<?php echo $title;?>

commit 1a268ba710b2cdb4ede98af3368c43d66c4c5e53 Author: Nicolas Lœuillet Date: Wed Apr 3 15:14:01 2013 +0200 first commit diff --git a/COPYING b/COPYING new file mode 100644 index 0000000..ee7d6a5 --- /dev/null +++ b/COPYING @@ -0,0 +1,14 @@ + DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE + Version 2, December 2004 + + Copyright (C) 2004 Sam Hocevar + + Everyone is permitted to copy and distribute verbatim or modified + copies of this license document, and changing it is allowed as long + as the name is changed. + + DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. You just DO WHAT THE FUCK YOU WANT TO. + diff --git a/README.md b/README.md new file mode 100755 index 0000000..b66aba1 --- /dev/null +++ b/README.md @@ -0,0 +1,13 @@ +# poche + +Abandon Pocket, Instapaper and other Readibility service : adopt poche. It is the same, but it is open source. + +## Usage + +... + +## License +Copyright © 2010-2013 Nicolas Lœuillet +This work is free. You can redistribute it and/or modify it under the +terms of the Do What The Fuck You Want To Public License, Version 2, +as published by Sam Hocevar. See the COPYING file for more details. \ No newline at end of file diff --git a/cache/footer.32a3c4422ad65642b8dbb7e731f4d990.rtpl.php b/cache/footer.32a3c4422ad65642b8dbb7e731f4d990.rtpl.php new file mode 100644 index 0000000..e069cab --- /dev/null +++ b/cache/footer.32a3c4422ad65642b8dbb7e731f4d990.rtpl.php @@ -0,0 +1,7 @@ + diff --git a/cache/index.0b3442bc62f6c429fc13004b3c821ba0.rtpl.php b/cache/index.0b3442bc62f6c429fc13004b3c821ba0.rtpl.php new file mode 100644 index 0000000..6dd72a4 --- /dev/null +++ b/cache/index.0b3442bc62f6c429fc13004b3c821ba0.rtpl.php @@ -0,0 +1,20 @@ + + + + + + <?php echo $title;?> + + +

+ + +

+ Come From : +

+ assign( $this->var );$tpl->draw( dirname("footer") . ( substr("footer",-1,1) != "/" ? "/" : "" ) . basename("footer") );?> + + + diff --git a/css/index.html b/css/index.html new file mode 100755 index 0000000..e69de29 diff --git a/css/knacss.css b/css/knacss.css new file mode 100644 index 0000000..56e91f9 --- /dev/null +++ b/css/knacss.css @@ -0,0 +1,1070 @@ +/* +* www.KNACSS.com V2.6c @author: Raphael Goetter, Alsacreations +* Licence CC-BY http://creativecommons.org/licenses/by/3.0/fr/ +*/ + +/* ----------------------------- */ +/* ==reset */ +/* ----------------------------- */ + +/* base font-size corresponds to 10px and is adapted to rem unit */ +html { + font-size: 62.5%; +} +body { + background-color: #fff; + color: #000; + font-family: "Century Gothic", helvetica, arial, sans-serif; + font-size: 1.4em; /* equiv 14px */ + line-height: 1.5; /* adapt to your design */ +} + +/* font-sizing for content */ +/* preserve vertical-rythm, thanks to http://soqr.fr/vertical-rhythm/ */ +p, +ul, +ol, +dl, +blockquote, +pre, +td, +th, +label, +textarea, +caption, +details, +figure, +hgroup { + font-size: 1em; /* equiv 14px */ + line-height: 1.5; + margin: .75em 0 0; +} +h1, .h1-like { + font-size: 1.8571em; /* equiv 26px */ + font-weight: normal; + line-height: 1.6154em; + margin: .8077em 0 0 0; +} +h2, .h2-like { + font-size: 1.7143em; /* equiv 24px */ + font-weight: normal; + line-height: 1.75em; + margin: .875em 0 0 0; +} +h3, .h3-like { + font-size: 1.5714em; /* equiv 22px */ + font-weight: normal; + line-height: 1.909em; + margin: .9545em 0 0 0; +} +h4, .h4-like { + font-size: 1.4286em; /* equiv 20px */ + font-weight: normal; + line-height: 1.05em; + margin: 1.05em 0 0 0; +} +h5, .h5-like { + font-size: 1.2857em; /* equiv 18px */ + font-weight: normal; + line-height: 1.1667em; + margin: 1.1667em 0 0 0; +} +h6, .h6-like { + font-size: 1.1429em; /* equiv 16px */ + font-weight: normal; + line-height: 1.3125em; + margin: 1.3125em 0 0 0; +} + +/* alternate font-sizing */ +.smaller { + font-size: .7143em; /* equiv 10px */ +} +.small { + font-size: .8571em; /* equiv 12px */ +} +.big { + font-size: 1.1429em; /* equiv 16px */ +} +.bigger { + font-size: 1.2857em; /* equiv 18px */ +} +.biggest { + font-size: 1.4286em; /* equiv 20px */ +} + +/* soft reset */ +html, +body, +textarea, +figure, +label { + margin: 0; + padding: 0; +} +ul, +ol { + padding-left: 2em; +} +code, +pre, +samp, +kbd { + white-space: pre-wrap; + font-family: consolas, 'DejaVu Sans Mono', courier, monospace; + line-height: 1em; +} +code, kbd, mark { + border-radius: 2px; +} +em { + font-style: italic; +} +strong { + font-weight: bold; +} +kbd { + padding: 0 2px; + border: 1px solid #999; +} +code { + padding: 2px 4px; + background: rgba(0,0,0,.04); + color: #b11; +} +mark { + padding:2px 4px; + background: #ff0; +} + +table { margin-bottom: 1.5em; } + +/* avoid top margins on first content element */ +p:first-child, +ul:first-child, +ol:first-child, +dl:first-child, +blockquote:first-child, +pre:first-child, +h1:first-child, +h2:first-child, +h3:first-child, +h4:first-child, +h5:first-child, +h6:first-child { + margin-top: 0; +} + +/* avoid margins on nested elements */ +li p, +li ul, +li ol { + margin-top: 0; + margin-bottom: 0; +} + +/* max values */ +img, table, td, blockquote, code, pre, textarea, input, video { + max-width: 100%; +} + +/* you shall not pass */ +div, textarea, table, td, th, code, pre, samp { + word-wrap: break-word; + -webkit-hyphens: auto; + -moz-hyphens: auto; + -ms-hyphens: auto; + -o-hyphens: auto; + hyphens: auto; +} + +/* pictures */ +img { + height: auto; + vertical-align: middle; +} +/* Gmap3 max-width bug fix on images */ +#map_canvas img, +.gmnoprint img {max-width: none;} + +a img { border: 0; } + +/* scripts */ +body > script {display: none !important;} + +/* skip-links */ +.skip-links { + position: absolute; +} +.skip-links a { + position: absolute; + left: -7000px; + padding: 0.5em; + background: #000; + color:#fff; + text-decoration: none; +} +.skip-links a:focus { + position: static; +} + +/* ----------------------------- */ +/* ==layout and modules */ +/* ----------------------------- */ + +/* switching box model for all elements */ +* { + -webkit-box-sizing: border-box; + -moz-box-sizing: border-box; + box-sizing: border-box; +} + +/* float layout */ +/* ----------- */ + +/* module, contains floats (.item is the same) */ +.mod, .item { + overflow: hidden; +} + +/* table layout */ +/* ------------------ */ +.row { + display: table; + table-layout: fixed; + width: 100%; +} +.row > *, +.col { + display: table-cell; + vertical-align: top; +} + +/* blocks that needs to be placed under floats */ +.clear, +.line, +.row { + clear: both; +} + +/* blocks that must contain floats */ +.clearfix:after, +.line:after, +.mod:after { + content: ""; + display: table; + clear: both; +} + +/* alignments (blocks and inline) */ +/* ------------------------------ */ + +/* left elements */ +.left { + float: left; +} +img.left { + margin-right: 1em; +} + +/* right elements */ +.right { + float: right; +} +img.right { + margin-left: 1em; +} + +img.left, img.right { + margin-bottom: 5px; +} + +.center { margin-left: auto; margin-right: auto; } +.txtleft { text-align: left; } +.txtright { text-align: right; } +.txtcenter { text-align: center; } + +/* just inline-block */ +.inbl { + display: inline-block; + vertical-align: top; + margin-right: -.25em; +} + +/* blocks widths (percentage and pixels) */ +.w10 { width: 10%; } +.w20 { width: 20%; } +.w25 { width: 25%; } +.w30 { width: 30%; } +.w33 { width: 33.333%; } +.w40 { width: 40%; } +.w50 { width: 50%; } +.w60 { width: 60%; } +.w66 { width: 66.666%; } +.w70 { width: 70%; } +.w75 { width: 75%; } +.w80 { width: 80%; } +.w90 { width: 90%; } +.w100 { width: 100%; } + +.w50p { width: 50px; } +.w100p { width: 100px; } +.w150p { width: 150px; } +.w200p { width: 200px; } +.w300p { width: 300px; } +.w400p { width: 400px; } +.w500p { width: 500px; } +.w600p { width: 600px; } +.w700p { width: 700px; } +.w800p { width: 800px; } +.w960p { width: 960px; } +.mw960p { max-width: 960px; } + +/* spacing helpers +p,m = padding,margin +a,t,r,b,l = all,top,right,bottom,left +s,m,l,n = small(10px),medium(20px),large(30px),none(0) +source https://github.com/stubbornella/oocss/blob/master/core/spacing/space.css +*/ +.m-reset, .ma0 { margin: 0 !important; } +.p-reset, .pa0 { padding: 0 !important; } +.ma1, .mas { margin: 10px !important; } +.ma2, .mam { margin: 20px !important; } +.ma3, .mal { margin: 30px !important; } +.pa1, .pas { padding: 10px; } +.pa2, .pam { padding: 20px; } +.pa3, .pal { padding: 30px; } + +.mt0, .mtn { margin-top: 0 !important; } +.mt1, .mts { margin-top: 10px !important; } +.mt2, .mtm { margin-top: 20px !important; } +.mt3, .mtl { margin-top: 30px !important; } +.mr0, .mrn { margin-right: 0; } +.mr1, .mrs { margin-right: 10px; } +.mr2, .mrm { margin-right: 20px; } +.mr3, .mrl { margin-right: 30px; } +.mb0, .mbn { margin-bottom: 0 !important; } +.mb1, .mbs { margin-bottom: 10px !important; } +.mb2, .mbm { margin-bottom: 20px !important; } +.mb3, .mbl { margin-bottom: 30px !important; } +.ml0, .mln { margin-left: 0; } +.ml1, .mls { margin-left: 10px; } +.ml2, .mlm { margin-left: 20px; } +.ml3, .mll { margin-left: 30px; } + +.pt0, .ptn { padding-top: 0; } +.pt1, .pts { padding-top: 10px; } +.pt2, .ptm { padding-top: 20px; } +.pt3, .ptl { padding-top: 30px; } +.pr0, .prn { padding-right: 0; } +.pr1, .prs { padding-right: 10px; } +.pr2, .prm { padding-right: 20px; } +.pr3, .prl { padding-right: 30px; } +.pb0, .pbn { padding-bottom: 0; } +.pb1, .pbs { padding-bottom: 10px; } +.pb2, .pbm { padding-bottom: 20px; } +.pb3, .pbl { padding-bottom: 30px; } +.pl0, .pln { padding-left: 0; } +.pl1, .pls { padding-left: 10px; } +.pl2, .plm { padding-left: 20px; } +.pl3, .pll { padding-left: 30px; } + +/* hiding content */ +.visually-hidden { + position: absolute; + left: -7000px; + overflow: hidden; +} +[dir=rtl] .visually-hidden { + left: auto; + right: -7000px; +} + +.desktop-hidden { display: none; } /* hidden on desktop */ + +/* ----------------------------- */ +/* ==header */ +/* ----------------------------- */ + +/* ----------------------------- */ +/* ==sidebar */ +/* ----------------------------- */ + +/* ----------------------------- */ +/* ==footer */ +/* ----------------------------- */ + +/* ----------------------------- */ +/* ==forms */ +/* ----------------------------- */ +form, +fieldset { + border: none; +} +input, +button, +select, +label, +.btn { + vertical-align: middle; /* @bugfix alignment */ + font-family: inherit; +} +textarea { + resize: vertical; + font-family: inherit; +} + +/* ----------------------------- */ +/* ==main */ +/* ----------------------------- */ + +/* ----------------------------- */ +/* ==iefix */ +/* ----------------------------- */ + +/* haslayout for IE6/IE7 */ +.ie67 .clearfix, +.ie67 .line, +.ie67 .mod, +.ie67 .row, +.ie67 .col { + zoom: 1; +} + +/* inline-block and table-cell for IE6/IE7 */ +/* warning: .col needs width on IE6/IE7 */ +.ie67 .btn, +.ie67 .col, +.ie67 .inbl { + display: inline; + zoom: 1; +} +.ie8 img { + width: auto; /* @bugfix for IE8 */ +} + +/* Active box-sizing for IE6/IE7 */ +/* @source https://github.com/Schepp/box-sizing-polyfill */ +/* +.ie67 * { + behavior: url(/js/boxsizing.htc); +} +*/ + +/* ----------------------------- */ +/* ==print */ +/* ----------------------------- */ + +/* quick print reset */ +@media print { + p, + blockquote { + orphans: 2; + widows: 2; + } + blockquote, + ul, + ol { + page-break-inside: avoid; + } + h1, + h2, + h3, + caption { + page-break-after: avoid; + } +} + +/* orientation iOS font-size fix */ +@media (orientation: landscape) and (max-device-width: 768px) { + html, + body { + -webkit-text-size-adjust: 100%; + } +} +/* ----------------------------- */ +/* ==grids */ +/* ----------------------------- */ + +/* equal grids with 2% gutter */ +[class*=grid] > * {float: left; } /* direct childrens are floating */ +[class*=grid] > * + * { margin-left: 2%; } /* here's the gutter */ +.grid2 > * { width: 49%; } +.grid3 > * { width: 32%; } +.grid4 > * { width: 23.5%; } +.grid5 > * { width: 18.4%; } +.grid6 > * { width: 15%; } + +/* unequal grids (1-2, 2-1, 1-3 and 3-1) */ +.grid2-1 > *:first-child, +.grid1-2 > * + * { width: 66%; } +.grid1-2 > *:first-child, +.grid2-1 > * + * { width: 32%; } +.grid1-3 > *:first-child, +.grid3-1 > * + * { width: 23.5%; } +.grid3-1 > *:first-child, +.grid1-3 > * + * { width: 74.5%; } + + +/* ----------------------------- */ +/* ==tables */ +/* ----------------------------- */ + +table, +.table { + max-width : 100%; + table-layout: fixed; + border-collapse: collapse; + vertical-align: top; +} +table { + width: 100%; +} +.table { + display: table; +} +caption { + padding: 10px; + color: #555; + font-style: italic; +} +table { + border: 1px solid #ccc; +} +tr > * + * { + border-left: 1px solid #ccc; +} +th, +td { + padding: .3em .8em; + text-align: left; + border-bottom: 1px solid #ccc; +} +td { + color: #333; +} + +/* alternate tables */ +.alternate { border: 0; } +.alternate tbody { + border: 1px solid #ccc; +} +.alternate thead tr > * + * { + border-left: 0; +} +.alternate tbody tr > * + * { + border-left: 1px solid #ccc; +} + +/* alternate-vert tables */ +.alternate-vert { + border: 0; + border-right: 1px solid #ccc; +} +.alternate-vert tr > :first-child { + border-bottom: 0; +} +.alternate-vert tr > * + * { + border-top: 1px solid #ccc; +} + +/* striped tables */ +.striped tbody tr:nth-child(odd) { + background: #eee; + background: rgba(0, 0, 0, .05); +} + +/* striped-vert tables */ +.striped-vert tr > :first-child { + background: #eee; + background: rgba(0, 0, 0, .05); +} +/* ----------------------------- */ +/* ==forms */ +/* ----------------------------- */ + +/* thanks to HTML5boilerplate, github.com/nathansmith/formalize and www.sitepen.com */ + + +/* buttons */ +.btn { display: inline-block; } + +.btn.alternate {} +.btn.highlight {} +.login {} +.logout {} +.primary {} +.warning {} +.error {} +.success {} + +/* forms items */ +label { + display: inline-block; + vertical-align: middle; + cursor: pointer; +} +legend { + border: 0; + white-space: normal; +} +button, +input, +select { + font-family: "Century Gothic", helvetica, arial, sans-serif; + font-size: 100%; + margin: 0; + vertical-align: middle; +} +textarea { + overflow: auto; /* Removes default vertical scrollbar on empty textarea in IE6/7/8/9 */ + min-height: 5em; + font-size: 1.75em; + vertical-align: top; + resize: vertical; +} +button, +input[type="button"], +input[type="reset"], +input[type="submit"] { + cursor: pointer; + -webkit-appearance: button; /* clickable input types in iOS */ + *overflow: visible; /* Corrects inner spacing displayed oddly in IE7 */ +} +input[type="checkbox"], +input[type="radio"] { + padding: 0; /* Corrects excess space around these inputs in IE8/9 */ + *width: 13px; *height: 13px; /* Corrects excess space around these inputs in IE7 */ +} +input[type="search"] { -webkit-appearance: textfield; } + +/* if select styling bugs on WebKit */ +/* select { -webkit-appearance: none; } */ + +/* 'x' appears on right of search input when text is entered. This removes it */ +input[type="search"]::-webkit-search-decoration, +input[type="search"]::-webkit-search-cancel-button, +input[type="search"]::-webkit-search-results-button, +input[type="search"]::-webkit-search-results-decoration { + display: none; +} +::-webkit-input-placeholder { color: #777; } +input:-moz-placeholder, +textarea:-moz-placeholder { color: #777; } + +/* Removes inner padding and border in FF3+ */ +button::-moz-focus-inner, +input[type='button']::-moz-focus-inner, +input[type='reset']::-moz-focus-inner, +input[type='submit']::-moz-focus-inner { + border: 0; + padding: 0; +} + +/* ----------------------------- */ +/* ==icons and bullets */ +/* ----------------------------- */ + +.icon {display: inline-block;} + +.icon:before, +.icon > li:before, +.icon.after:after, +.icon.after > li:after { + content: ""; + display: inline-block; + vertical-align: middle; + position: relative; top: -.1em; + margin: 0 0.3em 0 0; + font: 1.4em/1 sans-serif; + color: #000; + text-shadow: 1px 1px 0 rgba(0,0,0,.1); + speak: none; +} + +@media (min-device-width: 768px) { + .icon:before, + .icon > li:before, + .icon.after:after, + .icon.after > li:after { + font: 1em/0.6 sans-serif; + -webkit-transform: rotateZ(0.05deg); + } +} + +.icon.after:after, +.icon.after > li:after { + margin: 0 0 0 8px; +} + +ul.icon {display: block;} +ul.icon > li {list-style: none;} +ul.icon:before, +ul.icon.after:after {content:""} +.icon.after:before, +.icon.after > li:before {content: "" !important} + +.icon-rate:before, +.icon-rate > li:before, +.icon-rate.after:after, +.icon-rate.after > li:after { + content: "\2605"; +} +.icon-unrate:before, +.icon-unrate > li:before, +.icon-unrate.after:after, +.icon-unrate.after > li:after { + content: "\2606"; +} +.icon-check:before, +.icon-check > li:before, +.icon-check.after:after, +.icon-check.after > li:after { + content: "\2713"; +} +.icon-uncheck:before, +.icon-uncheck > li:before, +.icon-uncheck.after:after, +.icon-uncheck.after > li:after { + content: "\2717"; +} +.icon-cloud:before, +.icon-cloud > li:before, +.icon-cloud.after:after, +.icon-cloud.after > li:after { + content: "\2601"; +} +.icon-dl:before, +.icon-dl > li:before, +.icon-dl.after:after, +.icon-dl.after > li:after { + content: "\21E3"; + font-weight: bold; +} +.icon-cross:before, +.icon-cross > li:before, +.icon-cross.after:after, +.icon-cross.after > li:after { + content: "\2716"; + font-weight: bold; +} +.icon-arrow1:before, +.icon-arrow1 > li:before, +.icon-arrow1.after:after, +.icon-arrow1.after > li:after { + content: "\2192"; + position: relative; top: -0.15em; +} +.icon-arrow2:before, +.icon-arrow2 > li:before, +.icon-arrow2.after:after, +.icon-arrow2.after > li:after { + content: "\279E"; +} +.icon-arrow3:before, +.icon-arrow3 > li:before, +.icon-arrow3.after:after, +.icon-arrow3.after > li:after { + content: "\279A"; +} +.icon-bracket1:before, +.icon-bracket1 > li:before, +.icon-bracket1.after:after, +.icon-bracket1.after > li:after { + content: "\2039"; + font-weight: bold; + font-size: 1.6em; + position: relative; top: -0.15em; +} +.icon-bracket2:before, +.icon-bracket2 > li:before, +.icon-bracket2.after:after, +.icon-bracket2.after > li:after { + content: "\203A"; + font-weight: bold; + font-size: 1.6em; + position: relative; top: -0.15em; +} +.icon-up:before, +.icon-up > li:before, +.icon-up.after:after, +.icon-up.after > li:after { + content: "\25B2"; +} +.icon-down:before, +.icon-down > li:before, +.icon-down.after:after, +.icon-down.after > li:after { + content: "\25BC"; +} +.icon-bull:before, +.icon-bull > li:before, +.icon-bull.after:after, +.icon-bull.after > li:after { + content: "\2022"; + font-size: 1.2em; + top: -0.05em; +} +.icon-bull2:before, +.icon-bull2 > li:before, +.icon-bull2.after:after, +.icon-bull2.after > li:after { + content: "\25E6"; + top: -0.05em; +} +.icon-bull3:before, +.icon-bull3 > li:before, +.icon-bull3.after:after, +.icon-bull3.after > li:after { + content: "\2023"; + font-size: 1.6em; + top: -0.05em; +} +.icon-nav:before, +.icon-nav > li:before, +.icon-nav.after:after, +.icon-nav.after > li:after { + content: "\2261"; + font-weight: bold; + font-size: 1.6em; +} +.icon-losange:before, +.icon-losange > li:before, +.icon-losange.after:after, +.icon-losange.after > li:after { + content: "\25C6"; +} +.icon-asteri:before, +.icon-asteri > li:before, +.icon-asteri.after:after, +.icon-asteri.after > li:after { + content: "\2731"; + font-weight: bold; +} +.icon-mail:before, +.icon-mail > li:before, +.icon-mail.after:after, +.icon-mail.after > li:after { + content: "\2709"; + font-size: 1.6em; + top: -.05em; +} + +ol.styled {counter-reset: styled;} +ol.styled > li { + list-style-type: none; + counter-increment: styled; + margin-bottom: .3em; +} +ol.styled > li:before { + content: counter(styled); + display: inline-block; + width: 1em; height: 1em; + line-height: 1; + padding: 2px; + margin-right: .4em; + vertical-align: middle; + background: rgba(0,0,0,.5); + border-radius: 50%; + font-size: .9em; + text-align: center; + text-indent: -0.1em; + color: white; +} +/* ----------------------------- */ +/* ==desktop and retina medias */ +/* ----------------------------- */ + +@media (min-width: 641px) { +/* here go rules for big resources and big screens like: background-images, font-faces, etc. */ +} +@media (-webkit-min-device-pixel-ratio: 2), (min-resolution: 192dpi), (min-resolution: 2dppx) { +/* Style adjustments for retina devices */ +} + +/* ---------------------------------- */ +/* ==Responsive large / medium / tiny */ +/* ---------------------------------- */ + +@media (min-width: 1280px) { + + /* layouts for large (l) screens */ + .large-hidden, + .tablet-hidden { display: none !important; } + .large-visible { display: block !important; } + .large-no-float {float: none; } + .large-inbl { + display: inline-block; + float: none; + vertical-align: top; + } + .large-row { + display: table; + table-layout: fixed; + width: 100% !important; + } + .large-col { + display: table-cell; + vertical-align: top; + } + + /* widths for large (l) screens */ + .large-w25 { width: 25% !important; } + .large-w33 { width: 33.3333% !important; } + .large-w50 { width: 50% !important; } + .large-w66 { width: 66.6666% !important; } + .large-w75 { width: 75% !important; } + .large-w100 { + display: block !important; + float: none !important; + clear: none !important; + width: auto !important; + margin-left: 0 !important; + margin-right: 0 !important; + border: 0; + } + + /* margins for large (l) screens */ + .large-ma0, + .large-man { margin: 0 !important; } +} + +@media (max-width: 768px) { + + /* quick tablet reset */ + .w60, + .w66, + .w70, + .w75, + .w80, + .w90, + .w100, + .w600p, + .w700p, + .w800p, + .w960p, + .mw960p, + .medium-wauto { width: auto; } + + /* layouts for medium (m) screens */ + .medium-hidden, + .tablet-hidden { display: none !important; } + .medium-visible { display: block !important; } + .medium-no-float {float: none; } + .medium-inbl { + display: inline-block; + float: none; + vertical-align: top; + } + .medium-row { + display: table; + table-layout: fixed; + width: 100% !important; + } + .medium-col { + display: table-cell; + vertical-align: top; + } + + /* widths for medium (m) screens */ + .medium-w25 { width: 25% !important; } + .medium-w33 { width: 33.3333% !important; } + .medium-w50 { width: 50% !important; } + .medium-w66 { width: 66.6666% !important; } + .medium-w75 { width: 75% !important; } + .medium-w100 { + display: block !important; + float: none !important; + clear: none !important; + width: auto !important; + margin-left: 0 !important; + margin-right: 0 !important; + border: 0; + } + /* margins for medium (m) screens */ + .medium-ma0, + .medium-man { margin: 0 !important; } + + /* Responsive grids */ + .grid4 > * {width: 49% !important; } + .grid4 > :first-child + * + * {margin-left: 0 !important;} + .grid6 > * {width: 32% !important; } + .grid6 > :first-child + * + * + * {margin-left: 0 !important;} +} + +@media (max-width: 640px) { + + /* quick smartphone reset */ + .mod, + .item, + .col, + fieldset { + display: block !important; + float: none !important; + clear: none !important; + width: auto !important; + margin-left: 0 !important; + margin-right: 0 !important; + border: 0; + } + .w30, + .w33, + .w40, + .w50, + .w300p, + .w400p, + .w500p { + width: auto; + } + .row { + display: block !important; + width: 100% !important; + } + + /* layouts for tiny (t) screens */ + .tiny-hidden, + .phone-hidden { display: none !important; } + .tiny-visible { display: block !important; } + .tiny-no-float {float: none;} + .tiny-inbl { + display: inline-block; + float: none; + vertical-align: top; + } + .tiny-row { + display: table; + table-layout: fixed; + width: 100% !important; + } + .tiny-col { + display: table-cell; + vertical-align: top; + } + th, + td { + display: block !important; + width: auto !important; + text-align: left !important; + } + thead { display: none; } + + /* widths for tiny (t) screens */ + .tiny-w25 { width: 25% !important; } + .tiny-w33 { width: 33.3333% !important; } + .tiny-w50 { width: 50% !important; } + .tiny-w66 { width: 66.6666% !important; } + .tiny-w75 { width: 75% !important; } + .tiny-w100 { + display: block !important; + float: none !important; + clear: none !important; + width: auto !important; + margin-left: 0 !important; + margin-right: 0 !important; + border: 0; + } + /* margins for tiny (t) screens */ + .tiny-ma0, + .tiny-man { margin: 0 !important; } +} + diff --git a/css/reset.css b/css/reset.css new file mode 100755 index 0000000..530ddc3 --- /dev/null +++ b/css/reset.css @@ -0,0 +1,35 @@ +html, body, div, span, object, iframe, +h1, h2, h3, h4, h5, h6, p, blockquote, pre, +a, abbr, acronym, address, code, +del, dfn, em, img, q, dl, dt, dd, ol, ul, li, +fieldset, form, label, legend, +table, caption, tbody, tfoot, thead, tr, th, td { + margin: 0; + padding: 0; + border: 0; + font-weight: inherit; + font-style: inherit; + font-size: 100%; + font-family: inherit; + vertical-align: baseline; +} + + +/* Tables still need 'cellspacing="0"' in the markup. */ +table { border-collapse: separate; border-spacing: 0; } +caption, th, td { text-align: left; font-weight: normal; } +table, td, th { vertical-align: middle; } + +/* Remove possible quote marks (") from ,

