PHP Crawler类代码示例

 public function go()
 {
     $start_url = $this->url;
     $c = new Crawler($start_url);
     $c->go2linewhere('<p><a href="');
     $c->close();
     $ledak = explode('<a href="', $c->curline);
     for ($i = 1; $i < count($ledak); ++$i) {
         $aurl = Crawler::cutuntil($ledak[$i], '"');
         $aurl = str_replace('http://hentaifromhell.net/redirect.html?', '', $aurl);
         echo "<a href='{$aurl}'>{$aurl}</a><br />\n";
         flush();
         /*
         $basename = Crawler::cutuntillast($aurl, '/');
         if (!in_array($basename, $this->blacklist)) {
         	$c = new Crawler($aurl);
         	$c->go2linewhere('id="thepic"');
         	$imgurl = $c->getbetween('SRC="', '"');
         	$c->close();
         	echo "<a href='$basename/$imgurl'>".Crawler::n($i,3).".jpg</a><br />\n";
         	flush();
         } else {
         	echo "$i blacklisted server<br/>";flush();
         }
         */
     }
 }

 public function getHotSpots()
 {
     $crawler = new Crawler($this);
     $outlines = new CrawlerOutlineCollection();
     $size = $this->image->size();
     for ($x = 0; $x < $size[0]; $x++) {
         for ($y = 0; $y < $size[1]; $y++) {
             $pixel = $this->pixel($x, $y);
             // Skip white pixels
             if ($pixel->color()->compare(ImageColor::white(), 5)) {
                 continue;
             }
             // Skip crawled areas
             if ($outlines->contains($pixel)) {
                 continue;
             }
             // Start crawling
             $outline = $crawler->crawl($x, $y);
             $outlines->push($outline);
         }
     }
     $hotspots = new ImageCollection();
     foreach ($outlines as $outline) {
         $hotspots->push($this->image->sliceByOutline($outline));
     }
     return array($hotspots, $outlines);
 }

function crawl_1_page($url)
{
    echo "URL2 {$url} <br/>\n";
    flush();
    $dirname = html_entity_decode(Crawler::cutfromlast1(substr($url, 0, strlen($url) - 1), '/'));
    $hasil = array();
    $c = new Crawler($url);
    $c->go_to('<div class="entry">');
    while ($line = $c->readline()) {
        if (Crawler::is_there($line, "href='")) {
            $img = Crawler::extract($line, "href='", "'");
            echo "<a href='{$img}'>{$dirname}</a><br/>\n";
            flush();
        } else {
            if (Crawler::is_there($line, 'href="')) {
                $img = Crawler::extract($line, 'href="', '"');
                echo "<a href='{$img}'>{$dirname}</a><br/>\n";
                flush();
            } else {
                if (Crawler::is_there($line, '</div>')) {
                    break;
                }
            }
        }
    }
    $c->close();
}

 /**
  * Log the user
  * @param Crawler $crawler
  */
 private function login($crawler)
 {
     $form = $crawler->selectButton('_submit')->form();
     // définit certaines valeurs
     $form['_username'] = 'kwizer';
     $form['_password'] = 'sslover';
     return $this->client->submit($form);
 }

 public function testCrawl()
 {
     $account = Account::login("searchzen.org", "test");
     $c = $account->collections[0];
     $crawler = new Crawler($c);
     $crawler->pageLimit = 10;
     $crawler->start();
 }

