PHP simple_html_dom类代码示例

 function handleDocumentInfo($DocInfo)
 {
     echo "Page requested: " . $DocInfo->url . " (" . $DocInfo->http_status_code . ")" . PHP_EOL;
     if ($DocInfo->http_status_code == '200' and $DocInfo->received and $DocInfo->content_type == 'text/html' and isset($DocInfo->content)) {
         $html = $DocInfo->content;
         $host = $DocInfo->host;
         $urlPosted = $DocInfo->url;
         $htmldom = new simple_html_dom();
         $htmldom->load($html);
         $data = array();
         $images = $htmldom->find('ul#ListViewInner li img');
         echo 'Total images' . count($images) . '' . PHP_EOL;
         $i = 0;
         foreach ($images as $raw_links) {
             echo $raw_links->alt . "','1','" . $raw_links->src . "\n";
             $filename = '_e__' . $i . '.jpg';
             copy(str_replace("l225 ", "l900", $raw_links->src), 'downloads/' . $filename);
             $i++;
         }
         echo json_encode($data) . PHP_EOL;
         //$writer->writeRow(json_encode($data));
         unset($data);
         unset($htmldom);
     }
 }

 public function parse($isUpdate = false)
 {
     Ibos::import("application.extensions.simple_html_dom", true);
     if ($isUpdate) {
         $model = preg_replace("/\\s+data-id\\s?=\\s?\"?\\d+\"?/i", "", $this->printmodel);
         $max = 0;
     } else {
         $model = $this->printmodel;
         $max = intval($this->itemmax);
     }
     $elements = array();
     $doc = new simple_html_dom();
     $doc->load($model, true, true, CHARSET);
     $items = $doc->find("ic");
     $config = $this->getItemConfig();
     if (!empty($items) && !empty($config)) {
         $this->refactor($items, $config, $max, $elements);
     }
     $html = $doc->save();
     $this->_cache = $elements;
     CacheUtil::set("form_" . $this->ID, $elements);
     $form["printmodelshort"] = $html;
     if ($max != $this->itemmax) {
         $form["itemmax"] = $max;
     }
     $doc->clear();
     FlowFormType::model()->modify($this->ID, $form);
 }

function run_ml($q_num = 0)
{
    $html = scraperWiki::scrape("http://musiklegal.com/search/result/a/" . $q_num);
    $dom = new simple_html_dom();
    $dom->load($html);
    foreach ($dom->find("tr") as $data) {
        $tds = $data->find("td");
        $temp_data = explode('">', str_replace('</<strong>a</strong>>', '', str_replace('<<strong>a</strong> href="http://musiklegal.com/song/detail/', '', $tds[1]->plaintext)));
        $record = array('No' => str_replace('.', '', $tds[0]->plaintext), 'Code' => $temp_data[0], 'Song Title' => $temp_data[1], 'Artist' => $tds[2]->plaintext, 'Album' => $tds[3]->plaintext);
        /*
         *  Stores results
         */
        scraperwiki::save_sqlite(array("No"), $record);
        unset($temp_data);
    }
    foreach ($dom->find("a") as $a) {
        if ($a->plaintext == 'Next') {
            $tmp_a = $a->href;
            $tmp_a = str_replace('http://musiklegal.com/search/result/a/', '', $tmp_a);
            if ($tmp_a > 0) {
                continue;
            }
        }
    }
    if ((int) $tmp_a != 0) {
        run_ml($tmp_a);
    } else {
        exit;
    }
}

 /**
  * 動画のURLを取得する
  *
  * @param  simple_html_dom $html
  * @return array
  **/
 public function getMoviesUrl($html)
 {
     $query = 'div.entryBody div.topmore a img';
     $movies_els = $html->find($query);
     $movie_data = array();
     $manager = new UriManager();
     // 動画はこちらテキストのリンクを取得する
     foreach ($movies_els as $movies_el) {
         if (!preg_match('/^動画.+/', $movies_el->getAttribute('alt'))) {
             continue;
         }
         // 親のaタグからリンクを取得する
         $parent_el = $next_el = $movies_el->parentNode();
         $i = 0;
         while ($i < 3) {
             $next_el = $next_el->nextSibling();
             if (is_null($next_el)) {
                 break;
             }
             $i++;
         }
         if ($next_el->nodeName() == 'span') {
             $movie_data = [];
             break;
         }
         if ($parent_el->nodeName() == 'a') {
             $movie_data[] = $manager->resolve($parent_el->getAttribute('href'));
         }
     }
     return $movie_data;
 }

