\n";
#GOOGLE NEWS PARSER:
&html_border();
print NEW "Google News
\n";
&end_border();
$errorOccured=0;
foreach $line (@{$all_data[0]}) {
@temp = split(/\/,$line);
foreach $line2 (@temp) {
&html_error($line2);
#print NEW "\n";
#get categories
if( ($line2 =~ /\Top/) || ($line2 =~ /\World/) ||
($line2 =~ /\U\.S/) || ($line2 =~ /\Business/) ||
($line2 =~ /\Sci/) || ($line2 =~ /\Sports/)){# ||
# ($line2 =~ /\Enter/) || ($line2 =~ /\Health/)){
#$line2=~ /\([a-zA-Z ]+)\<\/b\>/;
#$result = $1;
#print $1."\n";
#remove HTML tags.
$line2 =~ s/\<\/?IMG.*?\>//g;
$line2 =~ s/\<\/?p.*?\>//g;
#remove table tags
$line2 =~ s/\<\/?tr.*?\>//g;
$line2 =~ s/\<\/?td.*?\>//g;
$line2 =~ s/\<\/?table.*?\>//g;
#remove links
$line2 =~ s/\//g;
#remove extra characters
$line2 =~ s/\|//g;
#remove whitespace
$line2 =~ s/\s+//g;
#Remove JUMP TO feature
$line2 =~ s/\ first time
if($headline_limit >= 1){
print NEW "\n";
}
print NEW $line2, "
\n";
print NEW "\n";
$headline_limit = $Number_of_headlines + 1;
}
#get headlines and put into file
if(($line2 =~ /.*class\=y/) && ($headline_limit > 1)){
#remove table tags
$line2 =~ s/\<\/?tr.*?\>//g;
$line2 =~ s/\<\/?td.*?\>//g;
$line2 =~ s/\<\/?table.*?\>//g;
#/url?ntc=0L0A0&q=
$line2 =~ s/\/url\?.*?q\=//g;
#$line2 =~ s/\<.*?\>//; #removes html
$line2 =~ s/class\=.//;
#add a linebreak after a
tag
$line2 =~ s/\/\\n/g;
#change %3F into actual characters
$line2 =~ s/\%3F/\?/g;
$line2 =~ s/\%3D/\=/g;
$line2 =~ s/\%26/\&/g;
#shorten links that are too long
# $line2 = &shorten_line($line2);
print NEW "*$line2
\n";
&print_error( $line2);
$headline_limit--;
}
}
}
print NEW " | \n";
#SLASHDOT NEWS PARSER:
&html_border();
print NEW "Slashdot\n";
&end_border();
print NEW " \n\n";
$errorOccured=0;
foreach $line (@{$all_data[1]}) {
&html_error($line);
#print NEW " $line
\n";
if($line =~ /Your Headline Reader Has Been Banned/){
print NEW "Slashdot is being a little b*!@#.
\n";
print NEW "Whoever wrote their crummy xml/rss
server ";
print NEW "needs a 133tness class
from yours truly.";
}
#bug fix to remove extra "amp;" due to xml weirdness
$line =~ s/amp\;amp\;/amp\;/g;
#parse XML for headlines
if(($line =~ /\//g;
$line =~ s/^\s+//g;
$title = $line;
$original_title = $title;
if(length($title)>$column_width+3){
$title=substr($title,0,$column_width);
$title=$title."...";
}
}
if(($line =~ /\<url\>(.*?)\</) && ($counter <= ($Number_of_headlines*4))){
$headline_url = $1;
# print NEW "<div id=\"sdlink$counter\" onMouseDown=\"sdtext$counter.style.display=\'block\';\">\n";
print NEW "<div id=\"sdlink$counter\" onMouseDown=\"ToggleSlash(sdtext$counter);\">\n";
print NEW "<font color=\"blue\"><u>$title</u></font>\n" . "</div>\n";
# print NEW "<a title=\"$original_title\" href=\"$headline_url\">$title</a><br>\n\n";
&print_error( "<a title=\"$original_title\" href=\"$headline_url\">$title</a><br>\n");
# GRAB CONTENT FROM LINK
my $slash_req = HTTP::Request->new(GET => $headline_url);
@slash_page = split(/\n/,$ua->request($slash_req)->as_string);
$div_header = "\t<div id=\"sdtext$counter\" style=\"display:none;\"\">\n";#onMouseDown=\"sdtext$counter.style.display ='none';
$div_header = $div_header . "\t <TABLE border=\"0\" width=\"100%\"><tr><td bgcolor=\"#999999\">\n";
$div_header = $div_header . "\t <TABLE border=\"0\" width=\"100%\"><tr><td bgcolor=\"#eeeeee\" align=\"left\" width=\"190\">\n";
$div_header = $div_header . "\t <small>\n" . "<b><a href=\"$headline_url\">$original_title</a></b><br>\n\t";
$div_tailer = " \t</small>\n\t </td></tr></table>\n\t </td></tr></table>\n\t</div>";
$gotcha=0;
