Annotation of comics/fetch.pl.new, revision 1.8
1.1 nick 1: #!/usr/bin/perl -w
2:
3: use strict;
4: use File::Path;
5: use Data::Dumper;
1.8 ! nick 6: use Pod::Usage;
! 7: use Getopt::Long;
1.1 nick 8:
9: ##
10: ## Some default values
11: ##
1.8 ! nick 12: my $ver = q/$Id: fetch.pl.new,v 1.7 2013-01-10 14:25:57 nick Exp $/;
1.1 nick 13: my $comicFile = "comics.conf";
14: my %comics = &readComicConfig ( $comicFile );
1.8 ! nick 15: my %opts = &fetchOptions( );
! 16: my $days_ago = $opts{'days'} || 0;
1.1 nick 17: my %dates = &fetchDates();
18: my $baseDir = $comics{'configs'}{'base_directory'} || ".";
19: my $imageDir = $baseDir . "/" . ( $comics{'configs'}{'image_directory'} || "images" ) .
20: "/$dates{'mon2'}$dates{'year2'}";
21: my $indexDir = $baseDir . "/" . ( $comics{'configs'}{'index_directory'} || "indexes" );
1.2 nick 22: my $USER_AGENT = "Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.18) Gecko/20110628 Ubuntu/10.10 (maverick) Firefox/3.6.18";
1.8 ! nick 23: my @days = qw/ Sunday Monday Tuesday Wednesday Thursday Friday Saturday /;
1.1 nick 24:
25:
26: my $DATE=`date`; chomp $DATE;
27: print STDOUT "Starting comic fetch at $DATE\n";
28:
29: ##
30: ## Main program starts here
31: ##
32: &checkDir ( [ $imageDir, $indexDir ] );
33:
1.5 nick 34: &writeTitle ( \%dates );
1.1 nick 35:
36: foreach my $comic ( sort keys %comics ) {
37: next if ( $comic =~ m/config/ );
38: $comics{$comic}{'error'} = &downloadComic ( \%comics, $comic, \%dates );
39: &writeComic ( \%comics, $comic, \%dates );
40: }
41:
1.8 ! nick 42: print "Finding in $imageDir/*-$dates{'day2'}.jpg\n";
! 43: foreach my $file ( glob( "$imageDir/*-$dates{'day2'}.jpg" ) )
1.4 nick 44: {
45: my $size = `/usr/bin/identify $file`;
46: $size =~ s/.*\s(\d+)x\d+.*/$1/;
47:
48: system( "/usr/bin/convert -resize 640 $file $file" )
49: if ( $size > 640 )
50: }
51:
1.1 nick 52: ## &writeMainIndex ( \%dates );
53:
54: &writeFooter( \%dates );
55:
56: $DATE=`date`; chomp( $DATE );
57: print STDOUT "Completed comic fetch at $DATE\n";
58:
59: ## End
60:
61: #######################################################################
62: ## Function : downloadComic
63: ##
64: ## Description :
65: ## This function determines the download method being used to
66: ## retrieve the comic and calls the apprioriate function.
67: ##
68: ## If the mode is invalid an error will be returned.
69: ##
70: #######################################################################
71: sub downloadComic ($$) {
72: my ( $comics, $comic, $date ) = @_;
73:
74: SWITCH: {
75: if ( $comics->{$comic}{'mode'} eq 1 ) {
76: return indexDownload ( \%comics, $comic, $date );
77: last SWITCH;
78: }
79: if ( $comics->{$comic}{'mode'} eq 2 ) {
80: return directDownload ( \%comics, $comic, $date );
81: last SWITCH;
82: }
83: }
84:
85: return "ERROR: Unknown download method specified for $comics->{$comic}{'fullName'}.";
86: }
87:
88: #######################################################################
89: #######################################################################
90: sub readComicConfig ($$) {
91: my ( $comicFile ) = @_;
92: my %comicConfig = ( );
93: my %config = ( );
94:
95: open FILEN, "<$comicFile";
96: while (<FILEN>) {
97: if ( ( $_ !~ m/^#/ ) && ( $_ =~ m/,.*,/) ){
98: my @res = split /,/, $_;
99: $comicConfig{$res[0]}{'url'} = $res[1];
100: $comicConfig{$res[0]}{'search'} = $res[2];
101: $comicConfig{$res[0]}{'mode'} = $res[3];
102: $comicConfig{$res[0]}{'fullName'} = $res[4];
103: $comicConfig{$res[0]}{'ext'} = $res[5];
104: $comicConfig{$res[0]}{'error'} = 0;
105: }
106: elsif ( $_ =~ m/(.*)\s+=\s+(.*)/ ) {
107: $comicConfig{'configs'}{$1} = $2;
108: }
109: }
110: close (FILEN);
111:
112: return %comicConfig;
113: }
114:
115: #######################################################################
116: #######################################################################
117: sub writeComic ($$) {
118: my ( $comics, $comic, $date ) = @_;
119: my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} .
