PHP simple_html_dom::getElementById方法代码示例

function grep_munich($url, $table_name)
{
    $html = scraperWiki::scrape($url);
    $count = 0;
    # Use the PHP Simple HTML DOM Parser to extract <td> tags
    $dom = new simple_html_dom();
    $dom->load($html);
    //Drop all old informations by dropping the table
    scraperwiki::sqliteexecute("drop table if exists " . $table_name);
    scraperwiki::sqlitecommit();
    $table = $dom->getElementById('flight_info_area');
    foreach ($table->find('tr') as $data) {
        // Flight details. Read tds or ths
        $tds = $data->find("td");
        //if there are less then 7 columns continue to next loop
        if (sizeof($tds) < 7) {
            continue;
        }
        //print $data->plaintext . "\n";
        $flightnr = $tds[1]->plaintext;
        $from = $tds[2]->plaintext;
        $time = $tds[3]->plaintext;
        $expected_time = $tds[4]->plaintext;
        //Create date
        $date = date("Y-m-d");
        //Build array of flight informations
        $flight_data = array("date" => $date, "count" => $count, "flightnr" => $flightnr, "from" => $from, "time" => $time, "expected_time" => $expected_time);
        //Save the informations of one flight
        scraperwiki::save_sqlite(array("date", "count"), $flight_data, $table_name);
        $count = $count + 1;
    }
}

#}
######################################
# PHP scraper for Seznam cirkvi
######################################
require 'scraperwiki/simple_html_dom.php';
#function odstranDiakritiku($text)
#{
#    return iconv("windows-1250", "ascii//TRANSLIT", $text);
#}
$html = scraperwiki::scrape("http://www3.mkcr.cz/cns_internet/CNS/detail_cns.aspx?id_subj=147&str_zpet=Seznam_cns.aspx");
#print $html;
# Use the PHP Simple HTML DOM Parser to extract <td> tags
$dom = new simple_html_dom();
$dom->load($html);
$nazev = false;
$table = $dom->getElementById('Table3');
foreach ($table->find('td') as $data) {
    print $data;
    #kdyz konci dvojteckou, indexuji timto slovem
    if (ereg(":\$", $data)) {
        if ($nazev == true && $data->plaintext == "Název:") {
            $data = "Nazev organu cirkve:";
        } elseif ($data->plaintext == "Název:") {
            $nazev = true;
        }
        $index = odstranDiakritiku($data->plaintext);
    } else {
        $output[$index] = $data;
    }
}
#foreach($dom->find('td') as $data)

print "fbjksdhf\n";
?>
//<?php 
# Blank PHP
require 'scraperwiki/simple_html_dom.php';
function toIndex($text)
{
    $text = iconv('Windows-1252', 'ASCII//TRANSLIT', $text);
    return Str_Replace(' ', '_', $text);
}
$html = scraperwiki::scrape("http://www3.mkcr.cz/cns_internet/CNS/detail_cns.aspx?id_subj=147&str_zpet=Seznam_cns.aspx");
$dom = new simple_html_dom();
$dom->load($html);
#print toIndex("Dataž :");
#$table=$data->find('table[id=Table3]');
$curIndex = "";
foreach ($dom->getElementById('Table3')->find('td') as $data) {
    $txt = $data->plaintext;
    if (ereg(":\$", $txt)) {
        $curIndex = toIndex($txt);
    } else {
        $field[$curIndex] = $txt;
        print $field[$curIndex] . "\n";
    }
}
foreach ($field as $i => $a) {
    print $i . $a . "\n";
}
print "fbjksdhf\n";
?>
//

}
require 'scraperwiki/simple_html_dom.php';
$start = 207;
$limit = 0;
//this can enable, disable automatic runs
$count = $start;
for ($i = $start; $i <= $limit; $i += 100) {
    $gURL = scraperwiki::scrape("http://www.google.com/search?q=site%3Amappery.com&num=100&start=" . $i);
    $gDOM = new simple_html_dom();
    $gDOM->load($gURL);
    foreach ($gDOM->find('a') as $a) {
        if (substr($a->href, 7, 8) == "webcache") {
            $rURL = scraperwiki::scrape($a->href);
            $rDOM = new simple_html_dom();
            $rDOM->load($rURL);
            $imgDiv = $rDOM->getElementById('mapPic');
            if (!$imgDiv) {
                continue;
            }
            $imgs = $imgDiv->find('img');
            if (count($imgs) == 0) {
                continue;
            }
            $detDiv = $rDOM->getElementById('mapDetailInfo');
            if (!$detDiv) {
                continue;
            }
            $as = $detDiv->find('a');
            if (count($as) == 0) {
                continue;
            }

// -----------------------------------------------------------------------------
// old fashion camel naming conventions test
$str = <<<HTML

