Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | .\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 |
2 | .\" | |
3 | .\" Standard preamble: | |
4 | .\" ======================================================================== | |
5 | .de Sh \" Subsection heading | |
6 | .br | |
7 | .if t .Sp | |
8 | .ne 5 | |
9 | .PP | |
10 | \fB\\$1\fR | |
11 | .PP | |
12 | .. | |
13 | .de Sp \" Vertical space (when we can't use .PP) | |
14 | .if t .sp .5v | |
15 | .if n .sp | |
16 | .. | |
17 | .de Vb \" Begin verbatim text | |
18 | .ft CW | |
19 | .nf | |
20 | .ne \\$1 | |
21 | .. | |
22 | .de Ve \" End verbatim text | |
23 | .ft R | |
24 | .fi | |
25 | .. | |
26 | .\" Set up some character translations and predefined strings. \*(-- will | |
27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left | |
28 | .\" double quote, and \*(R" will give a right double quote. | will give a | |
29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to | |
30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' | |
31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. | |
32 | .tr \(*W-|\(bv\*(Tr | |
33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' | |
34 | .ie n \{\ | |
35 | . ds -- \(*W- | |
36 | . ds PI pi | |
37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch | |
38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch | |
39 | . ds L" "" | |
40 | . ds R" "" | |
41 | . ds C` "" | |
42 | . ds C' "" | |
43 | 'br\} | |
44 | .el\{\ | |
45 | . ds -- \|\(em\| | |
46 | . ds PI \(*p | |
47 | . ds L" `` | |
48 | . ds R" '' | |
49 | 'br\} | |
50 | .\" | |
51 | .\" If the F register is turned on, we'll generate index entries on stderr for | |
52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index | |
53 | .\" entries marked with X<> in POD. Of course, you'll have to process the | |
54 | .\" output yourself in some meaningful fashion. | |
55 | .if \nF \{\ | |
56 | . de IX | |
57 | . tm Index:\\$1\t\\n%\t"\\$2" | |
58 | .. | |
59 | . nr % 0 | |
60 | . rr F | |
61 | .\} | |
62 | .\" | |
63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes | |
64 | .\" way too many mistakes in technical documents. | |
65 | .hy 0 | |
66 | .if n .na | |
67 | .\" | |
68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). | |
69 | .\" Fear. Run. Save yourself. No user-serviceable parts. | |
70 | . \" fudge factors for nroff and troff | |
71 | .if n \{\ | |
72 | . ds #H 0 | |
73 | . ds #V .8m | |
74 | . ds #F .3m | |
75 | . ds #[ \f1 | |
76 | . ds #] \fP | |
77 | .\} | |
78 | .if t \{\ | |
79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) | |
80 | . ds #V .6m | |
81 | . ds #F 0 | |
82 | . ds #[ \& | |
83 | . ds #] \& | |
84 | .\} | |
85 | . \" simple accents for nroff and troff | |
86 | .if n \{\ | |
87 | . ds ' \& | |
88 | . ds ` \& | |
89 | . ds ^ \& | |
90 | . ds , \& | |
91 | . ds ~ ~ | |
92 | . ds / | |
93 | .\} | |
94 | .if t \{\ | |
95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" | |
96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' | |
97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' | |
98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' | |
99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' | |
100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' | |
101 | .\} | |
102 | . \" troff and (daisy-wheel) nroff accents | |
103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' | |
104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' | |
105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] | |
106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' | |
107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' | |
108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] | |
109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] | |
110 | .ds ae a\h'-(\w'a'u*4/10)'e | |
111 | .ds Ae A\h'-(\w'A'u*4/10)'E | |
112 | . \" corrections for vroff | |
113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' | |
114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' | |
115 | . \" for low resolution devices (crt and lpr) | |
116 | .if \n(.H>23 .if \n(.V>19 \ | |
117 | \{\ | |
118 | . ds : e | |
119 | . ds 8 ss | |
120 | . ds o a | |
121 | . ds d- d\h'-1'\(ga | |
122 | . ds D- D\h'-1'\(hy | |
123 | . ds th \o'bp' | |
124 | . ds Th \o'LP' | |
125 | . ds ae ae | |
126 | . ds Ae AE | |
127 | .\} | |
128 | .rm #[ #] #H #V #F C | |
129 | .\" ======================================================================== | |
130 | .\" | |
131 | .IX Title "HTML::LinkExtor 3" | |
