moparisthebest/wallabag
1
0
Fork 0
mirror of https://github.com/moparisthebest/wallabag synced 2024-10-31 23:45:02 -04:00
Code Issues Releases Wiki Activity

Begin to properly import Readability classes in Symfony

Browse Source
This commit is contained in:
Fabien Meurillon 2014-08-04 01:56:12 +02:00
parent 0db3ad4bb2
commit 6405fdea2a
15 changed files with 649 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
app/AppKernel.php
View File

@ -20,6 +20,7 @@ class AppKernel extends Kernel
new Wallabag\Bundle\CoreBundle\WallabagCoreBundle(), new Wallabag\Bundle\CoreBundle\WallabagCoreBundle(),
new Wallabag\Bundle\ApiBundle\WallabagApiBundle(), new Wallabag\Bundle\ApiBundle\WallabagApiBundle(),
new Wallabag\Bundle\CliBundle\WallabagCliBundle(), new Wallabag\Bundle\CliBundle\WallabagCliBundle(),
new Wallabag\Bundle\ReadabilityBundle\WallabagReadabilityBundle(),
); );
if (in_array($this->getEnvironment(), array('dev', 'test'))) { if (in_array($this->getEnvironment(), array('dev', 'test'))) {

5
app/config/routing.yml
View File

@ -1,3 +1,8 @@
wallabag_readability:
resource: "@WallabagReadabilityBundle/Controller/"
type: annotation
prefix: /
wallabag_cli: wallabag_cli:
resource: "@WallabagCliBundle/Controller/" resource: "@WallabagCliBundle/Controller/"
type: annotation type: annotation

3
composer.json
View File

@ -19,7 +19,8 @@
"sensio/framework-extra-bundle": "~3.0", "sensio/framework-extra-bundle": "~3.0",
"incenteev/composer-parameter-handler": "~2.0", "incenteev/composer-parameter-handler": "~2.0",
"fivefilters/php-readability": "v1.0", "fivefilters/php-readability": "v1.0",
"friendsofsymfony/user-bundle": "2.0.x-dev" "friendsofsymfony/user-bundle": "2.0.x-dev",
"simplepie/simplepie": "1.3.1"
}, },
"require-dev": { "require-dev": {
"sensio/generator-bundle": "~2.3" "sensio/generator-bundle": "~2.3"

56
composer.lock generated
View File

@ -4,7 +4,7 @@
"Read more about it at http://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file", "Read more about it at http://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file",
"This file is @generated automatically" "This file is @generated automatically"
], ],
"hash": "4f4cbc95623d5596ec8cf7cb1e3e4b11", "hash": "aaca2ba5bd2f244555f16fb4cfa50fd4",
"packages": [ "packages": [
{ {
"name": "doctrine/annotations", "name": "doctrine/annotations",
@ -1138,6 +1138,60 @@
], ],
"time": "2014-05-22 23:27:44" "time": "2014-05-22 23:27:44"
}, },
{
"name": "simplepie/simplepie",
"version": "1.3.1",
"source": {
"type": "git",
"url": "https://github.com/simplepie/simplepie.git",
"reference": "ce53709778bc1e2e4deda1651b66e5081398d5cc"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/simplepie/simplepie/zipball/ce53709778bc1e2e4deda1651b66e5081398d5cc",
"reference": "ce53709778bc1e2e4deda1651b66e5081398d5cc",
"shasum": ""
},
"require": {
"php": ">=5.2.0"
},
"type": "library",
"autoload": {
"psr-0": {
"SimplePie": "library"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"BSD-3-Clause"
],
"authors": [
{
"name": "Ryan Parman",
"homepage": "http://ryanparman.com/",
"role": "Creator, alumnus developer"
},
{
"name": "Geoffrey Sneddon",
"homepage": "http://gsnedders.com/",
"role": "Alumnus developer"
},
{
"name": "Ryan McCue",
"email": "me@ryanmccue.info",
"homepage": "http://ryanmccue.info/",
"role": "Developer"
}
],
"description": "A simple Atom/RSS parsing library for PHP",
"homepage": "http://simplepie.org/",
"keywords": [
"atom",
"feeds",
"rss"
],
"time": "2012-10-30 17:54:03"
},
{ {
"name": "swiftmailer/swiftmailer", "name": "swiftmailer/swiftmailer",
"version": "v5.2.1", "version": "v5.2.1",