. */ +blockquote:before, blockquote:after, q:before, q:after { content: ""; } +blockquote, q { quotes: "" ""; } + +/* Remove annoying border on linked images. */ +a img { border: none; } + + +body { + + margin: 10px; +} + diff --git a/css/style.css b/css/style.css new file mode 100644 index 0000000..41a6178 --- /dev/null +++ b/css/style.css @@ -0,0 +1,35 @@ +body { + color: #222222; + font: 20px/1.3em Palatino,Georgia,serif; + background-color: #e6e6e6; +} + +a, a:hover, a:visited { + color: #000; +} +header { + text-align: center; +} + +#main { + margin: 0 auto; +} + +#main ul#links { + padding: 0; + list-style-type: none; + text-align: center; +} + +#main ul#links li { + display: inline; + padding: 15px; +} + +#main a.tool { + text-decoration: none; +} + +footer { + text-align: right; +} \ No newline at end of file diff --git a/css/typography.css b/css/typography.css new file mode 100755 index 0000000..e41db09 --- /dev/null +++ b/css/typography.css @@ -0,0 +1,85 @@ + +body { + font:1em/1.625em "lucida grande","lucida sans unicode", sans-serif; background-color:#FFFEF0; + font-size-adjust:none; + font-style:normal; + font-variant:normal; + font-weight:normal; + padding: 15px; + margin: 15px auto; +} + +article { + border: 3px solid grey; + max-width:700px; + margin: 15px auto; + padding: 15px; +} + +footer { + border: 1px solid black; + padding: 15px; + margin: 15px auto; +} + +p { padding:0 0 0.8125em 0; color:#111; font-weight:300;} + +p + p { text-indent:1.625em;} + +img { display: block; margin: 0.5em 0.8125em 0.8125em 0; padding: 0; } + +p > img { display: inline-block; margin: 0; } + +h1,h2{ font-weight:normal; color: #333; font-family:Georgia, serif; } +h3,h4,h5,h6 { font-weight: normal; color: #333; font-family:Georgia, serif; } + + +h1 { font-size: 2.125em; margin-bottom: 0.765em; line-height: 1.5em;} +h2 { font-size: 1.9em; margin-bottom: 0.855em; } +h3 { font-size: 1.7em; margin-bottom: 0.956em; } +h4 { font-size: 1.4em; margin-bottom: 1.161em; } +h5,h6 { font-size: 1.313em; margin-bottom: 1.238em; } + + + +ul{list-style-position:outside;} +li ul, +li ol { margin:0 1.625em; } +ul, ol { margin: 0 0 1.625em 0; } + + +dl { margin: 0 0 1.625em 0; } +dl dt { font-weight: bold; } +dl dd { margin-left: 1.625em; } + +a { color:#005AF2; text-decoration:none; } +a:hover { text-decoration: underline; } + + +table { margin-bottom:1.625em; border-collapse: collapse; } +th { font-weight:bold; } +tr,th,td { margin:0; padding:0 1.625em 0 1em; height:26px; } +tfoot { font-style: italic; } +caption { text-align:center; font-family:Georgia, serif; } + + +abbr, acronym { border-bottom:1px dotted #000; } +address { margin-top:1.625em; font-style: italic; } +del {color:#000;} + + +blockquote { padding:1em 1em 1.625em 1em; font-family:georgia,serif;font-style: italic; } +blockquote:before { content:"\201C";font-size:3em;margin-left:-.625em; font-family:georgia,serif;color:#aaa;line-height:0;}/* From Tripoli */ +blockquote > p {padding:0; margin:0; } + +strong { font-weight: bold; } +em, dfn { font-style: italic; } +dfn { font-weight: bold; } +pre, code { margin: 1.625em 0; white-space: pre; } +pre, code, tt { font: 1em monospace; line-height: 1.5; } +tt { display: block; margin: 1.625em 0; } +hr { margin-bottom:1.625em; } + +.oldbook { font-family:"Warnock Pro","Goudy Old Style","Book Antiqua","Palatino",Georgia,serif; } +.note { font-family:Georgia, "Times New Roman", Times, serif; font-style:italic; font-size:0.9em; margin:0.1em; color:#333; } +.mono { font-family:"Courier New", Courier, monospace; } diff --git a/inc/Encoding.php b/inc/Encoding.php new file mode 100755 index 0000000..ac107af --- /dev/null +++ b/inc/Encoding.php @@ -0,0 +1,262 @@ + + * @package Encoding + * @version 1.1 + * @link http://www.framework2.com.ar/dzone/forceUTF8-es/ + * @example http://www.framework2.com.ar/dzone/forceUTF8-es/ + */ + +class Encoding { + + protected static $win1252ToUtf8 = array( + 128 => "\xe2\x82\xac", + + 130 => "\xe2\x80\x9a", + 131 => "\xc6\x92", + 132 => "\xe2\x80\x9e", + 133 => "\xe2\x80\xa6", + 134 => "\xe2\x80\xa0", + 135 => "\xe2\x80\xa1", + 136 => "\xcb\x86", + 137 => "\xe2\x80\xb0", + 138 => "\xc5\xa0", + 139 => "\xe2\x80\xb9", + 140 => "\xc5\x92", + + 142 => "\xc5\xbd", + + + 145 => "\xe2\x80\x98", + 146 => "\xe2\x80\x99", + 147 => "\xe2\x80\x9c", + 148 => "\xe2\x80\x9d", + 149 => "\xe2\x80\xa2", + 150 => "\xe2\x80\x93", + 151 => "\xe2\x80\x94", + 152 => "\xcb\x9c", + 153 => "\xe2\x84\xa2", + 154 => "\xc5\xa1", + 155 => "\xe2\x80\xba", + 156 => "\xc5\x93", + + 158 => "\xc5\xbe", + 159 => "\xc5\xb8" + ); + + protected static $brokenUtf8ToUtf8 = array( + "\xc2\x80" => "\xe2\x82\xac", + + "\xc2\x82" => "\xe2\x80\x9a", + "\xc2\x83" => "\xc6\x92", + "\xc2\x84" => "\xe2\x80\x9e", + "\xc2\x85" => "\xe2\x80\xa6", + "\xc2\x86" => "\xe2\x80\xa0", + "\xc2\x87" => "\xe2\x80\xa1", + "\xc2\x88" => "\xcb\x86", + "\xc2\x89" => "\xe2\x80\xb0", + "\xc2\x8a" => "\xc5\xa0", + "\xc2\x8b" => "\xe2\x80\xb9", + "\xc2\x8c" => "\xc5\x92", + + "\xc2\x8e" => "\xc5\xbd", + + + "\xc2\x91" => "\xe2\x80\x98", + "\xc2\x92" => "\xe2\x80\x99", + "\xc2\x93" => "\xe2\x80\x9c", + "\xc2\x94" => "\xe2\x80\x9d", + "\xc2\x95" => "\xe2\x80\xa2", + "\xc2\x96" => "\xe2\x80\x93", + "\xc2\x97" => "\xe2\x80\x94", + "\xc2\x98" => "\xcb\x9c", + "\xc2\x99" => "\xe2\x84\xa2", + "\xc2\x9a" => "\xc5\xa1", + "\xc2\x9b" => "\xe2\x80\xba", + "\xc2\x9c" => "\xc5\x93", + + "\xc2\x9e" => "\xc5\xbe", + "\xc2\x9f" => "\xc5\xb8" + ); + + protected static $utf8ToWin1252 = array( + "\xe2\x82\xac" => "\x80", + + "\xe2\x80\x9a" => "\x82", + "\xc6\x92" => "\x83", + "\xe2\x80\x9e" => "\x84", + "\xe2\x80\xa6" => "\x85", + "\xe2\x80\xa0" => "\x86", + "\xe2\x80\xa1" => "\x87", + "\xcb\x86" => "\x88", + "\xe2\x80\xb0" => "\x89", + "\xc5\xa0" => "\x8a", + "\xe2\x80\xb9" => "\x8b", + "\xc5\x92" => "\x8c", + + "\xc5\xbd" => "\x8e", + + + "\xe2\x80\x98" => "\x91", + "\xe2\x80\x99" => "\x92", + "\xe2\x80\x9c" => "\x93", + "\xe2\x80\x9d" => "\x94", + "\xe2\x80\xa2" => "\x95", + "\xe2\x80\x93" => "\x96", + "\xe2\x80\x94" => "\x97", + "\xcb\x9c" => "\x98", + "\xe2\x84\xa2" => "\x99", + "\xc5\xa1" => "\x9a", + "\xe2\x80\xba" => "\x9b", + "\xc5\x93" => "\x9c", + + "\xc5\xbe" => "\x9e", + "\xc5\xb8" => "\x9f" + ); + + static function toUTF8($text){ + /** + * Function Encoding::toUTF8 + * + * This function leaves UTF8 characters alone, while converting almost all non-UTF8 to UTF8. + * + * It assumes that the encoding of the original string is either Windows-1252 or ISO 8859-1. + * + * It may fail to convert characters to UTF-8 if they fall into one of these scenarios: + * + * 1) when any of these characters: ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞß + * are followed by any of these: ("group B") + * ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶•¸¹º»¼½¾¿ + * For example: %ABREPRESENT%C9%BB. «REPRESENTÉ» + * The "«" (%AB) character will be converted, but the "É" followed by "»" (%C9%BB) + * is also a valid unicode character, and will be left unchanged. + * + * 2) when any of these: àáâãäåæçèéêëìíîï are followed by TWO chars from group B, + * 3) when any of these: ðñòó are followed by THREE chars from group B. + * + * @name toUTF8 + * @param string $text Any string. + * @return string The same string, UTF8 encoded + * + */ + + if(is_array($text)) + { + foreach($text as $k => $v) + { + $text[$k] = self::toUTF8($v); + } + return $text; + } elseif(is_string($text)) { + + $max = strlen($text); + $buf = ""; + for($i = 0; $i < $max; $i++){ + $c1 = $text{$i}; + if($c1>="\xc0"){ //Should be converted to UTF8, if it's not UTF8 already + $c2 = $i+1 >= $max? "\x00" : $text{$i+1}; + $c3 = $i+2 >= $max? "\x00" : $text{$i+2}; + $c4 = $i+3 >= $max? "\x00" : $text{$i+3}; + if($c1 >= "\xc0" & $c1 <= "\xdf"){ //looks like 2 bytes UTF8 + if($c2 >= "\x80" && $c2 <= "\xbf"){ //yeah, almost sure it's UTF8 already + $buf .= $c1 . $c2; + $i++; + } else { //not valid UTF8. Convert it. + $cc1 = (chr(ord($c1) / 64) | "\xc0"); + $cc2 = ($c1 & "\x3f") | "\x80"; + $buf .= $cc1 . $cc2; + } + } elseif($c1 >= "\xe0" & $c1 <= "\xef"){ //looks like 3 bytes UTF8 + if($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf"){ //yeah, almost sure it's UTF8 already + $buf .= $c1 . $c2 . $c3; + $i = $i + 2; + } else { //not valid UTF8. Convert it. + $cc1 = (chr(ord($c1) / 64) | "\xc0"); + $cc2 = ($c1 & "\x3f") | "\x80"; + $buf .= $cc1 . $cc2; + } + } elseif($c1 >= "\xf0" & $c1 <= "\xf7"){ //looks like 4 bytes UTF8 + if($c2 >= "\x80" && $c2 <= "\xbf" && $c3 >= "\x80" && $c3 <= "\xbf" && $c4 >= "\x80" && $c4 <= "\xbf"){ //yeah, almost sure it's UTF8 already + $buf .= $c1 . $c2 . $c3; + $i = $i + 2; + } else { //not valid UTF8. Convert it. + $cc1 = (chr(ord($c1) / 64) | "\xc0"); + $cc2 = ($c1 & "\x3f") | "\x80"; + $buf .= $cc1 . $cc2; + } + } else { //doesn't look like UTF8, but should be converted + $cc1 = (chr(ord($c1) / 64) | "\xc0"); + $cc2 = (($c1 & "\x3f") | "\x80"); + $buf .= $cc1 . $cc2; + } + } elseif(($c1 & "\xc0") == "\x80"){ // needs conversion + if(isset(self::$win1252ToUtf8[ord($c1)])) { //found in Windows-1252 special cases + $buf .= self::$win1252ToUtf8[ord($c1)]; + } else { + $cc1 = (chr(ord($c1) / 64) | "\xc0"); + $cc2 = (($c1 & "\x3f") | "\x80"); + $buf .= $cc1 . $cc2; + } + } else { // it doesn't need convesion + $buf .