<input type="checkbox" id="checkbox" name="checkbox" value="checkbox" checked>
<input type="checkbox" id="checkbox1" name="checkbox1" value="checkbox1">
<input type="checkbox" id="checkbox2" name="checkbox2" value="checkbox2" checked>
HTML;
$html->load($str);
assert($html == $str);
assert($html->getElementByTagName('input')->hasAttribute('checked') == true);
assert($html->getElementsByTagName('input', 1)->hasAttribute('checked') == false);
assert($html->getElementsByTagName('input', 1)->hasAttribute('not_exist') == false);
assert($html->find('input', 0)->value == $html->getElementByTagName('input')->getAttribute('value'));
assert($html->find('input', 1)->value == $html->getElementsByTagName('input', 1)->getAttribute('value'));
assert($html->find('#checkbox1', 0)->value == $html->getElementById('checkbox1')->getAttribute('value'));
assert($html->find('#checkbox2', 0)->value == $html->getElementsById('checkbox2', 0)->getAttribute('value'));
$e = $html->find('[name=checkbox]', 0);
assert($e->getAttribute('value') == 'checkbox');
assert($e->getAttribute('checked') == true);
assert($e->getAttribute('not_exist') == '');
$e->setAttribute('value', 'okok');
assert($e == '<input type="checkbox" id="checkbox" name="checkbox" value="okok" checked>');
$e->setAttribute('checked', false);
assert($e == '<input type="checkbox" id="checkbox" name="checkbox" value="okok">');
$e->setAttribute('checked', true);
assert($e == '<input type="checkbox" id="checkbox" name="checkbox" value="okok" checked>');
$e->removeAttribute('value');
assert($e == '<input type="checkbox" id="checkbox" name="checkbox" checked>');
$e->removeAttribute('checked');
assert($e == '<input type="checkbox" id="checkbox" name="checkbox">');

function getNavigation(simple_html_dom $DOM)
{
    $navbar = array();
    $navigation = $DOM->getElementById('prdMenu_RadMenu');
    if (empty($navigation)) {
        return false;
    }
    foreach ($navigation->find('li[class=rmItem rmLast] > div.rmSlide > ul.rmLevel1', 0)->children() as $navlist) {
        $navlink = $navlist->find('a', 0);
        $navtitle = $navlink->title;
        $navtitle = str_replace("GeForce", "", $navtitle);
        $navurl = $navlink->href;
        $navurl = str_replace("ProductList.aspx?type=8&family=", "", $navurl);
        $navurl = str_replace('+', "%2B", $navurl);
        //$navitem = $navitem->title;
        $navbar[$navtitle] = array('url' => $navurl);
    }
    return $navbar;
}

function parseDetails($name, $id, $in)
{
    $dom = new simple_html_dom();
    $dom->load($in);
    $data_table = $dom->getElementById('TabelleKitaDetails');
    foreach ($data_table->find("tbody tr") as $trs) {
        $switch = $trs->childNodes(0)->plaintext;
        switch ($switch) {
            case "Adresse":
                $addr = $trs->childNodes(1)->plaintext;
                break;
            case "Pädagogische Merkmale":
                $concept = $trs->childNodes(1)->plaintext;
                break;
            case "Telefon":
                $tel = $trs->childNodes(1)->plaintext;
                break;
            case "Email":
                $mail = $trs->childNodes(1)->plaintext;
                break;
            case "Internet":
                $web = $trs->childNodes(1)->plaintext;
                break;
            case "Einrichtungsart":
                $type = $trs->childNodes(1)->plaintext;
                break;
            case "Träger":
                $head = $trs->childNodes(1)->plaintext;
                break;
            case "Adresse Träger":
                $head_address = $trs->childNodes(1)->plaintext;
                break;
            case "Trägerart":
                $head_type = $trs->childNodes(1)->plaintext;
                break;
        }
    }
    $record = array('kitaID' => $id, 'kita' => $name, 'address' => $addr, 'telefone' => $tel, 'mail' => $mail, 'web' => $web, 'type' => $type, 'concept' => $concept, 'head' => $head, 'head_address' => $head_address, 'head_type' => $head_type);
    scraperwiki::save(array('kitaID'), $record);
}

    $date = date("m.d.y");
    //Build array of flight informations
    $flight_data = array("date" => $date, "flightnr" => $flightnr, "from" => $from, "time" => $time, "expected_time" => $expected_time);
    //Save the informations of one flight
    scraperWiki::save_sqlite(array("date", "flightnr"), $flight_data);
}
# Exercise sheet 8 - Task 12
# www.munich-airport.de
# we extracted information of the arivales of the munich airport
# we wanted schedule time of 5 minutes but this is not alowed for standard acount (1 day)
require "scraperwiki/simple_html_dom.php";
$html = scraperWiki::scrape("http://www.munich-airport.de/de/consumer/index.jsp");
# Use the PHP Simple HTML DOM Parser to extract <td> tags
$dom = new simple_html_dom();
$dom->load($html);
$table = $dom->getElementById('navigation_mainpage_flightinfo_table');
foreach ($table->find('tr') as $data) {
    print $data->plaintext . "\n";
    // Flight details. Read tds or ths
    $tds = sizeof($data->find("td")) > 1 ? $data->find("td") : $data->find("th");
    if (sizeof($tds) == 0) {
        break;
    }
    $flightnr = $tds[1]->plaintext;
    $from = $tds[2]->plaintext;
    $time = $tds[3]->plaintext;
    $expected_time = $tds[4]->plaintext;
    // Skip header
    if ($flightnr == "Flug") {
        continue;
    }