Annotation of comics/fetch.pl.new, revision 1.10
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: ##
1.10 ! nick 12: my $ver = q/$Id: fetch.pl.new,v 1.9 2013-02-25 13:48:21 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 ($$) {
118: my ( $comics, $comic, $date ) = @_;
1.9 nick 119: my $indexFile = $indexDir . "/index-" . $days[$date->{'dow'}] .
120: "-" . $date->{'year2'} . $date->{'mon2'} .
1.1 nick 121: $date->{'day2'} . ".html";
122: my $content = <<EOF;
123:
124: <!-- ********* Begin $comic ($comics->{$comic}{'fullName'}) ******* -->
125: <tr>
126: <td align="left">
127: <font color="blue"><b>$comics->{$comic}{'fullName'}</b></font>
128: <font size="-2">
129: <a href="$comics->{$comic}{'url'}">
130: $comics->{$comic}{'url'}
131: </a>
132: </font><br/>
133: <img src="../images/$date->{'mon2'}$date->{'year2'}/$comic-$date->{'day2'}.jpg" alt="$comic-$date->{'day2'}" />
134: <br/><br/>
135: </td></tr>
136: <!-- ********* Finish $comic ($comics->{$comic}{'fullName'}) ******* -->
137:
138: EOF
139: open INDEX, ">>$indexFile";
140:
141: print INDEX $content if ( ! $comics->{$comic}{'error'} );
142:
143: print INDEX <<EOF
144: <font color="blue"><b>$comics->{$comic}{'fullName'}</b></font>
145: <font size="-2"><
146: <a href="$comics->{$comic}{'url'}">
147: $comics->{$comic}{'url'}
148: </a>
149: </font><br/>
150: <font color="red"><b>$comic : $comics->{$comic}{'error'}</b></font><br/>
151: </td>
152: </tr>
153: EOF
154: if ( $comics->{$comic}{'error'} );
155:
156: close (INDEX);
157:
158: return 0;
159: }
160:
161:
162: #######################################################################
163: #######################################################################
164: sub writeMainIndex ($$) {
165: my ( $date ) = @_;
166:
167: }
168:
169:
170: #######################################################################
171: #######################################################################
172: sub writeFooter {
173: my ( $date ) = @_;
1.10 ! nick 174: my $indexFile = $indexDir . "/index-" . $days[$date->{'dow'}] .
! 175: "-" . $date->{'year2'} . $date->{'mon2'} .
1.1 nick 176: $date->{'day2'} . ".html";
177: my $sysDate = `date`;
178:
179: open INDEX, ">>$indexFile";
180: print INDEX <<EOF;
181: </table>
1.3 nick 182: <center>
183: <font size="2">
184: Generated on: <font color="green">$sysDate</font><br/>
1.7 nick 185: Version: <font color="green">$ver</font><br />
186: CVS: <a href="http://demandred.dyndns.org/cgi-bin/cvsweb/comics/">http://demandred.dyndns.org/cgi-bin/cvsweb/comics/</a>
1.1 nick 187: <p>
188: <a href="http://validator.w3.org/check?uri=referer"><img
189: src="http://www.w3.org/Icons/valid-xhtml10-blue" alt="Valid XHTML 1.0 Transitional" height="31" width="88" border="0" /></a>
190: </p>
191: </center>
192:
193: </body>
194: </html>
195: EOF
196: close( INDEX );
197: }
198:
199: #######################################################################
200: #######################################################################
201: sub checkDir ($$) {
202: my @dir = @_;
203:
204: foreach ( @dir ) {
205: if ( ! -d $_ ) { mkpath( $_ ); }
206: }
207: }
208:
209: #######################################################################
210: #######################################################################
211: sub writeTitle ($$) {
212: my ( $date ) = @_;
1.10 ! nick 213: my $indexFile = $indexDir . "/index-" . $days[$date->{'dow'}] .
! 214: "-" . $date->{'year2'} . $date->{'mon2'} .
1.1 nick 215: $date->{'day2'} . ".html";
1.8 nick 216: my $today = $days[$date->{'dow'}] . " " . $date->{'mon'} . "/" . $date->{'day'} . "/" . $date->{'year'};
1.1 nick 217:
218: open INDEX, ">$indexFile";
219: print INDEX <<EOF;
220: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
221:
222: <html xmlns="http://www.w3.org/1999/xhtml">
223: <head>
224: <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
225: <title>Daily Comics for $today</title>
226: </head>
227: <body bgcolor="#FFFFFF">
228: <h1>Daily Comics for $today</h1>
229: <table align="center" cellpadding="5" cellspacing="0">
230: EOF
231: close (INDEX);
232: }
233:
234: #######################################################################
235: #######################################################################
236: sub directDownload ($$) {
237: my ( $comics, $comic, $date ) = @_;
238: my $file = &parseComic ( $comics, $comic, $date );
239:
240: ##
241: ## Save the file to the appropriate directory
242: ##
243: my $cDir = $date->{'mon2'} . $date->{'year2'};
244: my $cDate = $date->{'day2'};
245:
1.3 nick 246: my $cmd = "wget -q $file --referer=\"" . $comics->{$comic}{'url'} ."\" --user-agent=\"$USER_AGENT\" -O - | /usr/bin/convert - jpeg:images/$cDir/$comic-$cDate.jpg";
1.1 nick 247: return system($cmd);
248: }
249:
250: #######################################################################
251: #######################################################################
252: sub indexDownload ($$) {
253: my ( $comics, $comic, $date ) = @_;
254: my ( @lines, $comicLine, $mainURL );
255: my $comicIndex = "indexes/index.$comic";
256:
257: `wget -q $comics->{$comic}{'url'} -O $comicIndex`;
258:
259: if ( ! open FILEN, "<$comicIndex" ) {
260: return "ERROR: Can't open index file for " . $comics->{$comic}{'fullName'} .
