summaryrefslogtreecommitdiff
path: root/perl/checklinks.pl.in
blob: 17032b36ac90b0146cabe8ee05c4da172912ccb8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
#!@PERL@
#
# checklinks.pl
#
# This script extracts all links from a HTML page and checks their validity.
# Written to use 'curl' for URL checking.
#
# Author: Daniel Stenberg <Daniel.Stenberg@sth.frontec.se>
# Version: 0.7 Sept 30, 1998
#
# HISTORY
#
# 0.5 - Cuts off the #-part from links before checking.
#
# 0.6 - Now deals with error codes 3XX better and follows the Location:
#       properly.
#     - Added the -x flag that only checks http:// -links
#
# 0.7 - Ok, http://www.viunga.se/main.html didn't realize this had no path
#       but a document. Now it does.
#
#

$in="";

 argv:
if($ARGV[0] eq "-v" ) {
    $verbose = 1;
    shift @ARGV;
    goto argv;
}
elsif($ARGV[0] eq "-i" ) {
    $usestdin = 1;
    shift @ARGV;
    goto argv;
}
elsif($ARGV[0] eq "-l" ) {
    $linenumber = 1;
    shift @ARGV;
    goto argv;
}
elsif($ARGV[0] eq "-h" ) {
    $help = 1;
    shift @ARGV;
    goto argv;
}
elsif($ARGV[0] eq "-x" ) {
    $external = 1;
    shift @ARGV;
    goto argv;
}

$geturl = $ARGV[0];

if(($geturl eq "") || $help) {
    print  "Usage: $0 [-hilvx] <full URL>\n",
    " Use a traling slash for directory URLs!\n",
    " -h  This help text\n",
    " -i  Read the initial page from stdin\n",
    " -l  Line number report for BAD links\n",
    " -v  Verbose mode\n",
    " -x  Check non-local (external?) links only\n";
    exit;
}

if($ARGV[1] eq "-") {
    print "We use stdin!\n";
    $usestdin = 1;
}

# This is necessary from where I tried this:
#$proxy =" -x 194.237.142.41:80";

# linkchecker, URL will be appended to the right of this command line
# this is the one using HEAD:
$linkcheck = "curl -s -m 20 -I$proxy";

# as a second attempt, this will be used. This is not using HEAD but will
# get the whole frigging document!
$linkcheckfull = "curl -s -m 20 -i$proxy";

# htmlget, URL will be appended to the right of this command line
$htmlget = "curl -s$proxy";

# Parse the input URL and split it into the relevant parts:

sub SplitURL {
    my $inurl = $_[0];

    if($inurl=~ /^([^:]+):\/\/([^\/]*)\/(.*)\/(.*)/ ) {
	$getprotocol = $1;
	$getserver = $2;
	$getpath = $3;
	$getdocument = $4;
    }
    elsif ($inurl=~ /^([^:]+):\/\/([^\/]*)\/(.*)/ ) {
	$getprotocol = $1;
	$getserver = $2;
	$getpath = $3;
	$getdocument = "";
	
	if($getpath !~ /\//) {
	    $getpath ="";
	    $getdocument = $3;
	}
    
    }
    elsif ($inurl=~ /^([^:]+):\/\/(.*)/ ) {
	$getprotocol = $1;
	$getserver = $2;
	$getpath = "";
	$getdocument = "";
    }
    else {
	print "Couldn't parse the specified URL, retry please!\n";
	exit;
    }
}

&SplitURL($geturl);

#print "protocol = $getprotocol\n";
#print "server = $getserver\n";
#print "path = $getpath\n";
#print "document = $getdocument\n";
#exit;

if(!$usestdin) {
    open(HEADGET, "$linkcheck $geturl|") ||
	die "Couldn't get web page for some reason";
  headget:
    while(<HEADGET>) {
#	print $_;
	if($_ =~ /HTTP\/.*3\d\d /) {
	    $pagemoved=1;
	}
	elsif($pagemoved &&
	       ($_ =~ /^Location: (.*)/)) {
	    $geturl = $1;

	    &SplitURL($geturl);