foreach $slashline (@slash_page) {
if($slashline =~ /\<i\>(.*?)\<\/i\>/i){
print NEW "\n $div_header $1 $div_tailer\n\n";
$gotcha=1;
last;
}
}
if($gotcha==0){
print NEW "\n $div_header Couldn't find the story. $div_tailer\n\n";
}
$counter++;
}
#
# #parse XML for images
# if( ($line =~ /\<image\>(\S+)\</) && ($counter<=($Number_of_headlines*4))){
# $image_name = $1;
# #http://images.slashdot.org/topics/
# $align="right";
# if($counter % 2 == 0){
# $align="left";
# }
# print NEW "<img align=\"$align\" height=\"32\" width=\"40\" src=\"http://images.slashdot.org/topics/";
# print NEW $image_name . "\">\n";
# print NEW $saved_title;
# }
}
print NEW "</small>\n</P>\n";
#END SLASHDOT NEWS PARSER:
print NEW "\n\n<!-------- INQUIRER NEWS SECTION -------------->\n";
$valid_data = 0;
#INQUIRER NEWS PARSER:
&html_border();
print NEW "<A STYLE=\"text-decoration:none\" href=\"http://www.theinquirer.net/\"><FONT size=\"5\" color=\"purple\"><b>The Inquirer</b></FONT></A>\n";
&end_border();
$errorOccured=0;
foreach $line (@{$all_data[2]}) {
&html_error($line);
#parse HTML for headlines
if($line =~ /td_mainbody/){
$valid_data=1;
}
if(($valid_data) && ($line =~ /div class\=\"ht\"/)){
#remove all the following HTML tags.
$line =~ s/\<\/?td.*?\>//g;
$line =~ s/\<\/?tr.*?\>//g;
$line =~ s/\<\/?img.*?\>//g;
$line =~ s/\<\/?b.*?\>//g;
$line =~ s/\<\/?embed.*?\>//g;
$line =~ s/\<\/?hr.*?\>//g;
$line =~ s/\<\/?s.*?\>//g;
#replace everything after a link with a <br>tag.
$line =~ s/\/a\>/\/a\>\<br\>/g;
#insert theinquirer.net into a link url
$line =~ s/\"\?/\"http\:\/\/www\.theinquirer\.net\/\?/g;
print NEW "</small>\n<P>\n<small>\n";
@temp = split(/\<\/div\>\<\/div\>\<\/div\>/,$line);
$count = 0;
foreach $newline (@temp) {
if(($count < ($Number_of_headlines*4)) && !($newline=~/2002 Breakthrough Publishing Ltd/) && !($newline=~/Advert/)) {
$newline =~ s/\<\/?div.*?\>//g;
#remove font tags and everything inside them
$newline =~ s/\<font.*?\/font\>//g;
$newline =~ s/\s+$//;
$newline =~ s/\<br\>.*/\<br\>\n/;
#remove everything between <a></a> links
$newline =~ s/\<\/a.*?\>.*?\<a/\<\/a\>\<br\>\n\<a/g;
#shorten links that are too long
$newline = &shorten_line($newline);
#remove leading whitespace
$newline =~ s/^\s+//;
print NEW $newline;
&print_error( $newline);
}
$count++;
}
if($newline=~/\w+/){
print NEW "</small>\n</P>\n";
print NEW "<BR>\n";
}
}
}
print NEW " </TD>\n <TD valign=\"top\">\n";
#END INQUIRER NEWS PARSER:
#!@#$%^&*()
print NEW "\n\n<!-------- SACBEE NEWS SECTION -------------->\n";
#SacBee NEWS & INFO PARSER
&html_border();
print NEW "<A STYLE=\"text-decoration:none\" href=\"http://sacbee.com/\"><FONT size=\"5\" color=\"orange\"><b>SacBee</b></FONT></A>";
&end_border();
print NEW "<BR>\n<small>\n";
$data_flag=$Number_of_headlines * 7;
$errorOccured=0;
foreach $line (@{$all_data[8]}) {
&html_error($line);
#grab and print actual links to articles
if( (($line =~ /nheadLineSS/) || ($line =~ /ntopStory/)) && ($data_flag>=0)){
$line =~ s/\<br \/\>/\<br\>/g;
#add html to link
$line =~ s/href\=\"/href\=\"http\:\/\/www\.sacbee\.com/;
$line = &shorten_line($line);
print NEW "$line\n";
&print_error( "$line\n");
$data_flag--;
}
}
print NEW"</small>\n</P>\n";
#END SACBEE NEWS & INFO PARSER
#print NEW "\n\n<!-------- YAHOO/REUTERS NEWS SECTION -------------->\n";
##YAHOO NEWS & INFO PARSER
#&html_border();
#print NEW "<A STYLE=\"text-decoration:none\" href=\"http://my.yahoo.com/\"><FONT size=\"5\" color=\"orange\"><b>My Yahoo!</b></FONT></A><BR>\n<small>\n";
#&end_border();
#
#$data_flag=0; $errorOccured=0;
