CVSROOT: /web/www
Module name: www
Changes by: Jason Self <jxself> 11/03/26 16:04:44
Modified files:
server/source/planetrss: planetrss.pl
Added files:
server/source/planetrss: changelog
Log message:
Updating planetrss.pl to version 1.1
CVSWeb URLs:
http://web.cvs.savannah.gnu.org/viewcvs/www/server/source/planetrss/planetrss.pl?cvsroot=www&r1=1.1&r2=1.2
http://web.cvs.savannah.gnu.org/viewcvs/www/server/source/planetrss/changelog?cvsroot=www&rev=1.1
Patches:
Index: planetrss.pl
===================================================================
RCS file: /web/www/www/server/source/planetrss/planetrss.pl,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -b -r1.1 -r1.2
--- planetrss.pl 25 Mar 2011 15:22:49 -0000 1.1
+++ planetrss.pl 26 Mar 2011 16:04:25 -0000 1.2
@@ -1,56 +1,85 @@
-# PlanetRSS, Version 1.0
-# Copyright © 2011 Shailesh Ghadge
+ # PlanetRSS, Version 1.1
+ # Copyright © 2011 Shailesh Ghadge
-#This program is free software: you can redistribute it and/or modify
-#it under the terms of the GNU General Public License as published by
-#the Free Software Foundation, either version 3 of the License, or
-#(at your option) any later version.
-#
-#This program is distributed in the hope that it will be useful,
-#but WITHOUT ANY WARRANTY; without even the implied warranty of
-#MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-#GNU General Public License for more details.
-#
-#You should have received a copy of the GNU General Public License
-#along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-#Email: shail...@gnu.org #Date Created: 20 Mar 2011
-#
-#Functionality: Fetch & save 'n' feeds from planet.gnu.org using RSS feed link
http://planet.gnu.org/rss20.xml in html format
-# Each feed is truncated to 'm' characters.
-
-
-#--------------------------------------------
-use XML::RSS::Parser::Lite;
-#Provides simple pure perl RSS parsing
-
-use LWP::Simple;
-#Provides get(url) function
-
-#---------------------------------------------
-my $FeedLines = 3; # 'n' feeds
-my $FeedLength = 200; # 'm' characters
-
-
-my $PGfeeds = get("http://planet.gnu.org/rss20.xml";);
-#Fetch RSS feeds as xml
-
-my $PGparser = new XML::RSS::Parser::Lite;
-#Create new RSS parser
-
-open (PGhtml, '>planetfeeds.html');
+ #This program is free software: you can redistribute it and/or modify
+ #it under the terms of the GNU General Public License as published by
+ #the Free Software Foundation, either version 3 of the License, or
+ #(at your option) any later version.
+ #
+ #This program is distributed in the hope that it will be useful,
+ #but WITHOUT ANY WARRANTY; without even the implied warranty of
+ #MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ #GNU General Public License for more details.
+ #
+ #You should have received a copy of the GNU General Public License
+ #along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+ #Email: shail...@gnu.org #Date: 26 Mar 2011
+ #
+ #Functionality: Compare with previously retrieved feeds(if any) and
then if required,
+ # Fetch & save 'n' feeds from planet.gnu.org using RSS
feed link http://planet.gnu.org/rss20.xml in html format
+ # Each feed is truncated to 'm' characters.
+
+
+ #--------------------------------------------
+ use XML::RSS::Parser::Lite;
+ #Provides simple pure perl RSS parsing
+
+ use LWP::Simple;
+ #Provides get(url) function
+
+ #---------------------------------------------
+ my $FeedLines = 3; # 'n' feeds
+ my $FeedLength = 200; # 'm' characters
+
+ my $PGfeeds = get("http://planet.gnu.org/rss20.xml";);
+ #Fetch RSS feeds as xml
+
+ my $PGparser = new XML::RSS::Parser::Lite;
+ #Create new RSS parser
+
+ $PGparser->parse($PGfeeds);
+ #To Parse the supplied xml
+
+ #-------------------Check----------------------
+ my $Write2File = 1; #Default: We write to PlanetFeeds.html;
+ my $CompareFeeds = 1;
+ open (CurPGhtml, 'planetfeeds.html') || $CompareFeeds--;
+ if($CompareFeeds == 1)
+ {
+ my @Cur_Content = <CurPGhtml>;
+ my $Cur_Title = $Cur_Content[0];
+ $Cur_Title=~ s/<(.*?)>//gi; $Cur_Title=~
s/<a(.*?)>//gi; $Cur_Title=~ s/<\/a>//gi;
+ $Cur_Title=~ s/<p>//gi; $Cur_Title=~ s/<\/p>//gi;
$Cur_Title=~ s/<li>//gi;
+ $Cur_Title=~ s/<ul>//gi; $Cur_Title=~ s/<br
\/>//gi; $Cur_Title =~ s/\s\s+/ /g;
+ $Cur_Title=substr($Cur_Title,0,index($Cur_Title,':'));
+ #Now we have Current Title
+
+ my $New_Checker = $PGparser->get(0);
+ my $New_Title = $New_Checker->get('title');
+ $New_Title = substr($New_Title,index($New_Title,':')+2);
+ #Now we have New Title
-#---------------------------------------------
+ if($Cur_Title eq $New_Title)
+ {
+ $Write2File=0;
+ }
+ #Decide whether to continue & write PGhtml
+ }
+ close(CurPGhtml);
+ #-------------------------End of Check-----------------------------
-$PGparser->parse($PGfeeds);
-#Parse the supplied xml
+ #print "content-type: text/html \n";
+ # Use above if you get errors regarding headers
-#print "content-type: text/html \n";
-# uncomment above if you get errors regarding headers
+ #---------------------To Create/Overwrite PlanetFeeds.html-----------
+ if($Write2File==1)
+ {
-#Print Feeds data in the format of- "Title - Description... <a
href='URL'>more</a>"
-for (my $i = 0; $i < $FeedLines; $i++)
-{
+ open (PGhtml, '>planetfeeds.html');
+ #Print Feeds data in the format of- "Title - Description... <a
href='URL'>more</a>"
+ for (my $i = 0; $i < $FeedLines; $i++)
+ {
my $PGfeed = $PGparser->get($i);
my $PGurl = $PGfeed->get('url');
my $PGtitle = $PGfeed->get('title');
@@ -77,5 +106,9 @@
#Output
print PGhtml "<p><a href='".$PGurl."'>".$PGtitle ."</a>:
".$PGdesc. "... <a href='".$PGurl."'>more</a></p>\n";
}
-}
-close(PGhtml);
+ }
+ close(PGhtml);
+ }
+ #------------------------------End of To Create/Overwrite
PlanetFeeds.html-------------------------
+
+
Index: changelog
===================================================================
RCS file: changelog
diff -N changelog
--- /dev/null 1 Jan 1970 00:00:00 -0000
+++ changelog 26 Mar 2011 16:04:25 -0000 1.1
@@ -0,0 +1,6 @@
+Version 1.1 - 26 Mar 2011
+Added Checker code, to first check previously retrieved feeds(if any) and only
then proceed to write to planetfeeds.html if required.
+
+Version 1.0 - 20 Mar 2011
+The Perl script fetches & saves 'n' feeds from planet.gnu.org using RSS feed
link http://planet.gnu.org/rss20.xml in html format.
+Each feed is truncated to 'm' characters.