function getProducts($u, $cat)
{
    global $o;
    $d = new simple_html_dom();
    $d->load(scraperwiki::scrape($u));
    //echo "Loaded URL: " . $u . "\n";
    $items = $d->find('li.grid-item');
    if (count($items) > 0) {
        foreach ($items as $p) {
            $prod = $p->find('p.product-name > a', 0);
            $prodname = trim($prod->innertext);
            $prodURL = $prod->href;
            if (!is_null($p->find('p.minimal-price', 0))) {
                $prodtype = 1;
            } else {
                $prodtype = 0;
            }
            fputcsv($o, array($prodname, $prodtype, $cat, $prodURL));
            echo $prodname . "\n";
        }
        if (!is_null($d->find('p.next', 0))) {
            getProducts($d->find('p.next', 0)->href, $cat);
        }
    }
}

 /**
  * curl 访问 开奖数据
  */
 private function get_data()
 {
     include_once 'simplehtmldom_1_5/simple_html_dom.php';
     $simple_html_dom = new \simple_html_dom();
     //zlib 解压 并转码
     $data = false;
     $data = @file_get_contents("compress.zlib://" . self::URL);
     if (!$data) {
         $this->setLog(false, '重庆时时彩-开奖数据抓取失败');
         exit('重庆时时彩-数据抓取失败,请尽快联系网站管理员' . "\r\n");
     }
     //转换成 UTF-8编码
     $encode = mb_detect_encoding($data, array('ASCII', 'UTF-8', 'GB2312', "GBK", 'BIG5'));
     $content = iconv($encode, 'UTF-8', $data);
     $simple_html_dom->load($content);
     //开奖期号
     $qihao = $simple_html_dom->find('div[class=aside]', 0)->find('h3', 0)->find('em', 0)->plaintext;
     //开奖号
     $code = $simple_html_dom->find('div[class=aside]', 0)->find('div[class=mod-aside mod-aside-xssckj]', 0)->find('div[class=bd]', 0)->find('div[class=kpkjcode]', 0)->find('table', 0)->find('tr', 1)->find('td', 1)->plaintext;
     if ($code == '--') {
         exit('重庆时时彩-等待开奖...' . "\r\n");
     }
     $isKaiJiang = $simple_html_dom->find('div[class=aside]', 0)->find('div[class=mod-aside mod-aside-xssckj]', 0)->find('div[class=bd]', 0)->find('div[class=kpkjcode]', 0)->find('table', 0)->find('tr', 1)->find('td', 2)->plaintext;
     if ($isKaiJiang == '--' && $isKaiJiang == '开奖中') {
         exit('重庆时时彩-等待开奖...' . "\r\n");
     }
     $simple_html_dom->clear();
     //将开奖号中间的空格去掉
     $code = str_replace(" ", '', $code);
     //开奖时间
     $kjsj = date('Y-m-d H:i:s');
     $this->data = ['qihao' => $qihao, 'kjsj' => $kjsj, 'code' => $code];
 }

 /**
  * 動画のURLを取得する
  *
  * @param  simple_html_dom $html
  * @return array
  **/
 public function getMoviesUrl($html)
 {
     $query = 'div.ently_body div.ently_text div.video-container iframe';
     $movies_els = $html->find($query);
     $movie_data = array();
     $manager = new UriManager();
     // 動画はこちらテキストのリンクを取得する
     foreach ($movies_els as $movies_el) {
         if ($movies_el->hasAttribute('src')) {
             $url = $manager->resolve($movies_el->getAttribute('src'));
             if ($url !== false) {
                 $movie_data[] = $url;
             }
         }
     }
     $query = 'div.ently_outline div.ently_body a';
     $movies_els = $html->find($query);
     foreach ($movies_els as $movies_el) {
         $text = $movies_el->plaintext;
         if (preg_match('/リンク（/', $text) && $movies_el->hasAttribute('href')) {
             $resolve_url = $manager->resolve($movies_el->getAttribute('href'));
             if ($resolve_url) {
                 $movie_data[] = $resolve_url;
             }
         }
     }
     return $movie_data;
 }

function do_day($rec)
{
    $html = scraperwiki::scrape($rec['url']);
    $dom = new simple_html_dom();
    $dom->load($html);
    $cell = $dom->find('a[name=discs]');
    $lines = $cell[0]->parent->find('text');
    print $lines[10] . "\n";
    print count($lines) . "\n";
    # loop by number, as null lines stop a foreach
    $n = 0;
    for ($line_no = 0; $line_no < count($lines); $line_no++) {
        $line = $lines[$line_no];
        if (strlen($line) == 3) {
            # the DOM object crashes on this row, so ignore
            continue;
        }
        #if (preg_match("#^" . $n . "#", $line, $matches)) {
        print $line_no . " " . strlen($line) . "\n";
        $n = $n + 1;
        print $line . "\n";
        #}
    }
    #scraperwiki::save(array('data'), array('data' => $data->plaintext));
}