#foreach $line (@{$all_data[8]}) {
# &html_error($line);
#
#
# #grab and print actual links to articles
# if(($data_flag) && ($line =~ /story\.news\.yahoo\.com/)){
# $line =~ s/\<\/?li.*?\>/\n/g;
# $line =~ s/\<\/?td.*?\>//g;
# $line =~ s/\<\/?tr.*?\>//g;
# $line =~ s/\<\/?font.*?\>//g;
# $line =~ s/\<\/?ul.*?\>//g;
# $line =~ s/\/a\>/\/a\>\<br\>/g;
# $line =~ s/\<i.*?\/i\>//g;
# if(!($line =~ /\<b\>/)){
#
# #do a split here.
# @three_headlines = split(/\n/,$line);
# foreach $line (@three_headlines) {
#
# #shorten links that are too long
# $line = &shorten_line($line);
#
# print NEW "$line\n";
# &print_error( "$line\n");
#
# $data_flag--;
# }
# }
# }
# #grab and print headlines
# if (($line =~ /Top Stories from Reuters/) || ($line =~ /World News from Reuters/) || ($line =~ /Business News from Reuters/) || ($line=~/Politics News from Reuters/)){
# #$line =~ s/\<[^a].*?\<\/.*?\>//g;
# $line =~ s/.*\<b\>/\<b\>/g;
# $line =~ s/\<\/?td.*?\>//g;
# $line =~ s/\<\/?tr.*?\>//g;
# $line =~ s/\<\/?br.*?\>//g;
# $line =~ s/\<\/?font.*?\>//g;
# $line =~ s/\<\/?table.*?\>//g;
# $line =~ s/\<i.*?\/i\>//g;
# $line =~ s/\<\!.*?\/\-\-\>//g;
#
# #may want to remove these
# $line =~ s/from\s+Reuters//g;
# $line =~ s/\<\/?a.*?\>//g;
# print NEW "</small>\n$line\n<br>\n<small>";
# $data_flag=2;
# }
#
#}
#print NEW"</small>\n</P>\n";
##END YAHOO NEWS & INFO PARSER
print NEW "\n\n<!-------- ACESHARDWARE NEWS SECTION -------------->\n";
$valid_data = 0;
$second_line=0;
############ ACESHARDWARE NEWS PARSER: ################
print NEW "<br>\n";
&html_border();
print NEW "<A STYLE=\"text-decoration:none\" href=\"$url[10]\"><FONT size=\"5\" color=\"blue\"><b>Ace's Hardware</b></FONT></A>\n";
&end_border();
print NEW "<P>\n<small>\n";
$errorOccured=0; $link_var = "";
foreach $line (@{$all_data[10]}) {
&html_error($line);
#PRINTS ARTICLE TITLE
if ($second_line) {
$line =~ s/\<\/?font.*?\>//g;
$line =~ s/\<\/?b\>//g;
#remove extra whitespace
$line =~ s/\s*$//;
$line =~ s/^\s*//;
$line_new = $link_var . $line;
$line_new = shorten_line($line_new);
print NEW $line_new."\n";
&print_error( "$line_new\n");
}
$second_line=0;
#Finds LINK
if(($valid_data) && ($line=~/\<a/)){
#print NEW "\n<!--$line-->\n";
$line =~ s/href\=\"\#/href=\"http\:\/\/www\.aceshardware\.com\/\#/g;
$line =~ s/\<\/?font.*?\>//g;
$line =~ s/\<\/?b\>//g;
#insert breaks after <br> tags
$line =~ s/\<br\>/\<br\>\n/g;
#remove extra whitespace
$line =~ s/\s*$//;
$line =~ s/^\s*//;
#insert title
#$line =~s /\<a\s+h/\<a title\=\"$temp_line\" h/;
$second_line=1;
#print NEW $line;
#&print_error( "$line");
$link_var = $line;
}
if ($line =~ /Latest News\<\/b\>/){
$valid_data = 1;
}
if ($line =~ /\<\/td/) {
$valid_data = 0;
}
}
print NEW "</small>\n</P>\n </TD>\n <TD valign=\"top\" width=\"180\">";
########################################
#Yahoo Top Images
# print NEW " <Table>\n <TR><TD valign=\"top\" width=\"180\">\n";
print NEW "\n <!-------- News Images from Yahoo-------------->\n";
&html_border();
print NEW "<A STYLE=\"text-decoration:none\"";
print NEW "href=\"http://news.yahoo.com/news?tmpl=index2&cid=716/\">";
print NEW "<FONT size=\"5\" color=\"red\"><b>Yahoo News</b></FONT></A><BR>\n";
&end_border();
print NEW " <P>\n";
$valid_data=0; $alternate=0;