19
src/Wallabag/Bundle/ReadabilityBundle/Controller/DefaultController.php Normal file
View File

@ -0,0 +1,19 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\Controller;
use Symfony\Bundle\FrameworkBundle\Controller\Controller;
use Sensio\Bundle\FrameworkExtraBundle\Configuration\Route;
use Sensio\Bundle\FrameworkExtraBundle\Configuration\Template;
class DefaultController extends Controller
{
/**
* @Route("/hello/{name}")
* @Template()
*/
public function indexAction($name)
{
return array('name' => $name);
}
}

29
src/Wallabag/Bundle/ReadabilityBundle/DependencyInjection/Configuration.php Normal file
View File

@ -0,0 +1,29 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\DependencyInjection;
use Symfony\Component\Config\Definition\Builder\TreeBuilder;
use Symfony\Component\Config\Definition\ConfigurationInterface;
/**
* This is the class that validates and merges configuration from your app/config files
*
* To learn more see {@link http://symfony.com/doc/current/cookbook/bundles/extension.html#cookbook-bundles-extension-config-class}
*/
class Configuration implements ConfigurationInterface
{
/**
* {@inheritDoc}
*/
public function getConfigTreeBuilder()
{
$treeBuilder = new TreeBuilder();
$rootNode = $treeBuilder->root('wallabag_readability');
// Here you should define the parameters that are allowed to
// configure your bundle. See the documentation linked above for
// more information on that topic.
return $treeBuilder;
}
}

28
src/Wallabag/Bundle/ReadabilityBundle/DependencyInjection/WallabagReadabilityExtension.php Normal file
View File

@ -0,0 +1,28 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\DependencyInjection;
use Symfony\Component\DependencyInjection\ContainerBuilder;
use Symfony\Component\Config\FileLocator;
use Symfony\Component\HttpKernel\DependencyInjection\Extension;
use Symfony\Component\DependencyInjection\Loader;
/**
* This is the class that loads and manages your bundle configuration
*
* To learn more see {@link http://symfony.com/doc/current/cookbook/bundles/extension.html}
*/
class WallabagReadabilityExtension extends Extension
{
/**
* {@inheritDoc}
*/
public function load(array $configs, ContainerBuilder $container)
{
$configuration = new Configuration();
$config = $this->processConfiguration($configuration, $configs);
$loader = new Loader\XmlFileLoader($container, new FileLocator(__DIR__.'/../Resources/config'));
$loader->load('services.xml');
}
}

48
src/Wallabag/Bundle/ReadabilityBundle/Readability/WallabagReadability.php Normal file
View File

@ -0,0 +1,48 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\Readability;
class WallabagReadability extends \Readability
{
/**
* 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', $origTitle);
}
}
else if(strlen($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;
}
}

14
src/Wallabag/Bundle/ReadabilityBundle/Resources/config/services.xml Normal file
View File

@ -0,0 +1,14 @@
<?xml version="1.0" ?>
<container xmlns="http://symfony.com/schema/dic/services"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://symfony.com/schema/dic/services http://symfony.com/schema/dic/services/services-1.0.xsd">
<parameters>
<parameter key="wallabag_readability.url_extractor.class">Wallabag\Bundle\ReadabilityBundle\Url\UrlExtractor</parameter>
</parameters>
<services>
<service id="wallabag_readability.url_extractor" class="%wallabag_readability.url_extractor.class%"/>
</services>
</container>

1
src/Wallabag/Bundle/ReadabilityBundle/Resources/views/Default/index.html.twig Normal file
View File

@ -0,0 +1 @@
Hello {{ name }}!

17
src/Wallabag/Bundle/ReadabilityBundle/Tests/Controller/DefaultControllerTest.php Normal file
View File

@ -0,0 +1,17 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\Tests\Controller;
use Symfony\Bundle\FrameworkBundle\Test\WebTestCase;
class DefaultControllerTest extends WebTestCase
{
public function testIndex()
{
$client = static::createClient();
$crawler = $client->request('GET', '/hello/Fabien');
$this->assertTrue($crawler->filter('html:contains("Hello Fabien")')->count() > 0);
}
}

16
src/Wallabag/Bundle/ReadabilityBundle/Url/DummySingleItem.php Normal file
View File