 /**
  * Compile a template file by reading it, converting the DOM using
  * {@see convert()}, then applying macros using {@see transform()}.
  * @param string $template Template file path.
  * @return string PHP template content. 
  * @throws InvalidTemplateException If template is inaccessible or invalid.
  */
 public function compile($template)
 {
     $dom = new \simple_html_dom();
     $this->currentTemplate = $template;
     $file = file_get_contents($template);
     if ($file === false) {
         throw new InvalidTemplateException(tr('Could not read template: %1', $template));
     }
     if (!$dom->load($file, true, false)) {
         throw new InvalidTemplateException(tr('Could not parse template: %1', $template));
     }
     $root = new InternalNode();
     $main = $dom->find('[j:main]', 0);
     if (isset($main)) {
         $root->append($this->convert($main));
     } else {
         foreach ($dom->find('*, text') as $html) {
             if ($html->parent->tag != 'root') {
                 continue;
             }
             $root->append($this->convert($html));
         }
     }
     $this->transform($root);
     return $root->__toString();
 }

function scrapPage($page)
{
    print "Scraping page " . $page;
    $url = "http://www.geipan.fr/index.php?id=202";
    $fields_string = "&no_cache=1&" . "tx_geipansearch_pi1%5Bsubmit_form%5D=1&" . "tx_geipansearch_pi1%5Btexte_resume%5D=&" . "tx_geipansearch_pi1%5Bdate_debut%5D=&" . "tx_geipansearch_pi1%5Bdate_fin%5D=&" . "no_cache=1&" . "tx_geipansearch_pi1%5Bclasse_cas%5D=tous&" . "tx_geipansearch_pi1%5Bregion%5D=&" . "page=" . $page . "&" . "order_by=&" . "sens=";
    $curl = curl_init($url);
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($curl, CURLOPT_MAXREDIRS, 10);
    curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
    curl_setopt($curl, CURLOPT_TIMEOUT, 20);
    curl_setopt($curl, CURLOPT_POST, 11);
    curl_setopt($curl, CURLOPT_POSTFIELDS, $fields_string);
    $html = curl_exec($curl);
    print curl_error($curl) . "\n";
    //      print($html);
    $dom = new simple_html_dom();
    $dom->load($html);
    $trs = $dom->find("tr");
    foreach ($trs as $tr) {
        if (isset($tr->attr['onclick'])) {
            $ID = substr($tr->attr['onclick'], strpos($tr->attr['onclick'], "cas=") + 4, 13);
            print $ID . "\n";
            $tds = $tr->find("td");
            $title = utf8_encode($tds[0]->plaintext);
            $date = $tds[1]->plaintext;
            $departement = utf8_encode($tds[2]->plaintext);
            $classe = $tds[3]->plaintext;
            $maj = $tds[4]->plaintext;
            $city = substr($title, 0, strpos($title, "(") - 1);
            $record = array('ID' => $ID, 'title' => $title, 'date' => $date, 'departement' => $departement, 'classe' => $classe, 'maj' => $maj, 'city' => $city);
            scraperwiki::save(array('ID', 'maj'), $record);
        }
    }
}

 public function getSearchResults(simple_html_dom $dom)
 {
     $result = array();
     $count = count($dom->find('div.srg'));
     if ($count) {
         // if found div.srg
         $c = $count > 1 ? 1 : 0;
         // if this is first page, we have 2 divs, first with some irrelevant
         //links, so skip the first page
         $d = $dom->find('div.srg', $c);
         // get second div(if this is 1st page), or first div
     } else {
         // no div.srg found, search all page
         $d = $dom;
     }
     foreach ($d->find('div.rc') as $div) {
         $a = $div->find('h3.r a', 0);
         // get link to the website
         //Get original image url
         $originalImg = $div->find('div.th a', 0);
         preg_match('/imgurl=(.+?)&/', $originalImg->href, $matches);
         $result[] = array(htmlspecialchars_decode($a->plaintext, ENT_QUOTES), $a->href, $matches[1]);
     }
     return $result;
 }