 /**
  * Start the crawler to retrieve pages from a given news website
  * @param type $nrOfDaysBack The nr of days the crawler should go back (counting from today)
  * @param type $newsSiteUrl The root URL of the news site (the seed of the crawler)
  * @return type
  */
 public function crawlForNews($nrOfDaysBack, $newsSiteUrl, $timeToLive, $startDate = null)
 {
     $crawler = new Crawler($newsSiteUrl, $timeToLive);
     if ($startDate) {
         $crawler->crawl($nrOfDaysBack, $startDate);
     } else {
         $crawler->crawl($nrOfDaysBack);
     }
     return count($crawler->getCrawled());
 }

 static function run()
 {
     if (isset($_GET['site_url']) && isset($_GET['sitemap_url']) && CODOF\Access\CSRF::valid($_GET['CSRF_token'])) {
         $sitemapObject = new Crawler($_GET['site_url']);
         $sitemapPath = ABSPATH . 'sitemap.xml';
         $sitemapFile = $sitemapObject->createSitemap($sitemapPath);
         // session_write_close();
         // ob_end_flush();
         exit;
     }
 }

function crawl_indowebster($url)
{
    //echo "'$url'";
    $craw = new Crawler($url);
    $craw->go2lineregexor('/(<\\/div><\\/a><\\/div><\\/div>)/', 1, 'href="#idws7"');
    $setring = $craw->getbetween('location.href=\'', '\'');
    $path = Crawler::extract($setring, 'path=', '&');
    $file_orig = Crawler::cutafter($setring, 'file_orig=');
    $craw->close();
    return '<a href="' . dirname($setring) . '/' . $path . '">' . rawurldecode($file_orig) . '</a>';
}

 public function mangareader_1_page($fil, $url, $prefix, $chapter)
 {
     $chapter = Crawler::pad($chapter, 3);
     $c = new Crawler($fil);
     $c->go_to('width="800"');
     $img = $c->getbetween('src="', '"');
     preg_match('/(\\d+\\.\\w+)$/', basename($img), $m);
     $iname = $m[1];
     $c->close();
     $name = $prefix . '-' . $chapter . '-' . $iname;
     return array($name => $img);
 }

 public function addCrawlMap($src, $patterns)
 {
     if (!empty($src)) {
         $root = $this->_src_root . '/' . $src;
     } else {
         $root = $this->_src_root;
     }
     $crawler = new Crawler($root, $patterns);
     $paths = $crawler->getPaths();
     foreach ($paths as $path) {
         $this->addMap($src . '/' . $path, str_replace('site/', '', $path));
     }
 }

 public function mangareader_1_page($fil, $url, $chapter)
 {
     $prefix = $this->prefix;
     $chapter = Crawler::pad($chapter, 3);
     $c = new Crawler($fil);
     $c->go_to('width="800"');
     $img = $c->getbetween('src="', '"');
     // if (@$_GET['show_url']) echo "<a href='$url'>URL</a> ";
     preg_match('/(\\d+\\.\\w+)$/', basename($img), $m);
     $iname = $m[1];
     echo '<li><a href="' . $img . '">' . $prefix . '-' . $chapter . '-' . $iname . '</a>' . "</li>\n";
     $c->close();
 }

 public function handleCrawling()
 {
     $view = new CrawlerResultViewSwe();
     if (isset($_SESSION['url'])) {
         $url = $_SESSION['url'];
         $curl = new Curl();
         $crawler = new Crawler($curl, $url);
     }
     //If user wants to book
     if ($view->bookParamExists() && isset($crawler)) {
         $group1 = $view->getBookInfo();
         $reservationInfo = $crawler->getReservations($group1);
         $view->outPutReservationResult($reservationInfo);
         //destroy session
         $_SESSION = array();
         session_destroy();
         session_unset();
     } else {
         if ($view->timeParamExists() && $view->dayParamExists() && $view->movieParamExists() && isset($crawler)) {
             $day = $view->getDay();
             $time = $view->getTime();
             $movie = $view->getMovie();
             $dinnerInfo = $crawler->getDinnerInfo($day, $time);
             $view->outPutDinnerAlts($dinnerInfo, $time, $movie);
         } else {
             if ($view->userHasSubmittedURL()) {
                 //$url ="http://localhost:8080/";
                 $url = $view->getURL();
                 $curl = new Curl();
                 $crawler = new Crawler($curl, $url);
                 $crawler->getLinks();
                 $dates = $crawler->getCalendarInfo();
                 $comparer = new compareData();
                 $matchingDay = $comparer->compareCommonDates($dates);
                 if (!is_null($matchingDay)) {
                     $filmDates = $crawler->getFilmInfo($matchingDay);
                     $view->outPutMovieResult($filmDates, $matchingDay);
                 } else {
                     $view->noMatchingDays();
                 }
                 $_SESSION['url'] = $url;
             } else {
                 $view = new formView();
             }
         }
     }
     return $view;
 }

    public function  testFlickrCrawl() {
        $builders = $this->buildData();

