
+         Text_IO.Put_Line (Buffer (5 .. Position + 2));
+         return;
+      end if;
+   end loop;
+end Get_UTC_Time;

Task/Web-scraping/FreeBASIC/web-scraping.basic

@@ -0,0 +1,52 @@
+' Linux: fbc programa.bas
+' Windows: install wget (winget install GnuWin32.WGet) & fbc programa.bas
+
+Dim As String sContent, sUTC, sRFC850, tmpFile, cmd
+
+' Detect system and use temporary folder
+#Ifdef __FB_WIN32__
+    tmpFile = Environ("TEMP") & "\utctime.html"
+    cmd = "wget -q -O """ & tmpFile & """ https://www.utctime.net"
+#Else
+    tmpFile = "/tmp/utctime.html"
+    cmd = "wget -q -O " & tmpFile & " https://www.utctime.net"
+#EndIf
+
+Shell cmd
+
+Dim As Integer ff = Freefile
+If Open(tmpFile For Input As #ff) <> 0 Then
+    Print "Error: wget failed or file is not accessible."
+    Sleep: End
+End If
+
+' Read full content
+sContent = ""
+While Not Eof(ff)
+    Dim As String linea
+    Line Input #ff, linea
+    sContent &= linea & Chr(10)
+Wend
+Close #ff
+
+' Extract UTC and RFC 850
+Dim As Integer utcStart = Instr(sContent, "UTC</td><td>")
+If utcStart > 0 Then
+    utcStart += 12
+    Dim As Integer utcEnd = Instr(utcStart, sContent, "</td>")
+    If utcEnd > 0 Then sUTC = Rtrim(Mid(sContent, utcStart, utcEnd - utcStart))
+End If
+
+Dim As Integer rfcStart = Instr(sContent, "RFC 850</td><td>")
+If rfcStart > 0 Then
+    rfcStart += 16
+    Dim As Integer rfcEnd = Instr(rfcStart, sContent, "</td>")
+    If rfcEnd > 0 Then sRFC850 = Rtrim(Mid(sContent, rfcStart, rfcEnd - rfcStart))
+End If
+
+Kill tmpFile
+
+If sUTC <> "" Then Print "UTC:     " & sUTC
+If sRFC850 <> "" Then Print "RFC 850: " & sRFC850
+
+Sleep

Task/Web-scraping/PowerShell/web-scraping-1.ps1

@@ -0,0 +1,4 @@
+$wc = New-Object Net.WebClient
+$html = $wc.DownloadString('http://tycho.usno.navy.mil/cgi-bin/timer.pl')
+$html -match ', (.*) UTC' | Out-Null
+Write-Host $Matches[1]

Task/Web-scraping/PowerShell/web-scraping-2.ps1

@@ -0,0 +1 @@
+[System.DateTime]::UtcNow

Task/Web-scraping/PowerShell/web-scraping-3.ps1

@@ -0,0 +1 @@
+[System.DateTime]::Now

Task/Web-scraping/QB64/web-scraping.qb64

@@ -0,0 +1,38 @@
+' Assuming WGET is installed
+Dim sContent$, sUTC$, sRFC850$, tmpFile$, cmd$, linea$
+
+tmpFile$ = Environ$("TEMP") + "\utctime.html"
+cmd$ = "wget -q -O " + tmpFile$ + " https://www.utctime.net"
+
+Print "Download with wget..."
+Shell _Hide cmd$
+
+' Read file
+If _FileExists(tmpFile$) Then
+    Open tmpFile$ For Input As #1
+    sContent$ = ""
+    While Not EOF(1)
+        Line Input #1, linea$
+        sContent$ = sContent$ + linea$ + Chr$(10)
+    Wend
+    Close #1
+    Kill tmpFile$
+End If
+
+' Extract UTC and RFC 850
+utcStart = InStr(sContent$, "UTC</td><td>")
+If utcStart > 0 Then
+    utcStart = utcStart + 12
+    utcEnd = InStr(utcStart, sContent$, "</td>")
+    If utcEnd > 0 Then sUTC$ = RTrim$(Mid$(sContent$, utcStart, utcEnd - utcStart))
+End If
+
+rfcStart = InStr(sContent$, "RFC 850</td><td>")
+If rfcStart > 0 Then
+    rfcStart = rfcStart + 16
+    rfcEnd = InStr(rfcStart, sContent$, "</td>")
+    If rfcEnd > 0 Then sRFC850$ = RTrim$(Mid$(sContent$, rfcStart, rfcEnd - rfcStart))
+End If
+
+Print "UTC:     "; sUTC$
+Print "RFC 850: "; sRFC850$