= $c1; + } + } + return $buf; + } else { + return $text; + } + } + + static function toWin1252($text) { + if(is_array($text)) { + foreach($text as $k => $v) { + $text[$k] = self::toWin1252($v); + } + return $text; + } elseif(is_string($text)) { + return utf8_decode(str_replace(array_keys(self::$utf8ToWin1252), array_values(self::$utf8ToWin1252), self::toUTF8($text))); + } else { + return $text; + } + } + + static function toISO8859($text) { + return self::toWin1252($text); + } + + static function toLatin1($text) { + return self::toWin1252($text); + } + + static function fixUTF8($text){ + if(is_array($text)) { + foreach($text as $k => $v) { + $text[$k] = self::fixUTF8($v); + } + return $text; + } + + $last = ""; + while($last <> $text){ + $last = $text; + $text = self::toUTF8(utf8_decode(str_replace(array_keys(self::$utf8ToWin1252), array_values(self::$utf8ToWin1252), $text))); + } + $text = self::toUTF8(utf8_decode(str_replace(array_keys(self::$utf8ToWin1252), array_values(self::$utf8ToWin1252), $text))); + return $text; + } + + static function UTF8FixWin1252Chars($text){ + // If you received an UTF-8 string that was converted from Windows-1252 as it was ISO8859-1 + // (ignoring Windows-1252 chars from 80 to 9F) use this function to fix it. + // See: http://en.wikipedia.org/wiki/Windows-1252 + + return str_replace(array_keys(self::$brokenUtf8ToUtf8), array_values(self::$brokenUtf8ToUtf8), $text); + } + + static function removeBOM($str=""){ + if(substr($str, 0,3) == pack("CCC",0xef,0xbb,0xbf)) { + $str=substr($str, 3); + } + return $str; + } +} \ No newline at end of file diff --git a/inc/JSLikeHTMLElement.php b/inc/JSLikeHTMLElement.php new file mode 100755 index 0000000..0557205 --- /dev/null +++ b/inc/JSLikeHTMLElement.php @@ -0,0 +1,110 @@ +registerNodeClass('DOMElement', 'JSLikeHTMLElement'); +* $doc->loadHTML('
Para 1
Para 2
'); +* $elem = $doc->getElementsByTagName('div')->item(0); +* +* // print innerHTML +* echo $elem->innerHTML; // prints '
Para 1
Para 2
' +* echo "\n\n"; +* +* // set innerHTML +* $elem->innerHTML = 'FiveFilters.org'; +* echo $elem->innerHTML; // prints 'FiveFilters.org' +* echo "\n\n"; +* +* // print document (with our changes) +* echo $doc->saveXML(); +* @endcode +* +* @author Keyvan Minoukadeh - http://www.keyvan.net - keyvan@keyvan.net +* @see http://fivefilters.org (the project this was written for) +*/ +class JSLikeHTMLElement extends DOMElement +{ + /** + * Used for setting innerHTML like it's done in JavaScript: + * @code + * $div->innerHTML = '
Chapter 2
The story begins...
'; + * @endcode + */ + public function __set($name, $value) { + if ($name == 'innerHTML') { + // first, empty the element + for ($x=$this->childNodes->length-1; $x>=0; $x--) { + $this->removeChild($this->childNodes->item($x)); + } + // $value holds our new inner HTML + if ($value != '') { + $f = $this->ownerDocument->createDocumentFragment(); + // appendXML() expects well-formed markup (XHTML) + $result = @$f->appendXML($value); // @ to suppress PHP warnings + if ($result) { + if ($f->hasChildNodes()) $this->appendChild($f); + } else { + // $value is probably ill-formed + $f = new DOMDocument(); + $value = mb_convert_encoding($value, 'HTML-ENTITIES', 'UTF-8'); + // Using will generate a warning, but so will bad HTML + // (and by this point, bad HTML is what we've got). + // We use it (and suppress the warning) because an HTML fragment will + // be wrapped around tags which we don't really want to keep. + // Note: despite the warning, if loadHTML succeeds it will return true. + $result = @$f->loadHTML(''.$value.''); + if ($result) { + $import = $f->getElementsByTagName('htmlfragment')->item(0); + foreach ($import->childNodes as $child) { + $importedNode = $this->ownerDocument->importNode($child, true); + $this->appendChild($importedNode); + } + } else { + // oh well, we tried, we really did. :( + // this element is now empty + } + } + } + } else { + $trace = debug_backtrace(); + trigger_error('Undefined property via __set(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE); + } + } + + /** + * Used for getting innerHTML like it's done in JavaScript: + * @code + * $string = $div->innerHTML; + * @endcode + */ + public function __get($name) + { + if ($name == 'innerHTML') { + $inner = ''; + foreach ($this->childNodes as $child) { + $inner .= $this->ownerDocument->saveXML($child); + } + return $inner; + } + + $trace = debug_backtrace(); + trigger_error('Undefined property via __get(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE); + return null; + } + + public function __toString() + { + return '['.$this->tagName.']'; + } +} +?> \ No newline at end of file diff --git a/inc/Readability.php b/inc/Readability.php new file mode 100755 index 0000000..52a37d5 --- /dev/null +++ b/inc/Readability.php @@ -0,0 +1,1103 @@ +init(); +echo $r->articleContent->innerHTML; +*/ + + +class Readability +{ + /* constants */ + const FLAG_STRIP_UNLIKELYS = 1; + const FLAG_WEIGHT_CLASSES = 2; + const FLAG_CLEAN_CONDITIONALLY = 4; + + public $version = '1.7.1-without-multi-page'; + public $convertLinksToFootnotes = false; + public $revertForcedParagraphElements = true; + public $articleTitle; + public $articleContent; + public $dom; + public $url = null; // optional - URL where HTML was retrieved + public $debug = false; + protected $body = null; // + protected $bodyCache = null; // Cache the body HTML in case we need to re-use it later + protected $flags = FLAG_CLEAN_CONDITIONALLY; // 1 | 2 | 4; // Start with all flags set. + protected $success = false; // indicates whether we were able to extract or not + + /** + * All of the regular expressions in use within readability. + * Defined up here so we don't instantiate them repeatedly in loops. + **/ + public $regexps = array( + 'unlikelyCandidates' => '/combx|comment|comments|community|disqus|extra|foot|header|menu|remark|rss|shoutbox|sidebar|sponsor|ad-break|agegate|pagination|pager|popup|tweet|twitter/i', + 'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i', + 'positive' => '/article|body|content|entry|hentry|main|page|pagination|post|text|blog|story/i', + 'negative' => '/combx|comment|comments|com-|contact|foot|footer|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget/i', + 'divToPElements' => '/<(a|blockquote|dl|div|ol|p|pre|table|ul)/i', + 'replaceBrs' => '/(]*>[ \n\r\t]*){2,}/i', + 'replaceFonts' => '/<(\/?)font[^>]*>/i', + // 'trimRe' => '/^\s+|\s+$/g', // PHP has trim() + 'normalize' => '/\s{2,}/', + 'killBreaks' => '/((\s| ?)*){1,}/', + 'video' => '/http:\/\/(www\.)?(youtube|vimeo|dailymotion)\.com/i', + 'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i' + ); + + /** + * Create instance of Readability + * @param string UTF-8 encoded string + * @param string (optional) URL associated with HTML (used for footnotes) + */ + function __construct($html, $url=null) + { + /* Turn all double br's into p's */ + $html = preg_replace($this->regexps['replaceBrs'], '
', $html); + $html = preg_replace($this->regexps['replaceFonts'], '<$1span>', $html); + $html = mb_convert_encoding($html, 'HTML-ENTITIES', "UTF-8"); + $this->dom = new DOMDocument(); + $this->dom->preserveWhiteSpace = false; + $this->dom->registerNodeClass('DOMElement', 'JSLikeHTMLElement'); + if (trim($html) == '') $html = ''; + @$this->dom->loadHTML($html); + $this->url = $url; + } + + /** + * Get article title element + * @return DOMElement + */ + public function getTitle() { + return $this->articleTitle; + } + + /** + * Get article content element + * @return DOMElement + */ + public function getContent() { + return $this->articleContent; + } + + /** + * Runs readability. + * + * Workflow: + * 1. Prep the document by removing script tags, css, etc. + * 2. Build readability's DOM tree. + * 3. Grab the article content from the current dom tree. + * 4. Replace the current DOM tree with the new one. + * 5. Read peacefully. + * + * @return boolean true if we found content, false otherwise + **/ + public function init() + { + if (!isset($this->dom->documentElement)) return false; + $this->removeScripts($this->dom); + //die($this->getInnerHTML($this->dom->documentElement)); + + // Assume successful outcome + $this->success = true; + + $bodyElems = $this->dom->getElementsByTagName('body'); + if ($bodyElems->length > 0) { + if ($this->bodyCache == null) { + $this->bodyCache = $bodyElems->item(0)->innerHTML; + } + if ($this->body == null) { + $this->body = $bodyElems->item(0); + } + } + + $this->prepDocument(); + + //die($this->dom->documentElement->parentNode->nodeType); + //$this->setInnerHTML($this->dom->documentElement, $this->getInnerHTML($this->dom->documentElement)); + //die($this->getInnerHTML($this->dom->documentElement)); + + /* Build readability's DOM tree */ + $overlay = $this->dom->createElement('div'); + $innerDiv = $this->dom->createElement('div'); + $articleTitle = $this->getArticleTitle(); + $articleContent = $this->grabArticle(); + + if (!$articleContent) { + $this->success = false; + $articleContent = $this->dom->createElement('div'); + $articleContent->setAttribute('id', 'readability-content'); + $articleContent->innerHTML = '
Sorry, Readability was unable to parse this page for content.
