Just another update

Task/Web-scraping/00DESCRIPTION

@@ -1,11 +1,22 @@
+{{omit from|ACL2|Does not have network access.}}
+{{omit from|Batch File|Does not have network access.}}
+{{omit from|Locomotive Basic|Does not have network access.}}
+{{omit from|Lotus 123 Macro Scripting}}
+{{omit from|M4}}
+{{omit from|Maxima}}
+{{omit from|Openscad}}
+{{omit from|PARI/GP}}
+{{omit from|PostScript|no network access}}
+{{omit from|Retro|Does not have network access.}}
+{{omit from|ZX Spectrum Basic|Does not have network access.}}
 Create a program that downloads the time from this URL: [http://tycho.usno.navy.mil/cgi-bin/timer.pl http://tycho.usno.navy.mil/cgi-bin/timer.pl] and then prints the current UTC time by extracting just the UTC time from the web page's [[HTML]].
 
 <!-- As of March 2014, the page is available
+{{task|Networking and Web Interaction}}
 
 The page http://tycho.usno.navy.mil/cgi-bin/timer.pl is no longer available since july 2011. The relevant part of that page source looked like this:
 
 <pre>
-
 ...
 
 <TITLE>What time is it?</TITLE>
@@ -19,7 +30,6 @@ The page http://tycho.usno.navy.mil/cgi-bin/timer.pl is no longer available sinc
 <BR>Jul. 27, 12:57:22 PM HAST	Hawaii-Aleutian Time
 
 ...
-
 </pre>
 
 End of comment -->

Task/Web-scraping/00META.yaml

@@ -1,2 +1,4 @@
 ---
-note: Networking and Web Interaction
+category:
+- Input_Output
+note: Networking

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

@@ -0,0 +1,39 @@
+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/JavaScript/web-scraping.js

@@ -0,0 +1,7 @@
+var req = new XMLHttpRequest();
+req.onload = function () {
+  var re = /[JFMASOND].+ UTC/; //beginning of month name to 'UTC'
+  console.log(this.responseText.match(re)[0]);
+};
+req.open('GET', 'http://tycho.usno.navy.mil/cgi-bin/timer.pl', true);
+req.send();