        $crawler = Crawler::getInstance();
        $config = Config::getInstance();

        //use fake Flickr API key
        $plugin_builder = FixtureBuilder::build('plugins', array('id'=>'2', 'folder_name'=>'flickrthumbnails'));
        $option_builder = FixtureBuilder::build('options', array(
            'namespace' => OptionDAO::PLUGIN_OPTIONS . '-2',
            'option_name' => 'flickr_api_key',
            'option_value' => 'dummykey') );
        //$config->setValue('flickr_api_key', 'dummykey');

        $this->simulateLogin('admin@example.com', true);
        $crawler->crawl();

        $ldao = DAOFactory::getDAO('LinkDAO');

        $link = $ldao->getLinkById(43);
        $this->assertEqual($link->expanded_url, 'http://farm3.static.flickr.com/2755/4488149974_04d9558212_m.jpg');
        $this->assertEqual($link->error, '');

        $link = $ldao->getLinkById(42);
        $this->assertEqual($link->expanded_url, '');
        $this->assertEqual($link->error, 'No response from Flickr API');

        $link = $ldao->getLinkById(41);
        $this->assertEqual($link->expanded_url, '');
        $this->assertEqual($link->error, 'No response from Flickr API');
    }

 /**
  * Destroy Config, Webapp, $_SESSION, $_POST, $_GET, $_REQUEST
  */
 public function tearDown()
 {
     Config::destroyInstance();
     Webapp::destroyInstance();
     Crawler::destroyInstance();
     if (isset($_SESSION)) {
         $this->unsetArray($_SESSION);
     }
     $this->unsetArray($_POST);
     $this->unsetArray($_GET);
     $this->unsetArray($_REQUEST);
     $this->unsetArray($_SERVER);
     $this->unsetArray($_FILES);
     Loader::unregister();
     $backup_dir = FileDataManager::getBackupPath();
     if (file_exists($backup_dir)) {
         try {
             @exec('cd ' . $backup_dir . '; rm -rf *');
             rmdir($backup_dir);
             // won't delete if has files
         } catch (Exception $e) {
         }
     }
     $data_dir = FileDataManager::getDataPath();
     if (file_exists($data_dir . 'compiled_view')) {
         try {
             @exec('cd ' . $data_dir . '; rm -rf compiled_view');
         } catch (Exception $e) {
         }
     }
     parent::tearDown();
 }

 public function control()
 {
     $output = "";
     $authorized = false;
     if (isset($this->argc) && $this->argc > 1) {
         // check for CLI credentials
         $session = new Session();
         $username = $this->argv[1];
         if ($this->argc > 2) {
             $pw = $this->argv[2];
         } else {
             $pw = getenv('THINKUP_PASSWORD');
         }
         $owner_dao = DAOFactory::getDAO('OwnerDAO');
         $owner = $owner_dao->getByEmail($username);
         if ($owner_dao->isOwnerAuthorized($username, $pw)) {
             $authorized = true;
             Session::completeLogin($owner);
         } else {
             $output = "ERROR: Incorrect username and password.";
         }
     } else {
         // check user is logged in on the web
         if ($this->isLoggedIn()) {
             $authorized = true;
         } else {
             $output = "ERROR: Invalid or missing username and password.";
         }
     }
     if ($authorized) {
         $crawler = Crawler::getInstance();
         $crawler->crawl();
     }
     return $output;
 }