@ -0,0 +1,16 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\Url;
class DummySingleItem {
public $url;
function __construct($url) { $this->url = $url; }
public function get_permalink() { return $this->url; }
public function get_title() { return null; }
public function get_date($format='') { return false; }
public function get_author($key=0) { return null; }
public function get_authors() { return null; }
public function get_description() { return ''; }
public function get_enclosure($key=0, $prefer=null) { return null; }
public function get_enclosures() { return null; }
public function get_categories() { return null; }
}

13
src/Wallabag/Bundle/ReadabilityBundle/Url/DummySingleItemFeed.php Normal file
View File

@ -0,0 +1,13 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle\Url;
class DummySingleItemFeed {
public $item;
function __construct($url) { $this->item = new DummySingleItem($url); }
public function get_title() { return ''; }
public function get_description() { return 'Content extracted from '.$this->item->url; }
public function get_link() { return $this->item->url; }
public function get_language() { return false; }
public function get_image_url() { return false; }
public function get_items($start=0, $max=1) { return array(0=>$this->item); }
}

392
src/Wallabag/Bundle/ReadabilityBundle/Url/UrlExtractor.php Normal file
View File

@ -0,0 +1,392 @@
<?php
/**
* wallabag, a read it later open source system
*
* @category wallabag
* @author Nicolas Lœuillet <hello@wallabag.org>
* @copyright 2013
* @license http://www.wtfpl.net/ see COPYING file
*/
namespace Wallabag\Bundle\ReadabilityBundle\Url;
use Wallabag\Bundle\ReadabilityBundle\Readability\WallabagReadability;
class UrlExtractor
{
public $url;
private $fingerprints = array(
// Posterous
'<meta name="generator" content="Posterous"' => array('hostname'=>'fingerprint.posterous.com', 'head'=>true),
// Blogger
'<meta content=\'blogger\' name=\'generator\'' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
'<meta name="generator" content="Blogger"' => array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
// WordPress (self-hosted and hosted)
'<meta name="generator" content="WordPress' => array('hostname'=>'fingerprint.wordpress.com', 'head'=>true)
);
private $user_agents = array( 'lifehacker.com' => 'PHP/5.2',
'gawker.com' => 'PHP/5.2',
'deadspin.com' => 'PHP/5.2',
'kotaku.com' => 'PHP/5.2',
'jezebel.com' => 'PHP/5.2',
'io9.com' => 'PHP/5.2',
'jalopnik.com' => 'PHP/5.2',
'gizmodo.com' => 'PHP/5.2',
'.wikipedia.org' => 'Mozilla/5.2'
);
private $content_type_exc = array(
'application/pdf' => array('action'=>'link', 'name'=>'PDF'),
'image' => array('action'=>'link', 'name'=>'Image'),
'audio' => array('action'=>'link', 'name'=>'Audio'),
'video' => array('action'=>'link', 'name'=>'Video')
);
private $rewrite_url = array(
// Rewrite public Google Docs URLs to point to HTML view:
// if a URL contains docs.google.com, replace /Doc? with /View?
'docs.google.com' => array('/Doc?' => '/View?'),
'tnr.com' => array('tnr.com/article/' => 'tnr.com/print/article/'),
'.m.wikipedia.org' => array('.m.wikipedia.org' => '.wikipedia.org')
);
private $rewrite_relative_urls = true;
private $error_message = '[unable to retrieve full-text content]';
function __construct($url)
{
$this->url = $url;
}
public function isCorrect($url) {
return filter_var($url, FILTER_VALIDATE_URL) !== FALSE;
}
public function extract($url) {
global $http, $extractor;
$extractor = new \ContentExtractor(dirname(__FILE__).'/../3rdparty/site_config/custom', dirname(__FILE__).'/../3rdparty/site_config/standard');
$extractor->fingerprints = $this->fingerprints;
$http = new \HumbleHttpAgent();
$http->userAgentMap = $this->user_agents;
$http->headerOnlyTypes = array_keys($this->content_type_exc);
$http->rewriteUrls = $this->rewrite_url;
$http->userAgentDefault = \HumbleHttpAgent::UA_PHP;
// configure SimplePie HTTP extension class to use our HumbleHttpAgent instance