'; + } + + $overlay->setAttribute('id', 'readOverlay'); + $innerDiv->setAttribute('id', 'readInner'); + + /* Glue the structure of our document together. */ + $innerDiv->appendChild($articleTitle); + $innerDiv->appendChild($articleContent); + $overlay->appendChild($innerDiv); + + /* Clear the old HTML, insert the new content. */ + $this->body->innerHTML = ''; + $this->body->appendChild($overlay); + //document.body.insertBefore(overlay, document.body.firstChild); + $this->body->removeAttribute('style'); + + $this->postProcessContent($articleContent); + + // Set title and content instance variables + $this->articleTitle = $articleTitle; + $this->articleContent = $articleContent; + + return $this->success; + } + + /** + * Debug + */ + protected function dbg($msg) { + if ($this->debug) echo '* ',$msg, '
', "\n"; + } + + /** + * Run any post-process modifications to article content as necessary. + * + * @param DOMElement + * @return void + */ + public function postProcessContent($articleContent) { + if ($this->convertLinksToFootnotes && !preg_match('/wikipedia\.org/', @$this->url)) { + $this->addFootnotes($articleContent); + } + } + + /** + * Get the article title as an H1. + * + * @return DOMElement + */ + protected function getArticleTitle() { + $curTitle = ''; + $origTitle = ''; + + try { + $curTitle = $origTitle = $this->getInnerText($this->dom->getElementsByTagName('title')->item(0)); + } catch(Exception $e) {} + + if (preg_match('/ [\|\-] /', $curTitle)) + { + $curTitle = preg_replace('/(.*)[\|\-] .*/i', '$1', $origTitle); + + if (count(explode(' ', $curTitle)) < 3) { + $curTitle = preg_replace('/[^\|\-]*[\|\-](.*)/i', '$1', $origTitle); + } + } + else if (strpos($curTitle, ': ') !== false) + { + $curTitle = preg_replace('/.*:(.*)/i', '$1', $origTitle); + + if (count(explode(' ', $curTitle)) < 3) { + $curTitle = preg_replace('/[^:]*[:](.*)/i','$1', $origTitle); + } + } + else if(strlen($curTitle) > 150 || strlen($curTitle) < 15) + { + $hOnes = $this->dom->getElementsByTagName('h1'); + if($hOnes->length == 1) + { + $curTitle = $this->getInnerText($hOnes->item(0)); + } + } + + $curTitle = trim($curTitle); + + if (count(explode(' ', $curTitle)) <= 4) { + $curTitle = $origTitle; + } + + $articleTitle = $this->dom->createElement('h1'); + $articleTitle->innerHTML = $curTitle; + + return $articleTitle; + } + + /** + * Prepare the HTML document for readability to scrape it. + * This includes things like stripping javascript, CSS, and handling terrible markup. + * + * @return void + **/ + protected function prepDocument() { + /** + * In some cases a body element can't be found (if the HTML is totally hosed for example) + * so we create a new body node and append it to the document. + */ + if ($this->body == null) + { + $this->body = $this->dom->createElement('body'); + $this->dom->documentElement->appendChild($this->body); + } + $this->body->setAttribute('id', 'readabilityBody'); + + /* Remove all style tags in head */ + $styleTags = $this->dom->getElementsByTagName('style'); + for ($i = $styleTags->length-1; $i >= 0; $i--) + { + $styleTags->item($i)->parentNode->removeChild($styleTags->item($i)); + } + + /* Turn all double br's into p's */ + /* Note, this is pretty costly as far as processing goes. Maybe optimize later. */ + //document.body.innerHTML = document.body.innerHTML.replace(readability.regexps.replaceBrs, '
').replace(readability.regexps.replaceFonts, '<$1span>'); + // We do this in the constructor for PHP as that's when we have raw HTML - before parsing it into a DOM tree. + // Manipulating innerHTML as it's done in JS is not possible in PHP. + } + + /** + * For easier reading, convert this document to have footnotes at the bottom rather than inline links. + * @see http://www.roughtype.com/archives/2010/05/experiments_in.php + * + * @return void + **/ + public function addFootnotes($articleContent) { + $footnotesWrapper = $this->dom->createElement('div'); + $footnotesWrapper->setAttribute('id', 'readability-footnotes'); + $footnotesWrapper->innerHTML = '
References
'; + + $articleFootnotes = $this->dom->createElement('ol'); + $articleFootnotes->setAttribute('id', 'readability-footnotes-list'); + $footnotesWrapper->appendChild($articleFootnotes); + + $articleLinks = $articleContent->getElementsByTagName('a'); + + $linkCount = 0; + for ($i = 0; $i < $articleLinks->length; $i++) + { + $articleLink = $articleLinks->item($i); + $footnoteLink = $articleLink->cloneNode(true); + $refLink = $this->dom->createElement('a'); + $footnote = $this->dom->createElement('li'); + $linkDomain = @parse_url($footnoteLink->getAttribute('href'), PHP_URL_HOST); + if (!$linkDomain && isset($this->url)) $linkDomain = @parse_url($this->url, PHP_URL_HOST); + //linkDomain = footnoteLink.host ? footnoteLink.host : document.location.host, + $linkText = $this->getInnerText($articleLink); + + if ((strpos($articleLink->getAttribute('class'), 'readability-DoNotFootnote') !== false) || preg_match($this->regexps['skipFootnoteLink'], $linkText)) { + continue; + } + + $linkCount++; + + /** Add a superscript reference after the article link */ + $refLink->setAttribute('href', '#readabilityFootnoteLink-' . $linkCount); + $refLink->innerHTML = '^{[' . $linkCount . ']}'; + $refLink->setAttribute('class', 'readability-DoNotFootnote'); + $refLink->setAttribute('style', 'color: inherit;'); + + //TODO: does this work or should we use DOMNode.isSameNode()? + if ($articleLink->parentNode->lastChild == $articleLink) { + $articleLink->parentNode->appendChild($refLink); + } else { + $articleLink->parentNode->insertBefore($refLink, $articleLink->nextSibling); + } + + $articleLink->setAttribute('style', 'color: inherit; text-decoration: none;'); + $articleLink->setAttribute('name', 'readabilityLink-' . $linkCount); + + $footnote->innerHTML = '^{^} '; + + $footnoteLink->innerHTML = ($footnoteLink->getAttribute('title') != '' ? $footnoteLink->getAttribute('title') : $linkText); + $footnoteLink->setAttribute('name', 'readabilityFootnoteLink-' . $linkCount); + + $footnote->appendChild($footnoteLink); + if ($linkDomain) $footnote->innerHTML = $footnote->innerHTML . ' (' . $linkDomain . ')'; + + $articleFootnotes->appendChild($footnote); + } + + if ($linkCount > 0) { + $articleContent->appendChild($footnotesWrapper); + } + } + + /** + * Reverts P elements with class 'readability-styled' + * to text nodes - which is what they were before. + * + * @param DOMElement + * @return void + */ + function revertReadabilityStyledElements($articleContent) { + $xpath = new DOMXPath($articleContent->ownerDocument); + $elems = $xpath->query('.//p[@class="readability-styled"]', $articleContent); + //$elems = $articleContent->getElementsByTagName('p'); + for ($i = $elems->length-1; $i >= 0; $i--) { + $e = $elems->item($i); + $e->parentNode->replaceChild($articleContent->ownerDocument->createTextNode($e->textContent), $e); + //if ($e->hasAttribute('class') && $e->getAttribute('class') == 'readability-styled') { + // $e->parentNode->replaceChild($this->dom->createTextNode($e->textContent), $e); + //} + } + } + + /** + * Prepare the article node for display. Clean out any inline styles, + * iframes, forms, strip extraneous
tags, etc. + * + * @param DOMElement + * @return void + */ + function prepArticle($articleContent) { + $this->cleanStyles($articleContent); + $this->killBreaks($articleContent); + if ($this->revertForcedParagraphElements) { + $this->revertReadabilityStyledElements($articleContent); + } + + /* Clean out junk from the article content */ + $this->cleanConditionally($articleContent, 'form'); + $this->clean($articleContent, 'object'); + $this->clean($articleContent, 'h1'); + + /** + * If there is only one h2, they are probably using it + * as a header and not a subheader, so remove it since we already have a header. + ***/ + if ($articleContent->getElementsByTagName('h2')->length == 1) { + $this->clean($articleContent, 'h2'); + } + $this->clean($articleContent, 'iframe'); + + $this->cleanHeaders($articleContent); + + /* Do these last as the previous stuff may have removed junk that will affect these */ + $this->cleanConditionally($articleContent, 'table'); + $this->cleanConditionally($articleContent, 'ul'); + $this->cleanConditionally($articleContent, 'div'); + + /* Remove extra paragraphs */ + $articleParagraphs = $articleContent->getElementsByTagName('p'); + for ($i = $articleParagraphs->length-1; $i >= 0; $i--) + { + $imgCount = $articleParagraphs->item($i)->getElementsByTagName('img')->length; + $embedCount = $articleParagraphs->item($i)->getElementsByTagName('embed')->length; + $objectCount = $articleParagraphs->item($i)->getElementsByTagName('object')->length; + + if ($imgCount === 0 && $embedCount === 0 && $objectCount === 0 && $this->getInnerText($articleParagraphs->item($i), false) == '') + { + $articleParagraphs->item($i)->parentNode->removeChild($articleParagraphs->item($i)); + } + } + + try { + $articleContent->innerHTML = preg_replace('/]*>\s*
innerHTML); + //articleContent.innerHTML = articleContent.innerHTML.replace(/]*>\s*
