September 2017 Update

Task/Web-scraping/CoffeeScript/web-scraping-1.coffee

@@ -1,39 +0,0 @@
-http = require 'http'
-
-CONFIG =
-  host: 'tycho.usno.navy.mil'
-  path: '/cgi-bin/timer.pl'
-
-# Web scraping code tends to be brittle, and this is no exception.
-# The tycho time page does not use highly structured markup, so
-# we do a real dirty scrape.
-scrape_tycho_ust_time = (text) ->
-  for line in text.split '\n'
-    matches = line.match /(.*:\d\d UTC)/
-    if matches
-      console.log matches[0].replace '<BR>', ''
-      return
-  throw Error("unscrapable page!")
-
-# This is low-level-ish code to get data from a URL. It's
-# pretty general purpose, so you'd normally tuck this away
-# in a library (or use somebody else's library).
-wget = (host, path, cb) ->
-  options =
-    host: host
-    path: path
-    headers:
-      "Cache-Control": "max-age=0"
-
-  req = http.request options, (res) ->
-    s = ''
-    res.on 'data', (chunk) ->
-      s += chunk
-    res.on 'end', ->
-      cb s
-  req.end()
-
-# Do our web scrape
-do ->
-  wget CONFIG.host, CONFIG.path, (data) ->
-    scrape_tycho_ust_time data

Task/Web-scraping/CoffeeScript/web-scraping-2.coffee

@@ -1,2 +0,0 @@
-> coffee web_scrape.coffee
-Jan. 09, 19:19:07 UTC

Task/Web-scraping/Gambas/web-scraping.gambas

@@ -0,0 +1,17 @@
+Public Sub Main()
+Dim sWeb, sTemp, sOutput As String                                          'Variables
+
+Shell "wget -O /tmp/web http://tycho.usno.navy.mil/cgi-bin/timer.pl" Wait   'Use 'wget' to save the web file in /tmp/
+
+sWeb = File.Load("/tmp/web")                                                'Open file and store in sWeb
+
+For Each sTemp In Split(sWeb, gb.NewLine)                                   'Split the file by NewLines..
+  If InStr(sTemp, "UTC") Then                                               'If the line contains "UTC" then..
+    sOutPut = sTemp                                                         'Extract the line into sOutput
+    Break                                                                   'Get out of here
+  End If
+Next
+
+Print Mid(sOutput, 5)                                                       'Print the result without the '<BR>' tag
+
+End

Task/Web-scraping/Kotlin/web-scraping.kotlin

@@ -0,0 +1,19 @@
+// version 1.1.3
+
+import java.net.URL
+import java.io.InputStreamReader
+import java.util.Scanner
+
+fun main(args: Array<String>) {
+    val url = URL("http://tycho.usno.navy.mil/cgi-bin/timer.pl")
+    val isr = InputStreamReader(url.openStream())
+    val sc = Scanner(isr)
+    while (sc.hasNextLine()) {
+        val line = sc.nextLine()
+        if ("UTC" in line) {
+            println(line.drop(4).take(17))
+            break
+        }
+    }
+    sc.close()
+}

Task/Web-scraping/MIRC-Scripting-Language/web-scraping.mirc

@@ -0,0 +1,23 @@
+alias utc {
+  sockclose UTC
+  sockopen UTC tycho.usno.navy.mil 80
+}
+
+on *:SOCKOPEN:UTC: {
+  sockwrite -n UTC GET /cgi-bin/timer.pl HTTP/1.1
+  sockwrite -n UTC Host: tycho.usno.navy.mil
+  sockwrite UTC $crlf
+}
+
+on *:SOCKREAD:UTC: {
+  sockread %UTC
+  while ($sockbr) {
+    if (<BR>*Universal Time iswm %UTC) {
+      echo -ag $remove(%UTC,<BR>,$chr(9),Universal Time)
+      unset %UTC
+      sockclose UTC
+      return
+    }
+    sockread %UTC
+  }
+}

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

@@ -0,0 +1,23 @@
+/* load the RexxcURL library */
+Call RxFuncAdd 'CurlLoadFuncs', 'rexxcurl', 'CurlLoadFuncs'
+Call CurlLoadFuncs
+
+url = "http://tycho.usno.navy.mil/cgi-bin/timer.pl"
+
+/* get a curl session */
+curl = CurlInit()
+if curl \= ''
+then do
+   call CurlSetopt curl, 'URL', Url
+   if curlerror.intcode \= 0 then exit
+   call curlSetopt curl, 'OUTSTEM', 'stem.'
+   if curlerror.intcode \= 0 then exit
+   call CurlPerform curl
+
+   /* content is in a stem - lets get it all in a string */
+   content = stem.~allItems~makestring('l')
+   /* now parse out utc time */
+   parse var content content 'Universal Time' .
+   utcTime = content~substr(content~lastpos('<BR>') + 4)
+   say utcTime
+end

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

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

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

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

Task/Web-scraping/Protium/web-scraping-1.protium

@@ -1,5 +0,0 @@
-<@ DEFAREPRS>Rexx Parse</@>
-<@ DEFPRSLIT>Rexx Parse|'<BR>' UTCtime 'UTC'</@>
-<@ LETVARURL>timer|http://tycho.usno.navy.mil/cgi-bin/timer.pl</@>
-<@ ACTRPNPRSVAR>Rexx Parse|timer</@>
-<@ SAYVAR>UTCtime</@>

Task/Web-scraping/Protium/web-scraping-2.protium

@@ -1,5 +0,0 @@
-<# DEFINE WORKAREA PARSEVALUES>Rexx Parse</#>
-<# DEFINE PARSEVALUES LITERAL>Rexx Parse|'<BR>' UTCtime 'UTC'</#>
-<# LET VARIABLE URLSOURCE>timer|http://tycho.usno.navy.mil/cgi-bin/timer.pl</#>
-<# ACT REPLACEBYPATTERN PARSEVALUES VARIABLE>Rexx Parse|timer</#>
-<# SAY VARIABLE>UTCtime</#>

Task/Web-scraping/Protium/web-scraping-3.protium

@@ -1 +0,0 @@
-<@ SAY AFT BEF URL LIT LIT LIT >http://tycho.usno.navy.mil/cgi-bin/timer.pl| UTC|<BR></@>

Task/Web-scraping/Zkl/web-scraping.zkl

@@ -0,0 +1,14 @@
+const HOST="tycho.usno.navy.mil", PORT=80, dir="/cgi-bin/timer.pl";
+get:="GET %s HTTP/1.0\r\nHost: %s:%s\r\n\r\n".fmt(dir,HOST,PORT);
+server:=Network.TCPClientSocket.connectTo(HOST,PORT);
+server.write(get);       // send request to web serer
+data:=server.read(True); // read data from web server
+
+data.seek(data.find("UTC")); // middle of line
+c:=data.seek(Void,0);       // start of line
+line:=data[c,data.seek(Void,1)-c].text;
+line.print();	// the HTML UTC line
+
+re:=RegExp(0'|.*(\d\d:\d\d:\d\d)|);  // get time
+re.search(line);
+re.matched[1].println();