\SimplePie_HumbleHttpAgent::set_agent($http);
$feed = new \SimplePie();
// some feeds use the text/html content type - force_feed tells SimplePie to process anyway
$feed->force_feed(true);
$feed->set_file_class('SimplePie_HumbleHttpAgent');
$feed->feed_url = $url;
$feed->set_autodiscovery_level(SIMPLEPIE_LOCATOR_NONE);
$feed->set_timeout(20);
$feed->enable_cache(false);
$feed->set_stupidly_fast(true);
$feed->enable_order_by_date(false); // we don't want to do anything to the feed
$feed->set_url_replacements(array());
// initialise the feed
// the @ suppresses notices which on some servers causes a 500 internal server error
$result = @$feed->init();
if ($result && (!is_array($feed->data) || count($feed->data) == 0)) {
die('Sorry, no feed items found');
}
// from now on, we'll identify ourselves as a browser
$http->userAgentDefault = \HumbleHttpAgent::UA_BROWSER;
unset($feed, $result);
$feed = new DummySingleItemFeed($url);
$items = $feed->get_items(0, 1);
// Request all feed items in parallel (if supported)
$urls_sanitized = array();
$urls = array();
foreach ($items as $key => $item) {
$permalink = htmlspecialchars_decode($item->get_permalink());
// Colons in URL path segments get encoded by SimplePie, yet some sites expect them unencoded
$permalink = str_replace('%3A', ':', $permalink);
if ($permalink) {
$urls_sanitized[] = $permalink;
}
$urls[$key] = $permalink;
}
$http->fetchAll($urls_sanitized);
foreach ($items as $key => $item) {
$do_content_extraction = true;
$extract_result = false;
$permalink = $urls[$key];
// TODO: Allow error codes - some sites return correct content with error status
// e.g. prospectmagazine.co.uk returns 403
if ($permalink && ($response = $http->get($permalink, true)) && ($response['status_code'] < 300 || $response['status_code'] > 400)) {
$effective_url = $response['effective_url'];
// check if action defined for returned Content-Type
$type = null;
if (preg_match('!^Content-Type:\s*(([-\w]+)/([-\w\+]+))!im', $response['headers'], $match)) {
// look for full mime type (e.g. image/jpeg) or just type (e.g. image)
$match[1] = strtolower(trim($match[1]));
$match[2] = strtolower(trim($match[2]));
foreach (array($match[1], $match[2]) as $_mime) {
if (isset($this->content_type_exc[$_mime])) {
$type = $match[1];
$_act = $this->content_type_exc[$_mime]['action'];
$_name = $this->content_type_exc[$_mime]['name'];
if ($_act == 'exclude') {
continue 2; // skip this feed item entry
} elseif ($_act == 'link') {
if ($match[2] == 'image') {
$html = "<a href=\"$effective_url\"><img src=\"$effective_url\" alt=\"$_name\" /></a>";
} else {
$html = "<a href=\"$effective_url\">Download $_name</a>";
}
$title = $_name;
$do_content_extraction = false;
break;
}
}
}
unset($_mime, $_act, $_name, $match);
}
if ($do_content_extraction) {
$html = $response['body'];
// remove strange things
$html = str_replace('</[>', '', $html);
$html = $this->convert_to_utf8($html, $response['headers']);
// check site config for single page URL - fetch it if found
if ($single_page_response = $this->getSinglePage($item, $html, $effective_url)) {
$html = $single_page_response['body'];
// remove strange things
$html = str_replace('</[>', '', $html);
$html = $this->convert_to_utf8($html, $single_page_response['headers']);
$effective_url = $single_page_response['effective_url'];
unset($single_page_response);
}
$extract_result = $extractor->process($html, $effective_url);
$readability = $extractor->readability;
$content_block = ($extract_result) ? $extractor->getContent() : null;
}
}
if ($do_content_extraction) {
// if we failed to extract content...
if (!$extract_result) {
$html = $this->error_message;
// keep the original item description
$html .= $item->get_description();
} else {
$readability->clean($content_block, 'select');
if ($this->rewrite_relative_urls) $this->makeAbsolute($effective_url, $content_block);