$errorOccured=0; $picture_size = 35;
foreach $line (@{$all_data[18]}) {
&html_error($line);
if($line =~ /class\=topstory/){
$line =~ s/.*?\>//;
print NEW " <small>$line</small></a><br clear=all>\n";
}
if(($line =~ /alt\=Photo/) or ($line =~ /alt\=Slideshow/)){
#only one leading space
$line =~ s/\s+/ /g;
#trim size
$line =~ s/width\=(\d{2,3})/width\=50/;
$width = $1;
$line =~ s/height\=(\d{2,3})/height\=50/;
$height = $1;
#keep original aspect ratio
$ratio = $width / $height;
if($width > $height){
$height = $picture_size;
$width = $picture_size * $ratio;
}else{
$width = $picture_size;
$height = $picture_size / $ratio;
}
$line =~ s/height\=(\d{2,3})/height\=$height/;
$line =~ s/width\=(\d{2,3})/width\=$width/;
#remove </a> tags
$line =~ s/\<\/a\>//;
#edit <a> tags for no underline, <img> tags no border
# $line =~ s/\<a/\<a STYLE\=\"text\-decoration\:none\"/;
$line =~ s/\<img/\<img border\=\"0\"/;
#remove comments
$line =~ s/\<\!\-\-.*?\-\-\>//g;
#align alternating
$line =~ s/align\=left//;
$line =~ s/align\=right//;
if($alternate==0){
$line =~ s/\<img/\<img align\=\"left\"/;
$alternate = 1;
}else{
$line =~ s/\<img/\<img align\=\"right\"/;
$alternate = 0;
}
print NEW " $line\n";
$valid_data = 1;
}
}
#border for news section
&end_border();
#end news section
print NEW " </TD>\n </TR>\n</TABLE>\n<BR>\n";
#start 4th Column
print NEW " </TD>\n <TD rowspan=\"9\" valign=\"top\">\n<!--START Righthand COLUMN 4-->\n";
####### SPECIAL RIGHT HAND COLUMN DATA
if (open(RB, "rightbar.txt")) {
while (<RB>){
print NEW $_;
}
}
else{
print NEW "\n\t<!-- CANNOT FIND rightbar.txt with HTML DATA-->\n";
}
print NEW "\t<!-- END OF RIGHTHAND COLUMN-->\n";
close(RB);
####### END SPECIAL RIGHT HAND COLUMN DATA
#create outer table for rightbar
print NEW "\t </TD></TR></TABLE>\n\n";
#END OF NEWS TABLE, START COMICS TABLE
print NEW "\n\n\n<!-------- END NEWS : START COMICS -------------->\n\n\n";
print NEW "<TABLE border=\"0\">\n <TR>\n <TD colspan=\"8\" valign=\"top\">\n";
if (!($comics_on)) {
print NEW "\n\n\n<!--------- COMICS ARE OFF ------------------->\n\n\n";
print NEW "<h3>Comics are off</h3>\n";
}
else{
print NEW "\n <!-------- COMICS:Dilbert SECTION -------------->\n";
$comic = "";
#DILBDERT URL PARSER:
print NEW " <hr><FONT size=\"5\" color=\"blue\">Comics</FONT>\n <P>\n";
$errorOccured=0;
foreach $line (@{$all_data[3]}) {
&html_error($line);
if($line =~ /Today\'s Dilbert Comic/){
$line =~ s/\<\/?TD.*?\>//g;
$line =~ s/\<\/?BR.*?\>//g;
$line =~ s/\<\/?a.*?\>//gi;
$line =~ s/\<\!\-\-.*?\-\-\>//g;
#<IMG SRC="/images/ffffff_dot.gif"
$line =~ s/\<IMG SRC\=\"\/images\/fffff.*?\>//g;
#$line =~ s/\<IMG SRC=\".*?mystery_artist.*?\>//;
#<IMG SRC="/comics/dilbert/
$line =~ s/\<IMG\s*SRC\=\"\/comics\/dilbert//g;
$line =~ s/gif\".*/gif\"/;
$line =~ s/^\s+//g;
$comic = $line;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.dilbert.com\"><IMG border=\"0\" SRC=\"http://www.dilbert.com/comics/dilbert$comic></A>\n";
}
}
print NEW " </P>\n";
#END DILBERT URL PARSER:
########################################
#PENNY ARCADE URL PARSER:
print NEW "\n <!-------- COMICS:Penny Arcade SECTION -------------->\n";
$comic = "";
print NEW " <P>\n";
$errorOccured=0;
foreach $line (@{$all_data[4]}) {
&html_error($line);
#Ack! Y2K10 bug!!!!