261: " (" . $comics->{$comic}{'url'} . ")";
262: }
263: @lines = <FILEN>;
264: close (FILEN);
265:
266: unlink ("$comicIndex");
267:
268: $mainURL = $comics->{$comic}{'url'};
269: ## I need to figure out how to merge these two in to one regex.
270: $mainURL =~ s/(http:\/\/.*)(?:\/.*\/){1,}.*/$1/;
271: $mainURL =~ s/([a-z])\/.*/$1/i;
272:
273: ##
274: ## Find the comic strip URL based on the specified regex in the search
275: ##
276: foreach my $line (@lines) {
277: if ( $line =~ m/$comics->{$comic}{'search'}/ ) {
278: $comicLine = $1; chomp $comicLine;
279: }
280: }
281:
282: ##
283: ## Save the file to the appropriate directory
284: ##
285: my $cDir = $date->{'mon2'} . $date->{'year2'};
286: my $cDate = $date->{'day2'};
287:
288: if ( $comicLine ) {
289: if ( $comicLine =~ m/(gif|jpg|png)/i ) { $comics->{$comic}{'ext'} = $1; }
290: my $comicURL = ( $comicLine =~ m/http/ ) ? $comicLine : $mainURL . $comicLine;
1.3 nick 291: 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 292: system( $cmd );
293: return 0;
294: }
295:
296: unlink "index.html";
297:
298: return "ERROR: Could not download comic $comics->{$comic}{'fullName'}";
299: }
300:
301: #######################################################################
302: #######################################################################
303: sub parseComic ($$) {
304: my ( $comics, $comic, $date ) = @_;
305: my $string = $comics->{$comic}{'search'};
306:
307: $string =~ s/__year__/$date->{'year'}/g;
308: $string =~ s/__year2__/$date->{'year2'}/g;
309: $string =~ s/__mon__/$date->{'mon'}/g;
310: $string =~ s/__mon2__/$date->{'mon2'}/g;
311: $string =~ s/__day__/$date->{'day'}/g;
312: $string =~ s/__day2__/$date->{'day2'}/g;
313: $string =~ s/__ext__/$comics->{$comic}{'ext'}/g;
314: chomp $string;
315:
316: return $string;
317: }
318:
319: #######################################################################
320: #######################################################################
321: sub fetchDates () {
322: my %dates = ();
323:
1.8 nick 324: ($dates{'day'}, $dates{'mon'}, $dates{'year'}, $dates{'dow'}) = (localtime(time - (86400 * $days_ago )))[3,4,5,6];
1.1 nick 325:
326: $dates{'year'} += 1900;
327: $dates{'year2'} = substr $dates{'year'}, 2, 2;
328: $dates{'day2'} = ( $dates{'day'} < 10 ) ? "0" . $dates{'day'} : $dates{'day'};
329: $dates{'mon'}++;
330: $dates{'mon2'} = ( $dates{'mon'} < 10 ) ? "0".$dates{'mon'} : $dates{'mon'};
331:
332: return %dates;
333: }
1.8 nick 334:
335: ###############################################################################
336: ##
337: ## &fetchOptions( );
338: ##
339: ## Grab our command line arguments and toss them in to a hash
340: ##
341: ###############################################################################
342: sub fetchOptions {
343: my %opts;
344:
345: &GetOptions(
346: "days:i" => \$opts{'days'},
347: "help|?" => \$opts{'help'},
348: "man" => \$opts{'man'},
349: ) || &pod2usage( );
350: &pod2usage( ) if defined $opts{'help'};
351: &pod2usage( { -verbose => 2, -input => \*DATA } ) if defined $opts{'man'};
352:
353: return %opts;
354: }
355:
356: __END__
357:
358: =head1 NAME
359:
360: fetch.pl - Fetches comics and places them all locally in a single html file.
361:
362: =head1 SYNOPSIS
363:
364: fetch.pl [options]
365:
366: Options:
367: --days,d Fetch comics from X days ago
368: --help,? Display the basic help menu
369: --man,m Display the detailed man page
370:
371: =head1 DESCRIPTION
372:
373: =head1 HISTORY
374:
375: =head1 AUTHOR
376:
377: Nicholas DeClario <nick@declario.com>
378:
379: =head1 BUGS
380:
381: This is a work in progress. Please report all bugs to the author.
382:
383: =head1 SEE ALSO
384:
385: =head1 COPYRIGHT
386:
387: =cut
388:
389:
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