if ($content_block->childNodes->length == 1 && $content_block->firstChild->nodeType === XML_ELEMENT_NODE) {
$html = $content_block->firstChild->innerHTML;
} else {
$html = $content_block->innerHTML;
}
// post-processing cleanup
$html = preg_replace('!<p>[\s\h\v]*</p>!u', '', $html);
}
}
}
$title = ($extractor->getTitle() != '' ? $extractor->getTitle() : _('Untitled'));
$content = array ('title' => $title, 'body' => $html);
return $content;
}
private function convert_to_utf8($html, $header=null)
{
$encoding = null;
if ($html || $header) {
if (is_array($header)) $header = implode("\n", $header);
if (!$header || !preg_match_all('/^Content-Type:\s+([^;]+)(?:;\s*charset=["\']?([^;"\'\n]*))?/im', $header, $match, PREG_SET_ORDER)) {
// error parsing the response
} else {
$match = end($match); // get last matched element (in case of redirects)
if (isset($match[2])) $encoding = trim($match[2], "\"' \r\n\0\x0B\t");
}
// TODO: check to see if encoding is supported (can we convert it?)
// If it's not, result will be empty string.
// For now we'll check for invalid encoding types returned by some sites, e.g. 'none'
// Problem URL: http://facta.co.jp/blog/archives/20111026001026.html
if (!$encoding || $encoding == 'none') {
// search for encoding in HTML - only look at the first 35000 characters
$html_head = substr($html, 0, 40000);
if (preg_match('/^<\?xml\s+version=(?:"[^"]*"|\'[^\']*\')\s+encoding=("[^"]*"|\'[^\']*\')/s', $html_head, $match)) {
$encoding = trim($match[1], '"\'');
} elseif (preg_match('/<meta\s+http-equiv=["\']?Content-Type["\']? content=["\'][^;]+;\s*charset=["\']?([^;"\'>]+)/i', $html_head, $match)) {
$encoding = trim($match[1]);
} elseif (preg_match_all('/<meta\s+([^>]+)>/i', $html_head, $match)) {
foreach ($match[1] as $_test) {
if (preg_match('/charset=["\']?([^"\']+)/i', $_test, $_m)) {
$encoding = trim($_m[1]);
break;
}
}
}
}
if (isset($encoding)) $encoding = trim($encoding);
// trim is important here!
if (!$encoding || (strtolower($encoding) == 'iso-8859-1')) {
// replace MS Word smart qutoes
$trans = array();
$trans[chr(130)] = '&sbquo;'; // Single Low-9 Quotation Mark
$trans[chr(131)] = '&fnof;'; // Latin Small Letter F With Hook
$trans[chr(132)] = '&bdquo;'; // Double Low-9 Quotation Mark
$trans[chr(133)] = '&hellip;'; // Horizontal Ellipsis
$trans[chr(134)] = '&dagger;'; // Dagger
$trans[chr(135)] = '&Dagger;'; // Double Dagger
$trans[chr(136)] = '&circ;'; // Modifier Letter Circumflex Accent
$trans[chr(137)] = '&permil;'; // Per Mille Sign
$trans[chr(138)] = '&Scaron;'; // Latin Capital Letter S With Caron
$trans[chr(139)] = '&lsaquo;'; // Single Left-Pointing Angle Quotation Mark
$trans[chr(140)] = '&OElig;'; // Latin Capital Ligature OE
$trans[chr(145)] = '&lsquo;'; // Left Single Quotation Mark
$trans[chr(146)] = '&rsquo;'; // Right Single Quotation Mark
$trans[chr(147)] = '&ldquo;'; // Left Double Quotation Mark
$trans[chr(148)] = '&rdquo;'; // Right Double Quotation Mark
$trans[chr(149)] = '&bull;'; // Bullet
$trans[chr(150)] = '&ndash;'; // En Dash
$trans[chr(151)] = '&mdash;'; // Em Dash
$trans[chr(152)] = '&tilde;'; // Small Tilde
$trans[chr(153)] = '&trade;'; // Trade Mark Sign
$trans[chr(154)] = '&scaron;'; // Latin Small Letter S With Caron
$trans[chr(155)] = '&rsaquo;'; // Single Right-Pointing Angle Quotation Mark
$trans[chr(156)] = '&oelig;'; // Latin Small Ligature OE
$trans[chr(159)] = '&Yuml;'; // Latin Capital Letter Y With Diaeresis
$html = strtr($html, $trans);
}
if (!$encoding) {
$encoding = 'utf-8';
} else {
if (strtolower($encoding) != 'utf-8') {
$html = \SimplePie_Misc::change_encoding($html, $encoding, 'utf-8');
/*
if (function_exists('iconv')) {
// iconv appears to handle certain character encodings better than mb_convert_encoding
$html = iconv($encoding, 'utf-8', $html);
} else {
$html = mb_convert_encoding($html, 'utf-8', $encoding);
}
*/
}
}
}
return $html;
}
private function makeAbsolute($base, $elem) {
$base = new \SimplePie_IRI($base);