if($line =~ /images\/200/){
$line =~ s/\<\/?td.*?\>//g;
$line =~ s/ALT\=\"\"//;
$line =~ s/c\=\"/c\=\"http\:\/\/www\.penny\-arcade\.com\//;
$line =~ s/\s+/ /g;
$line =~ s/\<img/\<img border\=\"0\"/;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.penny-arcade.com\">";
print NEW $line;
print NEW "</A>\n";
}
}
print NEW " </P>\n";
#END PENNY ARCADE URL PARSER:
########################################
#PVP SECTION
print NEW "\n <!-------- COMICS:PVP Online SECTION -------------->\n";
print NEW " <P>\n";
$errorOccured=0;
foreach $line (@{$all_data[5]}) {
&html_error($line);
if($line =~ /IMG.*?archive\//){
$line =~ s/C\=\"/C\=\"http\:\/\/www\.pvponline\.com\//;
$line =~ s/\<\/?center.*?\>//gi;
$line =~ s/\<\/?br.*?\>//g;
$line =~ s/\<\/?td.*?\>//g;
#remove extra <img> tag
$line =~ s/\<img.*?images.*?\>//;
$line =~ s/\<IMG/\<IMG align\=\"left\" border\=\"0\"/;
#fix: remove align="left"
$line =~ s/align\=\"left\"//g;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.pvponline.com/\">";
print NEW $line;
print NEW "</A>\n";
}
}
print NEW " </P>\n";
#END PVP URL PARSER
########################################
#Diesel Sweeties
print NEW "\n <!-------- COMICS:Diesel Sweeties SECTION -------------->\n";
print NEW " <P>\n";
$errorOccured=0; $linecount=0;
foreach $line (@{$all_data[6]}) {
&html_error($line);
$linecount++;
if($line =~ /\*\*\*newest/){
$line =~ s/.*?\*\*\*newest//;
$line =~ s/.*?\<img/\<img/i;
$line =~ s/\>.*/\>/;
$line =~ s/^\s*//;
$line =~ s/src\=\"/src\=\"http\:\/\/www\.dieselsweeties\.com/;
# $line =~ s/\<img/\<img align\=\"right\"/i;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.dieselsweeties.com/\">";
print NEW $line ."\n";
print NEW " </A>\n";
}
}
print NEW " </P>\n";
########################################
#Little Gamers SECTION
print NEW "\n <!-------- COMICS:Little Gamers Online SECTION -------------->\n";
print NEW " <P>\n";
$errorOccured=0;
foreach $line (@{$all_data[20]}) {
&html_error($line);
if($line =~ /show_strip/){
$line =~ s/src\=\'/src\=\'http\:\/\/www\.little\-gamers\.com/;
$line =~ s/\' border\=0/\'/i;
$line =~ s/\<\/?tr.*?\>//gi;
$line =~ s/\<\/?td.*?\>//gi;
$line =~ s/\<img/\<img align\=\"left\" border\=\"0\"/i;
$line =~ s/^\s+//;
$line =~ s/\s+$//;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.little-gamers.com/\">";
print NEW $line;
print NEW "</A>\n";
}
}
print NEW " </P>\n";
#END LittleGamers URL PARSER
########################################
#MegaTokyo Gamers SECTION
print NEW "\n <!-------- COMICS:MegaTokyo Online SECTION -------------->\n";
print NEW " <br clear=\"all\">\n";
print NEW " <P>\n";
$errorOccured=0;
foreach $line (@{$all_data[21]}) {
&html_error($line);
if($line =~ /\/strips/){
$line =~ s/\<\/?tr.*?\>//gi;
$line =~ s/\<\/?td.*?\>//gi;
$line =~ s/.*?\<img src\=\"\/strips/\<img src\=\"\/strips/i;
$line =~ s/src\=\"/src\=\"http\:\/\/www\.megatokyo\.com/i;
$line =~ s/\.gif\".*/\.gif\"\>/i;
$line =~ s/\<img/\<img align\=\"left\" border\=\"0\"/i;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.megatokyo.com/\">";
print NEW $line;
print NEW "</A>\n";
}
}
print NEW " </P>\n";
#END MEGATOKYO URL PARSER
########################################
#CTRL+ALT+DEL Gamers SECTION
print NEW "\n <!-------- COMICS:CTRL+ALT+DEL Online SECTION -------------->\n";
print NEW " <br clear=\"all\">\n";
print NEW " <P>\n";
$errorOccured=0;
foreach $line (@{$all_data[22]}) {
&html_error($line);
if($line =~ /\/comics/){
$line =~ s/\.jpg\".*/\.jpg\"\>/i;
$line =~ s/src\=\"/src\=\"http\:\/\/www\.ctrlaltdel\-online\.com/i;
$line =~ s/\<img/\<img align\=\"left\" border\=\"0\"/i;
print NEW " <A STYLE=\"text-decoration:none\" href=\"http://www.ctrlaltdel-online.com/\">";
print NEW $line;
print NEW "</A>\n";
}
}
print NEW " </P>\n";
#END CTRL+ALT+DEL URL PARSER
print NEW "\n\n";
}#comicsoff if statement.