120: $date->{'day2'} . ".html";
121: my $content = <<EOF;
122:
123: <!-- ********* Begin $comic ($comics->{$comic}{'fullName'}) ******* -->
124: <tr>
125: <td align="left">
126: <font color="blue"><b>$comics->{$comic}{'fullName'}</b></font>
127: <font size="-2">
128: <a href="$comics->{$comic}{'url'}">
129: $comics->{$comic}{'url'}
130: </a>
131: </font><br/>
132: <img src="../images/$date->{'mon2'}$date->{'year2'}/$comic-$date->{'day2'}.jpg" alt="$comic-$date->{'day2'}" />
133: <br/><br/>
134: </td></tr>
135: <!-- ********* Finish $comic ($comics->{$comic}{'fullName'}) ******* -->
136:
137: EOF
138: open INDEX, ">>$indexFile";
139:
140: print INDEX $content if ( ! $comics->{$comic}{'error'} );
141:
142: print INDEX <<EOF
143: <font color="blue"><b>$comics->{$comic}{'fullName'}</b></font>
144: <font size="-2"><
145: <a href="$comics->{$comic}{'url'}">
146: $comics->{$comic}{'url'}
147: </a>
148: </font><br/>
149: <font color="red"><b>$comic : $comics->{$comic}{'error'}</b></font><br/>
150: </td>
151: </tr>
152: EOF
153: if ( $comics->{$comic}{'error'} );
154:
155: close (INDEX);
156:
157: return 0;
158: }
159:
160:
161: #######################################################################
162: #######################################################################
163: sub writeMainIndex ($$) {
164: my ( $date ) = @_;
165:
166: }
167:
168:
169: #######################################################################
170: #######################################################################
171: sub writeFooter {
172: my ( $date ) = @_;
173: my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} .
174: $date->{'day2'} . ".html";
175: my $sysDate = `date`;
176:
177: open INDEX, ">>$indexFile";
178: print INDEX <<EOF;
179: </table>
1.3 nick 180: <center>
181: <font size="2">
182: Generated on: <font color="green">$sysDate</font><br/>
1.7 nick 183: Version: <font color="green">$ver</font><br />
184: CVS: <a href="http://demandred.dyndns.org/cgi-bin/cvsweb/comics/">http://demandred.dyndns.org/cgi-bin/cvsweb/comics/</a>
1.1 nick 185: <p>
186: <a href="http://validator.w3.org/check?uri=referer"><img
187: src="http://www.w3.org/Icons/valid-xhtml10-blue" alt="Valid XHTML 1.0 Transitional" height="31" width="88" border="0" /></a>
188: </p>
189: </center>
190:
191: </body>
192: </html>
193: EOF
194: close( INDEX );
195: }
196:
197: #######################################################################
198: #######################################################################
199: sub checkDir ($$) {
200: my @dir = @_;
201:
202: foreach ( @dir ) {
203: if ( ! -d $_ ) { mkpath( $_ ); }
204: }
205: }
206:
207: #######################################################################
208: #######################################################################
209: sub writeTitle ($$) {
210: my ( $date ) = @_;
211: my $indexFile = $indexDir . "/index-" . $date->{'year2'} . $date->{'mon2'} .
212: $date->{'day2'} . ".html";
1.8 ! nick 213: my $today = $days[$date->{'dow'}] . " " . $date->{'mon'} . "/" . $date->{'day'} . "/" . $date->{'year'};
1.1 nick 214:
215: open INDEX, ">$indexFile";
216: print INDEX <<EOF;
217: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
218:
219: <html xmlns="http://www.w3.org/1999/xhtml">
220: <head>
221: <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
222: <title>Daily Comics for $today</title>
223: </head>
224: <body bgcolor="#FFFFFF">
225: <h1>Daily Comics for $today</h1>
226: <table align="center" cellpadding="5" cellspacing="0">
227: EOF
228: close (INDEX);
229: }
230:
231: #######################################################################
232: #######################################################################
233: sub directDownload ($$) {
234: my ( $comics, $comic, $date ) = @_;
235: my $file = &parseComic ( $comics, $comic, $date );
236:
237: ##
238: ## Save the file to the appropriate directory
239: ##
240: my $cDir = $date->{'mon2'} . $date->{'year2'};
241: my $cDate = $date->{'day2'};
242:
1.3 nick 243: my $cmd = "wget -q $file --referer=\"" . $comics->{$comic}{'url'} ."\" --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg";
1.1 nick 244: return system($cmd);
245: }
246:
247: #######################################################################
248: #######################################################################
249: sub indexDownload ($$) {
250: my ( $comics, $comic, $date ) = @_;
251: my ( @lines, $comicLine, $mainURL );
252: my $comicIndex = "indexes/index.$comic";
253:
254: `wget -q $comics->{$comic}{'url'} -O $comicIndex`;
255:
256: if ( ! open FILEN, "<$comicIndex" ) {
257: return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} .