	    $pagemoved++;
	    last headget;
	}
    }
    close(HEADGET);

    if($pagemoved == 1) {
	print "Page is moved but we don't know where. Did you forget the ",
	"traling slash?\n";
	exit;
    }

    open(WEBGET, "$htmlget $geturl|") ||
	die "Couldn't get web page for some reason";

    while(<WEBGET>) {
	$line = $_;
	push @indoc, $line;
	$line=~ s/\n//g;
	$line=~ s/\r//g;
#    print $line."\n";
	$in=$in.$line;
    }

    close(WEBGET);
}
else {
    while(<STDIN>) {
	$line = $_;
	push @indoc, $line;
	$line=~ s/\n//g;
	$line=~ s/\r//g;
	$in=$in.$line;
    }
}

#print length($in)."\n";

sub LinkWorks {
    my $check = $_[0];

#   URL encode:
#    $check =~s/([^a-zA-Z0-9_:\/.-])/uc sprintf("%%%02x",ord($1))/eg;

    @doc = `$linkcheck \"$check\"`;

    $head = 1;

#    print "COMMAND: $linkcheck \"$check\"\n";
#    print $doc[0]."\n";

  boo:
    if( $doc[0] =~ /^HTTP[^ ]+ (\d+)/ ) {
	$error = $1;

	if($error < 400 ) {
	    return "GOOD";
	}
	else {
	    
	    if($head && ($error >= 500)) {
		# This server doesn't like HEAD!
		@doc = `$linkcheckfull \"$check\"`;
		$head = 0;
		goto boo;
	    }
	    return "BAD";
	}
    }
    return "BAD";
}


sub GetLinks {
    my $in = $_[0];
    my @result;

  getlinkloop:
    while($in =~ /[^<]*(<[^>]+>)/g ) {
	# we have a tag in $1
	$tag = $1;
	
	if($tag =~ /^<!--/) {
	    # this is a comment tag, ignore it 
	}
	else {
	    if($tag =~ /(src|href|background|archive) *= *(\"[^\"]\"|[^ )>]*)/i) {
   	        $url=$2;
		if($url =~ /^\"(.*)\"$/) {
		    # this was a "string" now $1 has removed the quotes:
		    $url=$1;
		}


		$url =~ s/([^\#]*)\#.*/$1/g;

		if($url eq "") {
		    # if the link was nothing than a #-link it may now have
		    # been emptied completely so then we skip the rest
		    next getlinkloop;		    
		}

		if($done{$url}) {
		    # if this url already is done, do next
		    $done{$url}++;
		    next getlinkloop;
		}

		$done{$url} = 1; # this is "done"

	        push @result, $url;
		if($tag =~ /< *([^ ]+)/) {
#		    print "TAG: $1\n";
		    $tagtype{$url}=$1;
		}
	    }
        }
    }
    return @result;
}

@links = &GetLinks($in);

 linkloop:
for(@links) {
    $url = $_;

    if($url =~ /^([^:]+):/) {
	$prot = $1;
#	if($prot !~ /(http|ftp|gopher)/i) {
	if($prot !~ /http/i) {
	    # this is an unsupported protocol, we ignore this
	    next linkloop;
	}
	$link = $url;
    }
    else {
	if($external) {
	    next linkloop;
	}

	# this is a link on the save server:
	if($url =~ /^\//) {
	    # from root
	    $link = "$getprotocol://$getserver$url";
	}
	else {
	    # from the scanned page's dir
	    $nyurl=$url;

	    if(length($getpath) &&
	       ($getpath !~ /\/$/) &&
	       ($nyurl !~ /^\//)) {
		# lacks ending slash, add one to the document part:
		$nyurl = "/".$nyurl;
	    }
	    $link = "$getprotocol://$getserver/$getpath$nyurl";
	}
    }

#print "test $link\n";
#$success = "GOOD";

    $success = &LinkWorks($link);

    $count = $done{$url};

    $allcount += $count;

    print "$success $count <".$tagtype{$url}."> $link $url\n";

# If bad and -l, present the line numbers of the usage
    if("BAD" eq $success) {
	$badlinks++;
	if($linenumber) {
	    $line =1;
	    for(@indoc) {
		if($_ =~ /$url/) {
		    print " line $line\n";
		}
		$line++;
	    }
	}
    }

}

if($verbose) {
    print "$allcount links were checked";
    if($badlinks > 0) {
	print ", $badlinks were found bad";
    }
    print "\n";
}