#
########################################
#Reuters Top Images
print NEW "\n <!-------- News Images from Reuters-------------->\n";
print NEW "<tr><td width=\"240\">\n<br clear=\"all\">\n";
&html_border();
print NEW "<A STYLE=\"text-decoration:none\"";
print NEW "href=\"http://www.reuters.com/newsPhotoGallery.jhtml?type=topNews\">";
print NEW "<FONT size=\"5\" color=\"orange\"><b>Reuters News</b></FONT></A><BR>\n";
&end_border();
print NEW " <P>\n";
$valid_data=0;
$errorOccured=0;
foreach $line (@{$all_data[19]}) {
&html_error($line);
if($line =~ /smPicBorder/){
$line =~ s/class\=\".*?\"//gi;
$line =~ s/onMouseOver\=\".*?\"//gi;
$line =~ s/onMouseOut\=\".*?\"//gi;
$line =~ s/javascript\:commonPopup\(\'/http\:\/\/www\.reuters\.com\//i;
$line =~ s/\'.*?\>/\"\>/;
$line =~ s/align\=\"\"/align\=\"left\"/i;
print NEW "\t$line\n";
}
if($line =~ /\<\/b\>\<br\>/){
$line =~ s/^\s+//;
print NEW "\t<small><small>$line</small></small>\n";
}
}
print NEW "<\p>\n";
print NEW "</td></tr>\n\n";
print NEW " </TD>\n </TR></TABLE>\n";
&print_error( "\n\nFinished. Closing $Output_file with the results.\n");
print NEW " </TD>\n </TR>\n</Table>\n";
########################################
#QOTD SECTION
#create row for qotd
print NEW "\n\n<!-------- Quote of the Day SECTION -------------->\n";
print NEW "<div id=\"qotd\" background=\"#555555\" style=\"visibility:hidden; position:absolute; left:270;\">\n";
print NEW "\t<TABLE border=\"0\" width=\"356\"><tr><td bgcolor=\"#999999\">\n";
print NEW "\t<TABLE border=\"0\" width=\"350\"><tr><td bgcolor=\"#eeeeee\" align=\"center\">\n";
print NEW "\t <font size=\"3\"><b>Quote of the Day</b></font><br>\n";
#QOTD
$data_flag=0;
foreach $line (@{$all_data[13]}) {
if($line =~ /\(Internal Server Error\)/ ){
print NEW "\t <small> $line </small>\n";
}
if ($data_flag==1){
$line =~ s/\<A.*?\<\/A\>//;
print NEW "\t <small>\n\t <a href=\"$url[13]\" style=\"text-decoration:none\"><font color=\"black\">";
print NEW $line;
print NEW "</a></font>\n\t </small>\n";
$data_flag=0;
}
if($line=~/randomly selected quote/){
$data_flag=1;
}
}
&end_border();
print NEW "</div>\n";
#END QOTD SECTION
########################################
#Upcoming Events SECTION
print NEW "\n\n<!-------- EVENTS SECTION -------------->\n\n";
print NEW "<div id=\"UpcomingEvents\" background=\"white\" style=\"visibility:hidden; position:absolute; top:100; left:30;\">\n";
&html_border();
#events table
print NEW "<table><tr>\n";
print NEW "\n\n<!-------- Mondavi Arts Center -------------->\n";
print NEW "<td align=\"left\" valign=\"top\" width=\"30%\">\n";
#MONDAVI ARTS CENTER
print NEW "<small><b>Mondavi Center</b><br>\n";
$errorOccured=0;
$data_flag=0; $more_info=0;
foreach $line (@{$all_data[14]}) {
$line_counter++;
&html_error($line);
#look for good data indicator:
#if($line=~/Begin lasso content/){
if($line=~/Featured Events\"/){
$data_flag=1;
#remove everything before our indiciator.
$line =~ s/.*?\<img.*?Featured Event\"/\<img Featured Events\"/;
#print NEW "\n<!--\n$line_counter:$line\n-->\n";
#data is all one line for some reason.