dbg("Cleaning innerHTML of breaks failed. This is an IE strict-block-elements bug. Ignoring.: " . $e); + } + } + + /** + * Initialize a node with the readability object. Also checks the + * className/id for special names to add to its score. + * + * @param Element + * @return void + **/ + protected function initializeNode($node) { + $readability = $this->dom->createAttribute('readability'); + $readability->value = 0; // this is our contentScore + $node->setAttributeNode($readability); + + switch (strtoupper($node->tagName)) { // unsure if strtoupper is needed, but using it just in case + case 'DIV': + $readability->value += 5; + break; + + case 'PRE': + case 'TD': + case 'BLOCKQUOTE': + $readability->value += 3; + break; + + case 'ADDRESS': + case 'OL': + case 'UL': + case 'DL': + case 'DD': + case 'DT': + case 'LI': + case 'FORM': + $readability->value -= 3; + break; + + case 'H1': + case 'H2': + case 'H3': + case 'H4': + case 'H5': + case 'H6': + case 'TH': + $readability->value -= 5; + break; + } + $readability->value += $this->getClassWeight($node); + } + + /*** + * grabArticle - Using a variety of metrics (content score, classname, element types), find the content that is + * most likely to be the stuff a user wants to read. Then return it wrapped up in a div. + * + * @return DOMElement + **/ + protected function grabArticle($page=null) { + $stripUnlikelyCandidates = $this->flagIsActive(self::FLAG_STRIP_UNLIKELYS); + if (!$page) $page = $this->dom; + $allElements = $page->getElementsByTagName('*'); + /** + * First, node prepping. Trash nodes that look cruddy (like ones with the class name "comment", etc), and turn divs + * into P tags where they have been used inappropriately (as in, where they contain no other block level elements.) + * + * Note: Assignment from index for performance. See http://www.peachpit.com/articles/article.aspx?p=31567&seqNum=5 + * TODO: Shouldn't this be a reverse traversal? + **/ + $node = null; + $nodesToScore = array(); + for ($nodeIndex = 0; ($node = $allElements->item($nodeIndex)); $nodeIndex++) { + //for ($nodeIndex=$targetList->length-1; $nodeIndex >= 0; $nodeIndex--) { + //$node = $targetList->item($nodeIndex); + $tagName = strtoupper($node->tagName); + /* Remove unlikely candidates */ + if ($stripUnlikelyCandidates) { + $unlikelyMatchString = $node->getAttribute('class') . $node->getAttribute('id'); + if ( + preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) && + !preg_match($this->regexps['okMaybeItsACandidate'], $unlikelyMatchString) && + $tagName != 'BODY' + ) + { + $this->dbg('Removing unlikely candidate - ' . $unlikelyMatchString); + //$nodesToRemove[] = $node; + $node->parentNode->removeChild($node); + $nodeIndex--; + continue; + } + } + + if ($tagName == 'P' || $tagName == 'TD' || $tagName == 'PRE') { + $nodesToScore[] = $node; + } + + /* Turn all divs that don't have children block level elements into p's */ + if ($tagName == 'DIV') { + if (!preg_match($this->regexps['divToPElements'], $node->innerHTML)) { + //$this->dbg('Altering div to p'); + $newNode = $this->dom->createElement('p'); + try { + $newNode->innerHTML = $node->innerHTML; + //$nodesToReplace[] = array('new'=>$newNode, 'old'=>$node); + $node->parentNode->replaceChild($newNode, $node); + $nodeIndex--; + $nodesToScore[] = $node; // or $newNode? + } + catch(Exception $e) { + $this->dbg('Could not alter div to p, reverting back to div.: ' . $e); + } + } + else + { + // EXPERIMENTAL + // TODO: change these p elements back to text nodes after processing + for ($i = 0, $il = $node->childNodes->length; $i < $il; $i++) { + $childNode = $node->childNodes->item($i); + if ($childNode->nodeType == 3) { // XML_TEXT_NODE + //$this->dbg('replacing text node with a p tag with the same content.'); + $p = $this->dom->createElement('p'); + $p->innerHTML = $childNode->nodeValue; + $p->setAttribute('style', 'display: inline;'); + $p->setAttribute('class', 'readability-styled'); + $childNode->parentNode->replaceChild($p, $childNode); + } + } + } + } + } + + /** + * Loop through all paragraphs, and assign a score to them based on how content-y they look. + * Then add their score to their parent node. + * + * A score is determined by things like number of commas, class names, etc. Maybe eventually link density. + **/ + $candidates = array(); + for ($pt=0; $pt < count($nodesToScore); $pt++) { + $parentNode = $nodesToScore[$pt]->parentNode; + // $grandParentNode = $parentNode ? $parentNode->parentNode : null; + $grandParentNode = !$parentNode ? null : (($parentNode->parentNode instanceof DOMElement) ? $parentNode->parentNode : null); + $innerText = $this->getInnerText($nodesToScore[$pt]); + + if (!$parentNode || !isset($parentNode->tagName)) { + continue; + } + + /* If this paragraph is less than 25 characters, don't even count it. */ + if(strlen($innerText) < 25) { + continue; + } + + /* Initialize readability data for the parent. */ + if (!$parentNode->hasAttribute('readability')) + { + $this->initializeNode($parentNode); + $candidates[] = $parentNode; + } + + /* Initialize readability data for the grandparent. */ + if ($grandParentNode && !$grandParentNode->hasAttribute('readability') && isset($grandParentNode->tagName)) + { + $this->initializeNode($grandParentNode); + $candidates[] = $grandParentNode; + } + + $contentScore = 0; + + /* Add a point for the paragraph itself as a base. */ + $contentScore++; + + /* Add points for any commas within this paragraph */ + $contentScore += count(explode(',', $innerText)); + + /* For every 100 characters in this paragraph, add another point. Up to 3 points. */ + $contentScore += min(floor(strlen($innerText) / 100), 3); + + /* Add the score to the parent. The grandparent gets half. */ + $parentNode->getAttributeNode('readability')->value += $contentScore; + + if ($grandParentNode) { + $grandParentNode->getAttributeNode('readability')->value += $contentScore/2; + } + } + + /** + * After we've calculated scores, loop through all of the possible candidate nodes we found + * and find the one with the highest score. + **/ + $topCandidate = null; + for ($c=0, $cl=count($candidates); $c < $cl; $c++) + { + /** + * Scale the final candidates score based on link density. Good content should have a + * relatively small link density (5% or less) and be mostly unaffected by this operation. + **/ + $readability = $candidates[$c]->getAttributeNode('readability'); + $readability->value = $readability->value * (1-$this->getLinkDensity($candidates[$c])); + + $this->dbg('Candidate: ' . $candidates[$c]->tagName . ' (' . $candidates[$c]->getAttribute('class') . ':' . $candidates[$c]->getAttribute('id') . ') with score ' . $readability->value); + + if (!$topCandidate || $readability->value > (int)$topCandidate->getAttribute('readability')) { + $topCandidate = $candidates[$c]; + } + } + + /** + * If we still have no top candidate, just use the body as a last resort. + * We also have to copy the body node so it is something we can modify. + **/ + if ($topCandidate === null || strtoupper($topCandidate->tagName) == 'BODY') + { + $topCandidate = $this->dom->createElement('div'); + if ($page instanceof DOMDocument) { + if (!isset($page->documentElement)) { + // we don't have a body either? what a mess! :) + } else { + $topCandidate->innerHTML = $page->documentElement->innerHTML; + $page->documentElement->innerHTML = ''; + $page->documentElement->appendChild($topCandidate); + } + } else { + $topCandidate->innerHTML = $page->innerHTML; + $page->innerHTML = ''; + $page->appendChild($topCandidate); + } + $this->initializeNode($topCandidate); + } + + /** + * Now that we have the top candidate, look through its siblings for content that might also be related. + * Things like preambles, content split by ads that we removed, etc. + **/ + $articleContent = $this->dom->createElement('div'); + $articleContent->setAttribute('id', 'readability-content'); + $siblingScoreThreshold = max(10, ((int)$topCandidate->getAttribute('readability')) * 0.2); + $siblingNodes = $topCandidate->parentNode->childNodes; + if (!isset($siblingNodes)) { + $siblingNodes = new stdClass; + $siblingNodes->length = 0; + } + + for ($s=0, $sl=$siblingNodes->length; $s < $sl; $s++) + { + $siblingNode = $siblingNodes->item($s); + $append = false; + + $this->dbg('Looking at sibling node: ' . $siblingNode->nodeName . (($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability')) ? (' with score ' . $siblingNode->getAttribute('readability')) : '')); + + //dbg('Sibling has score ' . ($siblingNode->readability ? siblingNode.readability.contentScore : 'Unknown')); + + if ($siblingNode === $topCandidate) + // or if ($siblingNode->isSameNode($topCandidate)) + { + $append = true; + } + + $contentBonus = 0; + /* Give a bonus if sibling nodes and top candidates have the example same classname */ + if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->getAttribute('class') == $topCandidate->getAttribute('class') && $topCandidate->getAttribute('class') != '') { + $contentBonus += ((int)$topCandidate->getAttribute('readability')) * 0.2; + } + + if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability') && (((int)$siblingNode->getAttribute('readability')) + $contentBonus) >= $siblingScoreThreshold) + { + $append = true; + } + + if (strtoupper($siblingNode->nodeName) == 'P') { + $linkDensity = $this->getLinkDensity($siblingNode); + $nodeContent = $this->getInnerText($siblingNode); + $nodeLength = strlen($nodeContent); + + if ($nodeLength > 80 && $linkDensity < 0.25) + { + $append = true; + } + else if ($nodeLength < 80 && $linkDensity === 0 && preg_match('/\.