// remove '//' in URL path (used to prevent URLs from resolving properly)
// TODO: check if this is still the case
if (isset($base->path)) $base->path = preg_replace('!//+!', '/', $base->path);
foreach(array('a'=>'href', 'img'=>'src') as $tag => $attr) {
$elems = $elem->getElementsByTagName($tag);
for ($i = $elems->length-1; $i >= 0; $i--) {
$e = $elems->item($i);
//$e->parentNode->replaceChild($articleContent->ownerDocument->createTextNode($e->textContent), $e);
$this->makeAbsoluteAttr($base, $e, $attr);
}
if (strtolower($elem->tagName) == $tag) $this->makeAbsoluteAttr($base, $elem, $attr);
}
}
private function makeAbsoluteAttr($base, $e, $attr) {
if ($e->hasAttribute($attr)) {
// Trim leading and trailing white space. I don't really like this but
// unfortunately it does appear on some sites. e.g. <img src=" /path/to/image.jpg" />
$url = trim(str_replace('%20', ' ', $e->getAttribute($attr)));
$url = str_replace(' ', '%20', $url);
if (!preg_match('!https?://!i', $url)) {
if ($absolute = \SimplePie_IRI::absolutize($base, $url)) {
$e->setAttribute($attr, $absolute);
}
}
}
}
private function makeAbsoluteStr($base, $url) {
$base = new \SimplePie_IRI($base);
// remove '//' in URL path (causes URLs not to resolve properly)
if (isset($base->path)) $base->path = preg_replace('!//+!', '/', $base->path);
if (preg_match('!^https?://!i', $url)) {
// already absolute
return $url;
} else {
if ($absolute = \SimplePie_IRI::absolutize($base, $url)) {
return $absolute;
}
return false;
}
}
// returns single page response, or false if not found
private function getSinglePage($item, $html, $url) {
global $http, $extractor;
$host = @parse_url($url, PHP_URL_HOST);
$site_config = \SiteConfig::build($host);
if ($site_config === false) {
// check for fingerprints
if (!empty($extractor->fingerprints) && ($_fphost = $extractor->findHostUsingFingerprints($html))) {
$site_config = \SiteConfig::build($_fphost);
}
if ($site_config === false) $site_config = new \SiteConfig();
\SiteConfig::add_to_cache($host, $site_config);
return false;
} else {
\SiteConfig::add_to_cache($host, $site_config);
}
$splink = null;
if (!empty($site_config->single_page_link)) {
$splink = $site_config->single_page_link;
} elseif (!empty($site_config->single_page_link_in_feed)) {
// single page link xpath is targeted at feed
$splink = $site_config->single_page_link_in_feed;
// so let's replace HTML with feed item description
$html = $item->get_description();
}
if (isset($splink)) {
// Build DOM tree from HTML
$readability = new WallabagReadability($html, $url);
$xpath = new DOMXPath($readability->dom);
// Loop through single_page_link xpath expressions
$single_page_url = null;
foreach ($splink as $pattern) {
$elems = @$xpath->evaluate($pattern, $readability->dom);
if (is_string($elems)) {
$single_page_url = trim($elems);
break;
} elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
foreach ($elems as $item) {
if ($item instanceof DOMElement && $item->hasAttribute('href')) {
$single_page_url = $item->getAttribute('href');
break;
} elseif ($item instanceof DOMAttr && $item->value) {
$single_page_url = $item->value;
break;
}
}
}
}
// If we've got URL, resolve against $url
if (isset($single_page_url) && ($single_page_url = $this->makeAbsoluteStr($url, $single_page_url))) {
// check it's not what we have already!
if ($single_page_url != $url) {
// it's not, so let's try to fetch it...
$_prev_ref = $http->referer;
$http->referer = $single_page_url;
if (($response = $http->get($single_page_url, true)) && $response['status_code'] < 300) {
$http->referer = $_prev_ref;
return $response;
}
$http->referer = $_prev_ref;
}
}
}
return false;
}
}

9
src/Wallabag/Bundle/ReadabilityBundle/WallabagReadabilityBundle.php Normal file
View File

@ -0,0 +1,9 @@
<?php
namespace Wallabag\Bundle\ReadabilityBundle;
use Symfony\Component\HttpKernel\Bundle\Bundle;
class WallabagReadabilityBundle extends Bundle
{
}