@lasso_data = split(/\<\/a>/,$line);
foreach $line2 (@lasso_data) {
if (($data_flag==1) || ($more_info==1)){
if (($line2=~/announcements\.gif/) || ($line2 =~ /Post-Performance/)){
$data_flag=0;
}
if ($line2=~/membership\//) {
$more_info=0;
}
if ($line2 =~ /blackcopysmall/) {
$more_info=1;
}
if (($data_flag==1) && ($line2 =~ /whitelink2/)){
$line2 =~ s/\<\!\-\-.*?\-\-\>//g;
$line2 =~ s/\&.*?\;//g;
$line2 =~ s/\<\/?td.*?\>//g;
$line2 =~ s/\<\/?tr.*?\>//g;
$line2 =~ s/\<\/?span.*?\>//g;
$line2 =~ s/\<\/?blockquote.*?\>//g;
$line2 =~ s/\<\/?br.*?\>//g;
$line2 =~ s/\<\/?p.*?\>//g;
$line2 =~ s/\<\/?img.*?\>//g;
$line2 =~ s/\<\/?div.*?\>//g; #########
$line2 =~ s/\<\/?table.*?\>//g;
$line2 =~ s/\<a href\=\"/\<a href\=\"http\:\/\/www\.mondaviarts\.org\//;
$line2 =~ s/\s+/ /g;
$line2 =~ s/^\s+//;
print NEW "$line2</a><br> ";
}
elsif (($data_flag==1) || ($more_info==1)){
$line2 =~ s/\<\!\-\-.*?\-\-\>//g;
#get rid of extra <a link
$line2 =~ s/\<\/?a.*?\>//g;
$line2 =~ s/\&.*?\;//g;
$line2 =~ s/\<\/?td.*?\>//g;
$line2 =~ s/\<\/?blockquote.*?\>//g;
$line2 =~ s/\<\/?br.*?\>//g;
$line2 =~ s/\<\/?p.*?\>//g;
$line2 =~ s/\<\/?tr.*?\>//g;
$line2 =~ s/\<\/?td.*?\>//g;
$line2 =~ s/\<\/?span.*?\>//g;
$line2 =~ s/\<\/?img.*?\>//g;
$line2 =~ s/\<\/?div.*?\>//g; #########
$line2 =~ s/\<\/?table.*?\>//g;
$line2 =~ s/\s+/ /g;
$line2 =~ s/Post-Performance.*//;
if ($line2 =~ /[a-zA-Z<]/) {
print NEW "$line2<BR>\n";
}
}
}
}
}
}
print NEW "</small>\n";
#end mondavi column
print NEW "</td>\n";
#UC Berkley
print NEW "\n\n<!-------- UC Berkley -------------->\n";
print NEW "<td align=\"left\" valign=\"top\" width=\"30%\">\n";
print NEW "<small><b>UC Berkley</b><br>\n";
$errorOccured=0; $limit=34;
$pre_data_flag = 0; $data_flag=0; $a_tag_start=0;
foreach $line (@{$all_data[15]}) {
&html_error($line);
if ($line =~ /\#top/) {
#get rid of everything after #top
$line =~ s/\#top.*/\#top/;
$data_flag=0;
$pre_data_flag=0;
}
if ($line =~ /Events this week/) {
$pre_data_flag=1;
#print NEW "--$line--\n";
}
if (($pre_data_flag==1) && ($line =~ /\<\/tr\>/)) {
$data_flag=1;
}
if (($data_flag==1) && ($limit > 0)){
$line =~ s/\<\/?td.*?\>//g;
$line =~ s/\<\/?img.*?\>//g;
$line =~ s/\<\/?tr.*?\>//g;
$line =~ s/\<\/?table.*?\>//g;
$line =~ s/\s+/ /g;
$line =~ s/^\s+//g;
$line =~ s/\<\/a\>/\<\/a\>\<br\>\n/g;
$line =~ s/\<a href\=\"\#/\<a href\=\"http\:\/\/www\.berkeley\.edu\/calendar\/\#/;
print NEW "$line";
$limit--;
}
}
print NEW "</small>\n";
print NEW "</td>\n";
#end Berkely column
#EPICKS
print NEW "\n\n<!-------- SF E-Picks -------------->\n";
print NEW "<td align=\"left\" valign=\"top\" width=\"30%\">\n";
print NEW "<small><b>SF Gate</b><br>\n";
$errorOccured=0;
$data_flag=0;
foreach $line (@{$all_data[16]}) {
&html_error($line);
if ($line =~ /Movies:/) {
$data_flag=1;
}
if ($line =~ /\TABLE/) {
$data_flag=0;
}
if ($data_flag==1){
$line =~ s/\<\/?TD.*?\>//g;
$line =~ s/\<\/?TR.*?\>//g;
$line =~ s/\<\/?FONT.*?\>//g;
$line =~ s/\<\/?P.*?\>//g;
$line =~ s/HREF\=\"\#/href\=\"http\:\/\/sfgate\.com\/eguide\/epicks\/\#/;
$line =~ s/^\s+//g;
if ($line =~ /\S+/) {
print NEW "$line\n";
}
}
}
print NEW "</small>\n";
print NEW "</td>\n";
#EPICKS
print NEW " </tr>\n";
print NEW "</table>\n";
&end_border();
print NEW "</div>\n\n";
#END Events SECTION
print NEW " </TD></TR>\n";
########################################
#COPYRIGHT WARNING
print NEW "\n<p>\n <center>\n <small>\n";
print NEW " <!----COPYRIGHT WARNING---->\n <b>COPYRIGHT WARNING</b><br>\n";
print NEW " Webpage content is owned by corresponding webpage owner,";
print NEW " see individual pages for details.\n";
print NEW " </small>\n </center>\n</p>\n\n";
print NEW "</BODY>\n</HTML>\n";
print NEW "<!--END OF FILE-->\n";
close(NEW);
if($logfiles){
close(LOGFILE);
}
##########################################
#FUNCTIONS
sub print_error{
$toPrint = $_[0];
if ($logfiles){
print LOGFILE $toPrint;
print $toPrint;
}
}
sub shorten_line{
$long_string = $_[0];
#look for too many uppercase letters
if ($long_string =~ /[A-Z].*?[A-Z].*?[A-Z].*?[A-Z].*?[A-Z].*?[A-Z].*?[A-Z]/) {
$column_temp=$column_width;
}
else{
#set full length of string.
