| 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::PullParser 3" |
| 132 | .TH HTML::PullParser 3 "2001-04-02" "perl v5.8.0" "User Contributed Perl Documentation" |
| 133 | .SH "NAME" |
| 134 | HTML::PullParser \- Alternative HTML::Parser interface |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 1 |
| 138 | \& use HTML::PullParser; |
| 139 | .Ve |
| 140 | .PP |
| 141 | .Vb 8 |
| 142 | \& $p = HTML::PullParser->new(file => "index.html", |
| 143 | \& start => 'event, tagname, @attr', |
| 144 | \& end => 'event, tagname', |
| 145 | \& ignore_elements => [qw(script style)], |
| 146 | \& ) || die "Can't open: $!"; |
| 147 | \& while (my $token = $p->get_token) { |
| 148 | \& #...do something with $token |
| 149 | \& } |
| 150 | .Ve |
| 151 | .SH "DESCRIPTION" |
| 152 | .IX Header "DESCRIPTION" |
| 153 | The HTML::PullParser is an alternative interface to the HTML::Parser class. |
| 154 | It basically turns the HTML::Parser inside out. You associate a file |
| 155 | (or any IO::Handle object or string) with the parser at construction time and |
| 156 | then repeatedly call \f(CW$parser\fR\->get_token to obtain the tags and text |
| 157 | found in the parsed document. |
| 158 | .PP |
| 159 | The following methods are provided: |
| 160 | .ie n .IP "$p = HTML::PullParser\->new( file => $file\fR, \f(CW%options )" 4 |
| 161 | .el .IP "$p = HTML::PullParser\->new( file => \f(CW$file\fR, \f(CW%options\fR )" 4 |
| 162 | .IX Item "$p = HTML::PullParser->new( file => $file, %options )" |
| 163 | .PD 0 |
| 164 | .ie n .IP "$p = HTML::PullParser\->new( doc => \e$doc, %options )" 4 |
| 165 | .el .IP "$p = HTML::PullParser\->new( doc => \e$doc, \f(CW%options\fR )" 4 |
| 166 | .IX Item "$p = HTML::PullParser->new( doc => $doc, %options )" |
| 167 | .PD |
| 168 | A \f(CW\*(C`HTML::PullParser\*(C'\fR can be made to parse from either a file or a |
| 169 | literal document based on whether the \f(CW\*(C`file\*(C'\fR or \f(CW\*(C`doc\*(C'\fR option is |
| 170 | passed to the parser's constructor. |
| 171 | .Sp |
| 172 | The \f(CW\*(C`file\*(C'\fR passed in can either be a file name or a file handle |
| 173 | object. If a file name is passed, and it can't be opened for reading, |
| 174 | then the constructor will return an undefined value and $! will tell |
| 175 | you why it failed. Otherwise the argument is taken to be some object |
| 176 | that the \f(CW\*(C`HTML::PullParser\*(C'\fR can \fIread()\fR from when it needs more data. |
| 177 | The stream will be \fIread()\fR until \s-1EOF\s0, but not closed. |
| 178 | .Sp |
| 179 | A \f(CW\*(C`doc\*(C'\fR can be passed plain or as a reference |
| 180 | to a scalar. If a reference is passed then the value of this scalar |
| 181 | should not be changed before all tokens have been extracted. |
| 182 | .Sp |
| 183 | Next the information to be returned for the different token types must |
| 184 | be set up. This is done by simply assosiating an argspec (as defined |
| 185 | in HTML::Parser) with the events you have an interrest in. For |
| 186 | instance, if you want \f(CW\*(C`start\*(C'\fR tokens to be reported as the string |
| 187 | \&\f(CW'S'\fR followed by the tagname and the attributes you might pass an |
| 188 | \&\f(CW\*(C`start\*(C'\fR\-option like this: |
| 189 | .Sp |
| 190 | .Vb 4 |
| 191 | \& $p = HTML::Parser-New( doc => $doc_to_parse, |
| 192 | \& start => '"S", tagname, @attr', |
| 193 | \& end => '"E", tagname', |
| 194 | \& ); |
| 195 | .Ve |
| 196 | .Sp |
| 197 | At last other \f(CW\*(C`HTML::Parser\*(C'\fR options, like \f(CW\*(C`ignore_tags\*(C'\fR, and |
| 198 | \&\f(CW\*(C`unbroken_text\*(C'\fR, can be passed in. Note that you should not use the |
| 199 | \&\fIevent\fR_h options to set up parser handlers. |
| 200 | .ie n .IP "$token = $p\->get_token" 4 |
| 201 | .el .IP "$token = \f(CW$p\fR\->get_token" 4 |
| 202 | .IX Item "$token = $p->get_token" |
| 203 | This method will return the next \fItoken\fR found in the \s-1HTML\s0 document, |
| 204 | or \f(CW\*(C`undef\*(C'\fR at the end of the document. The token is usually returned |
| 205 | as an array reference. The content of this array match the argspec |
| 206 | set up during \f(CW\*(C`HTML::PullParser\*(C'\fR construction. |
| 207 | .IP "$p\->unget_token($token,...)" 4 |
| 208 | .IX Item "$p->unget_token($token,...)" |
| 209 | If you find out you have read too many tokens you can push them back, |
| 210 | so that they are returned again the next time \f(CW$p\fR\->get_token is called. |
| 211 | .SH "EXAMPLES" |
| 212 | .IX Header "EXAMPLES" |
| 213 | The 'eg/hform' script shows how we might parse the form section of |
| 214 | HTML::Documents using HTML::PullParser. |
| 215 | .SH "SEE ALSO" |
| 216 | .IX Header "SEE ALSO" |
| 217 | HTML::Parser, HTML::TokeParser |
| 218 | .SH "COPYRIGHT" |
| 219 | .IX Header "COPYRIGHT" |
| 220 | Copyright 1998\-2001 Gisle Aas. |
| 221 | .Sp |
| 222 | This library is free software; you can redistribute it and/or |
| 223 | modify it under the same terms as Perl itself. |