From 7f0f20d779ea34473ae45db53de9a3c2b03bcd3f Mon Sep 17 00:00:00 2001
From: Jacob Haddon <jhaddon@apokrupha.com>
Date: Thu, 7 Mar 2024 14:22:17 -0500
Subject: [PATCH] updated blank with changes from other file

---
 blankRSS.pl | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/blankRSS.pl b/blankRSS.pl
index 41e0445..7e2a72b 100755
--- a/blankRSS.pl
+++ b/blankRSS.pl
@@ -28,10 +28,12 @@ use HTML::Entities; # https://metacpan.org/pod/HTML::Entities
 # server file folders
 # my $rssFilePath = "/home/USER_FOLDER/public_html/feed.xml";
 # my $htmlFilePath = "/home/USER_FOLDER/public_html/index.html";
+# my $errorFilePath = "/home/USER_FOLDER/public_html/feed.log";
 
 # local file folders
 my $rssFilePath = "feed.xml";
 my $htmlFilePath = "index.html";
+my $errorFilePath = "feed.log";
 
 ###################################
 #  RSS Configurations 
@@ -63,6 +65,10 @@ my %list;
 # Make the list of URLS while parsing DATA
 my $listHTML = "<div class=\'listHTML\'><ul>\n";
 
+# Make a list of URLs that have an error
+my $listURLError = "The following feeds had issues this time:\n\n" . $now->strftime('%a, %d %b %Y %H:%M:%S %z'). "\n\n";
+
+# Go through each URL in the DATA section and make the new list
 while ( my $url = <DATA>) {
     chomp $url;
     
@@ -75,7 +81,12 @@ while ( my $url = <DATA>) {
 	# parse the XML
     my $rss1 = XML::RSS->new;
     eval { $rss1->parse( $xml ) };
-    next if $@;
+    
+    # if empty, add URL to log file variable
+ 	if ($@) {
+    	$listURLError .= "* " . $url . "\n";
+    	next; 
+    }; # if $@
     
     # go through the items from the XML
     for (my $j = 0; $j <= $number_of_items; $j++){
@@ -96,14 +107,29 @@ while ( my $url = <DATA>) {
 			$testItem->{'feedURL'} = $_;
 			$testItem->{'feedName'} = $rss1->{'channel'}{'title'};
 			
+			# Find Author tags 
+			if ($testItem->{'dc'}{'creator'}) {
+				$testItem->{'itemAuthor'} = $testItem->{'dc'}{'creator'};
+			} elsif ($testItem->{'author'}) {
+				$testItem->{'itemAuthor'} = $testItem->{'author'}
+			} else {
+				$testItem->{'itemAuthor'} = $rss1->{'channel'}{'title'};
+			} # if author  
+						
 			# Clean up some of the artifacts in the RSS feed 'description' section
 			$testItem->{'description'} =~ s/\n\s*/\n/g; # get rid of excess white space
 			$testItem->{'description'} =~ s/(<a(.+?)<\/a>)$//s; # link at end of description
 			$testItem->{'description'} =~ s/<(\w) class=(.*?)>/<$1>/s; # remove class statements from text
 			$testItem->{'description'} =~ s/<figure ((.|\n)+?)figure>//sg; #remove "figure" can use pipe to add more
 			$testItem->{'description'} =~ s/<img(.+?)>//sg; # remove IMG tags
+			$testItem->{'description'} =~ s/<span ((.|\n)+?)>//sg; #remove "span" tags (mostly blogger)
+			$testItem->{'description'} =~ s/<\/span>//sg; #remove "span" endtags 
+			$testItem->{'description'} =~ s/<div class="separator" style(.+?)<\/div>//sg; # remove blogger DIV tags
+			$testItem->{'description'} =~ s/<br(.+?)>/<br>/sg; # remove blogger BR tags
+			$testItem->{'description'} =~ s/(<div><br><\/div>)+/<br>/sg; # remove blogger BR + DIV tags
 			$testItem->{'description'} =~ s/.{1200}\K.*//s; # limit length 
-			$testItem->{'description'} =~ s/(<[^<]+)$//s; # link at end of description
+			$testItem->{'description'} =~ s/<\/?div.*?>//sg; # remove div tags
+			$testItem->{'description'} =~ s/(<a[^<]+)$//s; # link at end of description
 			
 			#add continue reading to end. 
 			$testItem->{'description'} .= " <a href=\'" . $testItem->{'link'} . "\' target=\'_blank\'>Continue Reading</a>"; 
@@ -122,6 +148,14 @@ while ( my $url = <DATA>) {
 #close out the list URL html
 $listHTML .= "</div></ul>\n";
 
+###################################
+#  Write the error file 
+###################################
+
+open(FH, '>', $errorFilePath) or die $!;
+print FH $listURLError;
+close(FH);
+
 ###################################
 #  Make an RSS Feed! 
 ###################################