$column_temp=$column_width+3;
}
if ($long_string =~ /\>([^<]{$column_temp,})/ ) {
# if ($long_string =~ /\>(.){$column_temp,})?\<\/a\>/ ) { #will crash script
$temp_1a = $1;
$line2 = substr($temp_1a,0,$column_temp-3);
$line2 = $line2."...";
#remove quotes and insert ascii for quote
$line2 =~ s/\"/\"\;/g;
$temp_1a =~ s/\"/\"\;/g;
$long_string =~ s/\<a/\<a title\=\"$temp_1a\"/;
$long_string =~ s/\>([^<]*)/\>$line2/;
}
return $long_string;
}
sub html_border{
print NEW "\n\t<!--BORDER-2 START-->\n";
print NEW "\t<TABLE border=\"0\" width=\"100%\"><tr><td bgcolor=\"#999999\">\n";
print NEW "\t<TABLE border=\"0\" width=\"100%\"><tr><td bgcolor=\"#eeeeee\" align=\"center\">\n";
print NEW "\t<!--BORDER-2 START-->\n\n";
}
sub end_border{
print NEW "\n\t<!--BORDER-2 END-->\n";
print NEW "\t</td></tr></table>\n";
print NEW "\t</td></tr></table>\n";
print NEW "\t<!--BORDER-2 END-->\n\n";
}
sub html_error{
$error_line = $_[0];
#handle failed html lookups
if( ($error_line =~ /\(Internal Server Error\)/) || ($errorOccured>0 && $errorOccured<3)){
print NEW $error_line;
$errorOccured++;
}
}
#EOF#
###############OLD CNN NEWS SECTION ##############
print NEW "\n\n<!-------- CNN NEWS SECTION -------------->\n";
&html_border();
print NEW "<A STYLE=\"text-decoration:none\" href=\"$url[11]\"><FONT size=\"5\" color=\"red\"><b>CNN News</b></FONT></A><BR>\n";
&end_border();
$errorOccured=0;
foreach $line (@{$all_data[11]}) {
&html_error($line);
#get rid of <td> tags
$line =~ s/\<td.*?\>//g;
#get categories
if( ($line=~ /cnnMainSections/) && (
($line =~ /Education/) || ($line =~ /World/) ||
($line =~ /U\.S/) || ($line =~ /Business/) ||
($line =~ /Scien/) || ($line =~ /Sports/) ||
($line =~ /Entert/) || ($line =~ /Health/) ||
($line =~ /Travel/) || ($line =~ /Asia/) ||
($line =~ /Europe/) || ($line =~ /Technol/)
) ){
$line =~ s/<div.*?\>//g;
#get name of section
$line =~ s/.*?\"\s+alt\=\"/\<b\>/;
$line =~ s/\s*\w+\:\s*\".*/\<\/b\>/;
#dont print </small> first time
if($headline_limit >= 1){
print NEW "</small>\n";
}
print NEW $line, "<BR>\n";
print NEW "<small>\n";
$headline_limit = $Number_of_headlines + 1;
}
#get headlines and put into file
if( (($line =~ /\&\#8226\;\&/) || ($line =~ /\&\#149\;\&/)) && ($headline_limit > 1) && !($line=~ /target\=\"new\"/) ){
#$line =~ s/\<.*?\>//; #removes html
$line =~ s/<img.*?\>//g;
$line =~ s/<br.*?\>//g;
$line =~ s/<span.*?\/span\>//g;
$line =~ s/<div.*?\>//g;
$line =~ s/\&.*?\;//g;
#add <br> tags after link
$line =~ s/\/a\>/\/a\>\<br\>\n/g;
#add cnn.com to links
$line =~ s/\<a href\=\"/\<a href\=\"http\:\/\/www\.cnn\.com/g;
#shorten links that are too long
$line = &shorten_line($line);
#remove leading whitespace
$line =~ s/^\s+//;
print NEW $line;
&print_error( $line);
$headline_limit--;
}
}
############### END CNN SECTION ############### |