132 | .TH HTML::LinkExtor 3 "2001-04-10" "perl v5.8.0" "User Contributed Perl Documentation" | |
133 | .SH "NAME" | |
134 | HTML::LinkExtor \- Extract links from an HTML document | |
135 | .SH "SYNOPSIS" | |
136 | .IX Header "SYNOPSIS" | |
137 | .Vb 7 | |
138 | \& require HTML::LinkExtor; | |
139 | \& $p = HTML::LinkExtor->new(\e&cb, "http://www.perl.org/"); | |
140 | \& sub cb { | |
141 | \& my($tag, %links) = @_; | |
142 | \& print "$tag @{[%links]}\en"; | |
143 | \& } | |
144 | \& $p->parse_file("index.html"); | |
145 | .Ve | |
146 | .SH "DESCRIPTION" | |
147 | .IX Header "DESCRIPTION" | |
148 | \&\fIHTML::LinkExtor\fR is an \s-1HTML\s0 parser that extracts links from an | |
149 | \&\s-1HTML\s0 document. The \fIHTML::LinkExtor\fR is a subclass of | |
150 | \&\fIHTML::Parser\fR. This means that the document should be given to the | |
151 | parser by calling the \f(CW$p\fR\->\fIparse()\fR or \f(CW$p\fR\->\fIparse_file()\fR methods. | |
152 | .ie n .IP "$p = HTML::LinkExtor\->new([$callback[, $base]])" 4 | |
153 | .el .IP "$p = HTML::LinkExtor\->new([$callback[, \f(CW$base\fR]])" 4 | |
154 | .IX Item "$p = HTML::LinkExtor->new([$callback[, $base]])" | |
155 | The constructor takes two optional arguments. The first is a reference | |
156 | to a callback routine. It will be called as links are found. If a | |
157 | callback is not provided, then links are just accumulated internally | |
158 | and can be retrieved by calling the \f(CW$p\fR\->\fIlinks()\fR method. | |
159 | .Sp | |
160 | The \f(CW$base\fR argument is an optional base \s-1URL\s0 used to absolutize all URLs found. | |
161 | You need to have the \fI\s-1URI\s0\fR module installed if you provide \f(CW$base\fR. | |
162 | .Sp | |
163 | The callback is called with the lowercase tag name as first argument, | |
164 | and then all link attributes as separate key/value pairs. All | |
165 | non-link attributes are removed. | |
166 | .IP "$p\->links" 4 | |
167 | .IX Item "$p->links" | |
168 | Returns a list of all links found in the document. The returned | |
169 | values will be anonymous arrays with the follwing elements: | |
170 | .Sp | |
171 | .Vb 1 | |
172 | \& [$tag, $attr => $url1, $attr2 => $url2,...] | |
173 | .Ve | |
174 | .Sp | |
175 | The \f(CW$p\fR\->links method will also truncate the internal link list. This | |
176 | means that if the method is called twice without any parsing | |
177 | between them the second call will return an empty list. | |
178 | .Sp | |
179 | Also note that \f(CW$p\fR\->links will always be empty if a callback routine | |
180 | was provided when the \fIHTML::LinkExtor\fR was created. | |
181 | .SH "EXAMPLE" | |
182 | .IX Header "EXAMPLE" | |
183 | This is an example showing how you can extract links from a document | |
184 | received using \s-1LWP:\s0 | |
185 | .PP | |
186 | .Vb 3 | |
187 | \& use LWP::UserAgent; | |
188 | \& use HTML::LinkExtor; | |
189 | \& use URI::URL; | |
190 | .Ve | |
191 | .PP | |
192 | .Vb 2 | |
193 | \& $url = "http://www.perl.org/"; # for instance | |
194 | \& $ua = LWP::UserAgent->new; | |
195 | .Ve | |
196 | .PP | |
197 | .Vb 7 | |
198 | \& # Set up a callback that collect image links | |
199 | \& my @imgs = (); | |
200 | \& sub callback { | |
201 | \& my($tag, %attr) = @_; | |
202 | \& return if $tag ne 'img'; # we only look closer at <img ...> | |
203 | \& push(@imgs, values %attr); | |
204 | \& } | |
205 | .Ve | |
206 | .PP | |
207 | .Vb 3 | |
208 | \& # Make the parser. Unfortunately, we don't know the base yet | |
209 | \& # (it might be diffent from $url) | |
210 | \& $p = HTML::LinkExtor->new(\e&callback); | |
211 | .Ve | |
212 | .PP | |
213 | .Vb 3 | |
214 | \& # Request document and parse it as it arrives | |
215 | \& $res = $ua->request(HTTP::Request->new(GET => $url), | |
216 | \& sub {$p->parse($_[0])}); | |
217 | .Ve | |
218 | .PP | |
219 | .Vb 3 | |
220 | \& # Expand all image URLs to absolute ones | |
221 | \& my $base = $res->base; | |
222 | \& @imgs = map { $_ = url($_, $base)->abs; } @imgs; | |
223 | .Ve | |
224 | .PP | |
225 | .Vb 2 | |
226 | \& # Print them out | |
227 | \& print join("\en", @imgs), "\en"; | |
228 | .Ve | |
229 | .SH "SEE ALSO" | |
230 | .IX Header "SEE ALSO" | |
231 | HTML::Parser, HTML::Tagset, \s-1LWP\s0, \s-1URI::URL\s0 | |
232 | .SH "COPYRIGHT" | |
233 | .IX Header "COPYRIGHT" | |
234 | Copyright 1996\-2001 Gisle Aas. | |
235 | .PP | |
236 | This library is free software; you can redistribute it and/or | |
237 | modify it under the same terms as Perl itself. |