aboutsummaryrefslogtreecommitdiff
path: root/perl/contrib/getlinks.pl.in
blob: 7253f1e7b63196241d08330e3b0c2a3cdaa40ec8 (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
#!@PERL@
#
# getlinks.pl
#
# This script extracts all links from a HTML page, compares them to a pattern
# entered on the command line and then downloads matching links into the
# target dir (also specified on the command line).
#
# Written to use 'curl' for URL fetching, uses the source file names in the
# target directory.
#
# Author: Daniel Stenberg <Daniel.Stenberg@sth.frontec.se>
# Version: 0.1 Oct 7, 1998
#
# HISTORY
#
# 0.1 - Created now!
#

$in="";

 argv:
if($ARGV[0] eq "-v" ) {
    $verbose = 1;
    shift @ARGV;
    goto argv;
}
if($ARGV[0] eq "-d" ) {
    $display = 1;
    shift @ARGV;
    goto argv;
}
elsif($ARGV[0] eq "-h" ) {
    $help = 1;
    shift @ARGV;
    goto argv;
}

$geturl = $ARGV[0];
$getdir = $ARGV[1];
$getregex = $ARGV[2];

if(($geturl eq "") ||
   (($getdir eq "") && !$display) ||
   $help) {
    print  "Usage: $0 [-hv] <full source URL> <target dir> [regex]\n",
    " Use a traling slash for directory URLs!\n",
    " Use \"quotes\" around the regex!\n",
    " -h  This help text\n",
    " -d  Display matches only instead of downloading\n",
    " -v  Verbose mode\n";
    exit;
}

# change to target directory:
chdir $getdir ||
    die "couldn't cd into $getdir";

# 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";

# urlget, URL will be appended to the right of this command line
# this stores the file with the remote file name in the current dir
$urlget = "curl -O -s$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;
    }
}

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 =~ /^([^:]+):/) {
        $link = $url;
    }
    else {
        # this is an absolute link on the same server:
        if($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";
        }
    }

    if($link =~ /$getregex/) {
        if($display) {
            print "$link\n";
        }
        else {
            if($verbose) {
                print "Gets $link\n";
            }
            print `$urlget $link`;
        }
    }


}