258: " (" . $comics->{$comic}{'url'} . ")";
259: }
260: @lines = <FILEN>;
261: close (FILEN);
262:
263: unlink ("$comicIndex");
264:
265: $mainURL = $comics->{$comic}{'url'};
266: ## I need to figure out how to merge these two in to one regex.
267: $mainURL =~ s/(http:\/\/.*)(?:\/.*\/){1,}.*/$1/;
268: $mainURL =~ s/([a-z])\/.*/$1/i;
269:
270: ##
271: ## Find the comic strip URL based on the specified regex in the search
272: ##
273: foreach my $line (@lines) {
274: if ( $line =~ m/$comics->{$comic}{'search'}/ ) {
275: $comicLine = $1; chomp $comicLine;
276: }
277: }
278:
279: ##
280: ## Save the file to the appropriate directory
281: ##
282: my $cDir = $date->{'mon2'} . $date->{'year2'};
283: my $cDate = $date->{'day2'};
284:
285: if ( $comicLine ) {
286: if ( $comicLine =~ m/(gif|jpg|png)/i ) { $comics->{$comic}{'ext'} = $1; }
287: my $comicURL = ( $comicLine =~ m/http/ ) ? $comicLine : $mainURL . $comicLine;
1.3 nick 288: my $cmd = "wget --user-agent=\"$USER_AGENT\" --referer=\"" . $comics->{$comic}{'url'} . "\" -q $comicURL -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg";
1.1 nick 289: system( $cmd );
290: return 0;
291: }
292:
293: unlink "index.html";
294:
295: return "ERROR: Could not download comic $comics->{$comic}{'fullName'}";
296: }
297:
298: #######################################################################
299: #######################################################################
300: sub parseComic ($$) {
301: my ( $comics, $comic, $date ) = @_;
302: my $string = $comics->{$comic}{'search'};
303:
304: $string =~ s/__year__/$date->{'year'}/g;
305: $string =~ s/__year2__/$date->{'year2'}/g;
306: $string =~ s/__mon__/$date->{'mon'}/g;
307: $string =~ s/__mon2__/$date->{'mon2'}/g;
308: $string =~ s/__day__/$date->{'day'}/g;
309: $string =~ s/__day2__/$date->{'day2'}/g;
310: $string =~ s/__ext__/$comics->{$comic}{'ext'}/g;
311: chomp $string;
312:
313: return $string;
314: }
315:
316: #######################################################################
317: #######################################################################
318: sub fetchDates () {
319: my %dates = ();
320:
1.8 ! nick 321: ($dates{'day'}, $dates{'mon'}, $dates{'year'}, $dates{'dow'}) = (localtime(time - (86400 * $days_ago )))[3,4,5,6];
1.1 nick 322:
323: $dates{'year'} += 1900;
324: $dates{'year2'} = substr $dates{'year'}, 2, 2;
325: $dates{'day2'} = ( $dates{'day'} < 10 ) ? "0" . $dates{'day'} : $dates{'day'};
326: $dates{'mon'}++;
327: $dates{'mon2'} = ( $dates{'mon'} < 10 ) ? "0".$dates{'mon'} : $dates{'mon'};
328:
329: return %dates;
330: }
1.8 ! nick 331:
! 332: ###############################################################################
! 333: ##
! 334: ## &fetchOptions( );
! 335: ##
! 336: ## Grab our command line arguments and toss them in to a hash
! 337: ##
! 338: ###############################################################################
! 339: sub fetchOptions {
! 340: my %opts;
! 341:
! 342: &GetOptions(
! 343: "days:i" => \$opts{'days'},
! 344: "help|?" => \$opts{'help'},
! 345: "man" => \$opts{'man'},
! 346: ) || &pod2usage( );
! 347: &pod2usage( ) if defined $opts{'help'};
! 348: &pod2usage( { -verbose => 2, -input => \*DATA } ) if defined $opts{'man'};
! 349:
! 350: return %opts;
! 351: }
! 352:
! 353: __END__
! 354:
! 355: =head1 NAME
! 356:
! 357: fetch.pl - Fetches comics and places them all locally in a single html file.
! 358:
! 359: =head1 SYNOPSIS
! 360:
! 361: fetch.pl [options]
! 362:
! 363: Options:
! 364: --days,d Fetch comics from X days ago
! 365: --help,? Display the basic help menu
! 366: --man,m Display the detailed man page
! 367:
! 368: =head1 DESCRIPTION
! 369:
! 370: =head1 HISTORY
! 371:
! 372: =head1 AUTHOR
! 373:
! 374: Nicholas DeClario <nick@declario.com>
! 375:
! 376: =head1 BUGS
! 377:
! 378: This is a work in progress. Please report all bugs to the author.
! 379:
! 380: =head1 SEE ALSO
! 381:
! 382: =head1 COPYRIGHT
! 383:
! 384: =cut
! 385:
! 386:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvsweb/icons/back.gif){kind=icon}
Return to fetch.pl.new CVS log ![[TXT]](/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvsweb/icons/dir.gif){kind=icon}
Up to [Local Repository] / comics