Task/Web-scraping/REXX/web-scraping.rexx

@@ -0,0 +1,30 @@
+-- 23 Oct 2025
+include Setting
+signal off notready
+
+say 'WEB SCRAPING'
+say version
+say
+call Task
+exit
+
+Task:
+procedure
+-- Get page from web (curl is pre-installed on Windows 10/11, Unix and MacOS)
+out='Web.html'
+'curl https://rosettacode.org/wiki/Talk:Web_scraping --ssl-no-revoke --silent --output' out
+-- Read file
+file=Charin(out,1,100000)
+-- Extract all time stamps
+p=Pos('(UTC)',file)
+do while p>0
+   p2=p-2
+   do p1=p2 by -1 until Substr(file,p1,1)=':'
+   end
+   p1-=2
+   say Substr(file,p1,p2-p1+1)
+   p=Pos('(UTC)',file,p+1)
+end
+return
+
+include Abend

Task/Web-scraping/Rebol/web-scraping.rebol

@@ -0,0 +1,25 @@
+Rebol [
+  Title: "Web Scraping"
+  URL: http://rosettacode.org/wiki/Web_Scraping
+]
+
+; Notice that REBOL understands unquoted URL's:
+
+service: http://tycho.usno.navy.mil/cgi-bin/timer.pl
+
+; The 'read' function can read from any data scheme that REBOL knows
+; about, which includes web URLs. NOTE: Depending on your security
+; settings, REBOL may ask you for permission to contact the service.
+
+html: read service
+
+; I parse the HTML to find the first <br> (note the unquoted HTML tag
+; -- REBOL understands those too), then copy the current time from
+; there to the "UTC" terminator.
+
+; I have the "to end" in the parse rule so the parse will succeed.
+; Not strictly necessary once I've got the time, but good practice.
+
+parse html [thru <br> copy current thru "UTC" to end]
+
+print ["Current UTC time:" current]

Task/Web-scraping/VBScript/web-scraping.vbs

@@ -0,0 +1,30 @@
+Function GetUTC() As String
+    Url = "http://tycho.usno.navy.mil/cgi-bin/timer.pl"
+    With CreateObject("MSXML2.XMLHTTP.6.0")
+        .Open "GET", Url, False
+        .send
+        arrt = Split(.responseText, vbLf)
+    End With
+    For Each t In arrt
+        If InStr(t, "UTC") Then
+            GetUTC = StripHttpTags(t)
+
+            Exit For
+        End If
+    Next
+End Function
+
+Function StripHttpTags(s)
+    With New RegExp
+        .Global = True
+        .Pattern = "\<.+?\>"
+        If .Test(s) Then
+            StripHttpTags = .Replace(s, "")
+        Else
+            StripHttpTags = s
+        End If
+    End With
+End Function
+
+WScript.StdOut.Write GetUTC
+WScript.StdOut.WriteLine

Task/Web-scraping/Yabasic/web-scraping-1.basic

@@ -0,0 +1,3 @@
+cd /d c:\Yabasic
+wget -q -O utctime.html https://www.utctime.net
+yabasic webscraping.yab

Task/Web-scraping/Yabasic/web-scraping-2.basic

@@ -0,0 +1,25 @@
+// Read file line by line
+open "utctime.html" for reading as #1
+sContent$ = ""
+while not eof(1)
+    line input #1 linea$
+    sContent$ = sContent$ + linea$ + chr$(10)
+wend
+close #1
+
+utcStart = instr(sContent$, "UTC</td><td>")
+if utcStart > 0 then
+    utcStart = utcStart + 12
+    utcEnd = instr(sContent$, "</td>", utcStart)
+    if utcEnd > 0  sUTC$ = trim$(mid$(sContent$, utcStart, utcEnd - utcStart))
+end if
+
+rfcStart = instr(sContent$, "RFC 850</td><td>")
+if rfcStart > 0 then
+    rfcStart = rfcStart + 16
+    rfcEnd = instr(sContent$, "</td>", rfcStart)
+    if rfcEnd > 0  sRFC850$ = trim$(mid$(sContent$, rfcStart, rfcEnd - rfcStart))
+end if
+
+print "UTC:     ", sUTC$
+print "RFC 850: ", sRFC850$