--- a/app0.scala	Wed Sep 26 02:08:55 2012 +0100
+++ b/app0.scala	Wed Sep 26 02:50:44 2012 +0100
@@ -3,5 +3,6 @@
 def get_page(url: String) : String = { 
   Source.fromURL(url).take(10000).mkString  
 
+get_page("""http://www.inf.kcl.ac.uk/staff/urbanc/""")
 
 

--- a/app1.scala	Wed Sep 26 02:08:55 2012 +0100
+++ b/app1.scala	Wed Sep 26 02:50:44 2012 +0100
@@ -1,7 +1,3 @@
-import io.Source
-import scala.util.matching.Regex
-
-// gets the first ~10K of a page
 def get_page(url: String) : String = { 
   try {
     Source.fromURL(url).take(10000).mkString  
@@ -14,27 +10,3 @@
   }
 }
 
-// staring URL for the crawler
-val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
-
-// regex for URLs
-val http_pattern = """\"https?://[^\"]*\"""".r
-
-def unquote(s: String) = s.drop(1).dropRight(1)
-
-def get_all_URLs(page: String) : Set[String] = {
-  (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
-}
-
-// naive version - seraches until a given depth
-// visits pages potentially more than once
-def crawl(url: String, n: Int) : Unit = {
-  if (n == 0) ()
-  else {
-    println("Visiting: " + n + " " + url)
-    for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
-  }
-}
-
-crawl(startURL, 2)
-

Binary file slides01.pdf has changed

--- a/slides01.tex	Wed Sep 26 02:08:55 2012 +0100
+++ b/slides01.tex	Wed Sep 26 02:50:44 2012 +0100
@@ -228,16 +228,50 @@
 \end{frame}}
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%   
 
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}A Web Crawler\end{tabular}}
+
+\begin{enumerate}
+\item given an URL, read the corresponding webpage
+\item extract all links from it
+\item call the web-crawler again for all these links
+\end{enumerate}
+
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%   
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\mode<presentation>{
+\begin{frame}[c]
+\frametitle{\begin{tabular}{c}A Web Crawler\end{tabular}}
+
+\begin{enumerate}
+\item given an URL, read the corresponding webpage
+\item if not possible print, out a problem
+\item if possible, extract all links from it
+\item call the web-crawler again for all these links
+\end{enumerate}\bigskip\pause
+
+\small (we need to bound the number of recursive calls)
+
+\small (the purpose is to check all links on my own webpage)
+\end{frame}}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%   
+
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 \mode<presentation>{
 \begin{frame}[c]
 \frametitle{\begin{tabular}{c}Scala\end{tabular}}
 
-\footnotesize a simple function for reading webpages
+\footnotesize a simple Scala function for reading webpages\\[-3mm]
 
 {\lstset{language=Scala}\fontsize{8}{10}\selectfont
 \texttt{\lstinputlisting{app0.scala}}}\pause\bigskip
 
+\footnotesize slightly more complicated for handling errors:\\[-3mm]
+
 \footnotesize
 {\lstset{language=Scala}\fontsize{8}{10}\selectfont
 \texttt{\lstinputlisting{app1.scala}}}