( |$)/', $nodeContent)) + { + $append = true; + } + } + + /* Look for a special classname */ + if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('class') && $siblingNode->getAttribute('class') != '') + { + if (preg_match($this->regexps['okMaybeItsACandidate'], $siblingNode->getAttribute('class'))) { + $append = true; + } + } + + /* Look for a special classname */ + if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('id') && $siblingNode->getAttribute('id') != '') + { + if (preg_match($this->regexps['okMaybeItsACandidate'], $siblingNode->getAttribute('id'))) { + $append = true; + } + } + + + if ($append) + { + $this->dbg('Appending node: ' . $siblingNode->nodeName); + + $nodeToAppend = null; + $sibNodeName = strtoupper($siblingNode->nodeName); + if ($sibNodeName != 'DIV' && $sibNodeName != 'P') { + /* We have a node that isn't a common block level element, like a form or td tag. Turn it into a div so it doesn't get filtered out later by accident. */ + + $this->dbg('Altering siblingNode of ' . $sibNodeName . ' to div.'); + $nodeToAppend = $this->dom->createElement('div'); + try { + $nodeToAppend->setAttribute('id', $siblingNode->getAttribute('id')); + $nodeToAppend->innerHTML = $siblingNode->innerHTML; + } + catch(Exception $e) + { + $this->dbg('Could not alter siblingNode to div, reverting back to original.'); + $nodeToAppend = $siblingNode; + $s--; + $sl--; + } + } else { + $nodeToAppend = $siblingNode; + $s--; + $sl--; + } + + /* To ensure a node does not interfere with readability styles, remove its classnames */ + $nodeToAppend->removeAttribute('class'); + + /* Append sibling and subtract from our list because it removes the node when you append to another node */ + $articleContent->appendChild($nodeToAppend); + } + } + + /** + * So we have all of the content that we need. Now we clean it up for presentation. + **/ + $this->prepArticle($articleContent); + + /** + * Now that we've gone through the full algorithm, check to see if we got any meaningful content. + * If we didn't, we may need to re-run grabArticle with different flags set. This gives us a higher + * likelihood of finding the content, and the sieve approach gives us a higher likelihood of + * finding the -right- content. + **/ + if (strlen($this->getInnerText($articleContent, false)) < 250) + { + // TODO: find out why element disappears sometimes, e.g. for this URL http://www.businessinsider.com/6-hedge-fund-etfs-for-average-investors-2011-7 + // in the meantime, we check and create an empty element if it's not there. + if (!isset($this->body->childNodes)) $this->body = $this->dom->createElement('body'); + $this->body->innerHTML = $this->bodyCache; + + if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS)) { + $this->removeFlag(self::FLAG_STRIP_UNLIKELYS); + return $this->grabArticle($this->body); + } + else if ($this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) { + $this->removeFlag(self::FLAG_WEIGHT_CLASSES); + return $this->grabArticle($this->body); + } + else if ($this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) { + $this->removeFlag(self::FLAG_CLEAN_CONDITIONALLY); + return $this->grabArticle($this->body); + } + else { + return false; + } + } + return $articleContent; + } + + /** + * Remove script tags from document + * + * @param DOMElement + * @return void + */ + public function removeScripts($doc) { + $scripts = $doc->getElementsByTagName('script'); + for($i = $scripts->length-1; $i >= 0; $i--) + { + $scripts->item($i)->parentNode->removeChild($scripts->item($i)); + } + } + + /** + * Get the inner text of a node. + * This also strips out any excess whitespace to be found. + * + * @param DOMElement $ + * @param boolean $normalizeSpaces (default: true) + * @return string + **/ + public function getInnerText($e, $normalizeSpaces=true) { + $textContent = ''; + + if (!isset($e->textContent) || $e->textContent == '') { + return ''; + } + + $textContent = trim($e->textContent); + + if ($normalizeSpaces) { + return preg_replace($this->regexps['normalize'], ' ', $textContent); + } else { + return $textContent; + } + } + + /** + * Get the number of times a string $s appears in the node $e. + * + * @param DOMElement $e + * @param string - what to count. Default is "," + * @return number (integer) + **/ + public function getCharCount($e, $s=',') { + return substr_count($this->getInnerText($e), $s); + } + + /** + * Remove the style attribute on every $e and under. + * + * @param DOMElement $e + * @return void + */ + public function cleanStyles($e) { + if (!is_object($e)) return; + $elems = $e->getElementsByTagName('*'); + foreach ($elems as $elem) { + $elem->removeAttribute('style'); + } + } + + /** + * Get the density of links as a percentage of the content + * This is the amount of text that is inside a link divided by the total text in the node. + * + * @param DOMElement $e + * @return number (float) + */ + public function getLinkDensity($e) { + $links = $e->getElementsByTagName('a'); + $textLength = strlen($this->getInnerText($e)); + $linkLength = 0; + for ($i=0, $il=$links->length; $i < $il; $i++) + { + $linkLength += strlen($this->getInnerText($links->item($i))); + } + if ($textLength > 0) { + return $linkLength / $textLength; + } else { + return 0; + } + } + + /** + * Get an elements class/id weight. Uses regular expressions to tell if this + * element looks good or bad. + * + * @param DOMElement $e + * @return number (Integer) + */ + public function getClassWeight($e) { + if(!$this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) { + return 0; + } + + $weight = 0; + + /* Look for a special classname */ + if ($e->hasAttribute('class') && $e->getAttribute('class') != '') + { + if (preg_match($this->regexps['negative'], $e->getAttribute('class'))) { + $weight -= 25; + } + if (preg_match($this->regexps['positive'], $e->getAttribute('class'))) { + $weight += 25; + } + } + + /* Look for a special ID */ + if ($e->hasAttribute('id') && $e->getAttribute('id') != '') + { + if (preg_match($this->regexps['negative'], $e->getAttribute('id'))) { + $weight -= 25; + } + if (preg_match($this->regexps['positive'], $e->getAttribute('id'))) { + $weight += 25; + } + } + return $weight; + } + + /** + * Remove extraneous break tags from a node. + * + * @param DOMElement $node + * @return void + */ + public function killBreaks($node) { + $html = $node->innerHTML; + $html = preg_replace($this->regexps['killBreaks'], '
', $html); + $node->innerHTML = $html; + } + + /** + * Clean a node of all elements of type "tag". + * (Unless it's a youtube/vimeo video. People love movies.) + * + * @param DOMElement $e + * @param string $tag + * @return void + */ + public function clean($e, $tag) { + $targetList = $e->getElementsByTagName($tag); + $isEmbed = ($tag == 'object' || $tag == 'embed'); + + for ($y=$targetList->length-1; $y >= 0; $y--) { + /* Allow youtube and vimeo videos through as people usually want to see those. */ + if ($isEmbed) { + $attributeValues = ''; + for ($i=0, $il=$targetList->item($y)->attributes->length; $i < $il; $i++) { + $attributeValues .= $targetList->item($y)->attributes->item($i)->value . '|'; // DOMAttr? (TODO: test) + } + + /* First, check the elements attributes to see if any of them contain youtube or vimeo */ + if (preg_match($this->regexps['video'], $attributeValues)) { + continue; + } + + /* Then check the elements inside this element for the same. */ + if (preg_match($this->regexps['video'], $targetList->item($y)->innerHTML)) { + continue; + } + } + $targetList->item($y)->parentNode->removeChild($targetList->item($y)); + } + } + + /** + * Clean an element of all tags of type "tag" if they look fishy. + * "Fishy" is an algorithm based on content length, classnames, + * link density, number of images & embeds, etc. + * + * @param DOMElement $e + * @param string $tag + * @return void + */ + public function cleanConditionally($e, $tag) { + if (!$this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) { + return; + } + + $tagsList = $e->getElementsByTagName($tag); + $curTagsLength = $tagsList->length; + + /** + * Gather counts for other typical elements embedded within. + * Traverse backwards so we can remove nodes at the same time without effecting the traversal. + * + * TODO: Consider taking into account original contentScore here. + */ + for ($i=$curTagsLength-1; $i >= 0; $i--) { + $weight = $this->getClassWeight($tagsList->item($i)); + $contentScore = ($tagsList->item($i)->hasAttribute('readability')) ? (int)$tagsList->item($i)->getAttribute('readability') : 0; + + $this->dbg('Cleaning Conditionally ' . $tagsList->item($i)->tagName . ' (' . $tagsList->item($i)->getAttribute('class') . ':' . $tagsList->item($i)->getAttribute('id') . ')' . (($tagsList->item($i)->hasAttribute('readability')) ? (' with score ' . $tagsList->item($i)->getAttribute('readability')) : '')); + + if ($weight + $contentScore < 0) { + $tagsList->item($i)->parentNode->removeChild($tagsList->item($i)); + } + else if ( $this->getCharCount($tagsList->item($i), ',') < 10) { + /** + * If there are not very many commas, and the number of + * non-paragraph elements is more than paragraphs or other ominous signs, remove the element. + **/ + $p = $tagsList->item($i)->getElementsByTagName('p')->length; + $img = $tagsList->item($i)->getElementsByTagName('img')->length; + $li = $tagsList->item($i)->getElementsByTagName('li')->length-100; + $input = $tagsList->item($i)->getElementsByTagName('input')->length; + + $embedCount = 0; + $embeds = $tagsList->item($i)->getElementsByTagName('embed'); + for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) { + if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) { + $embedCount++; + } + } + + $linkDensity = $this->getLinkDensity($tagsList->item($i)); + $contentLength = strlen($this->getInnerText($tagsList->item($i))); + $toRemove = false; + + if ( $img > $p ) { + $toRemove = true; + } else if ($li > $p && $tag != 'ul' && $tag != 'ol') { + $toRemove = true; + } else if ( $input > floor($p/3) ) { + $toRemove = true; + } else if ($contentLength < 25 && ($img === 0 || $img > 2) ) { + $toRemove = true; + } else if($weight < 25 && $linkDensity > 0.2) { + $toRemove = true; + } else if($weight >= 25 && $linkDensity > 0.5) { + $toRemove = true; + } else if(($embedCount == 1 && $contentLength < 75) || $embedCount > 1) { + $toRemove = true; + } + + if ($toRemove) { + $tagsList->item($i)->parentNode->removeChild($tagsList->item($i)); + } + } + } + } + + /** + * Clean out spurious headers from an Element. Checks things like classnames and link density. + * + * @param DOMElement $e + * @return void + */ + public function cleanHeaders($e) { + for ($headerIndex = 1; $headerIndex < 3; $headerIndex++) { + $headers = $e->getElementsByTagName('h' . $headerIndex); + for ($i=$headers->length-1; $i >=0; $i--) { + if ($this->getClassWeight($headers->item($i)) < 0 || $this->getLinkDensity($headers->item($i)) > 0.33) { + $headers->item($i)->parentNode->removeChild($headers->item($i)); + } + } + } + } + + public function flagIsActive($flag) { + return ($this->flags & $flag) > 0; + } + + public function addFlag($flag) { + $this->flags = $this->flags | $flag; + } + + public function removeFlag($flag) { + $this->flags = $this->flags & ~$flag; + } +} +?> \ No newline at end of file diff --git a/inc/index.html b/inc/index.html new file mode 100755 index 0000000..e69de29 diff --git a/inc/rain.tpl.class.php b/inc/rain.tpl.class.php new file mode 100755 index 0000000..ea83b2c --- /dev/null +++ b/inc/rain.tpl.class.php @@ -0,0 +1,1043 @@ +), stylesheet (), script (