function scrape_page()
{
    $row = 0;
    $html = scraperWiki::scrape("http://asuntojen.hintatiedot.fi/haku/?c=" . $GLOBALS['c'] . "&s=" . $GLOBALS['s'] . "&r=" . $GLOBALS['r'] . "&amin=" . $GLOBALS['amin'] . "&amax=" . $GLOBALS['amax'] . "&z=" . $GLOBALS['z']);
    $dom = new simple_html_dom();
    $dom->load($html);
    foreach ($dom->find("tr") as $data) {
        $tds = $data->find("td");
        if (count($tds) > 8) {
            $row++;
            $GLOBALS['rowTotal']++;
            $apt = array("Uniikkiavain" => $GLOBALS['rowTotal'], "Kaupunginosa" => $tds[0]->plaintext, "Myyntihinta" => $tds[3]->plaintext, "Neliohinta" => $tds[4]->plaintext, "Tyyppi" => $tds[1]->plaintext, "Koko" => $tds[2]->plaintext);
            scraperwiki::save_sqlite(null, $apt, $table_name = $GLOBALS['c'] . " " . $GLOBALS['time']);
            print $GLOBALS['rowTotal'] . "\n";
            print $row . ". Sijainti: " . $tds[0]->plaintext . " Hinta: " . $tds[3]->plaintext . " Tyyppi: " . $tds[1]->plaintext . " Koko: " . $tds[2]->plaintext . " Neliöhinta: " . $tds[4]->plaintext . "€" . "\n";
        }
    }
    if ($row == 50) {
        print "Vielä jatkuu, haetaan seuraava sivu..." . "\n";
        $GLOBALS['z']++;
        scrape_page();
    } else {
        print "Skrääpiminen suoritettu." . "\n";
        print "Sivuja yhteensä: " . $GLOBALS['z'] . "\n";
        print "Rivejä yhteensä: " . $GLOBALS['rowTotal'] . "\n";
    }
}

 public function save($html, $dir)
 {
     import("@.ORG.htmltodocx.documentation.support_functions");
     $phpword_object = new PHPWord();
     $section = $phpword_object->createSection();
     // HTML Dom object:
     $html_dom = new simple_html_dom();
     $html_dom->load('<html><body>' . $html . '</body></html>');
     // Note, we needed to nest the html in a couple of dummy elements.
     // Create the dom array of elements which we are going to work on:
     $html_dom_array = $html_dom->find('html', 0)->children();
     // We need this for setting base_root and base_path in the initial_state array
     // (below). We are using a function here (derived from Drupal) to create these
     // paths automatically - you may want to do something different in your
     // implementation. This function is in the included file
     // documentation/support_functions.inc.
     $paths = htmltodocx_paths();
     // Provide some initial settings:
     $initial_state = array('phpword_object' => &$phpword_object, 'base_root' => $paths['base_root'], 'base_path' => $paths['base_path'], 'current_style' => array('size' => '11'), 'parents' => array(0 => 'body'), 'list_depth' => 0, 'context' => 'section', 'pseudo_list' => TRUE, 'pseudo_list_indicator_font_name' => 'Wingdings', 'pseudo_list_indicator_font_size' => '7', 'pseudo_list_indicator_character' => 'l ', 'table_allowed' => TRUE, 'treat_div_as_paragraph' => TRUE, 'style_sheet' => htmltodocx_styles_example());
     // Convert the HTML and put it into the PHPWord object
     htmltodocx_insert_html($section, $html_dom_array[0]->nodes, $initial_state);
     // Clear the HTML dom object:
     $html_dom->clear();
     unset($html_dom);
     // Save File
     $str = explode(".", $h2d_file_uri);
     $h2d_file_uri = $dir . "wordtemp/" . time() . ".docx";
     if (!file_exists($dir . "wordtemp/")) {
         $this->createFolders($dir . "wordtemp/");
         //判断目标文件夹是否存在
     }
     $objWriter = PHPWord_IOFactory::createWriter($phpword_object, 'Word2007');
     $objWriter->save($h2d_file_uri);
     return $h2d_file_uri;
 }

 function handleDocumentInfo($DocInfo)
 {
     //	global $writer;
     echo "Page requested: " . $DocInfo->url . " (" . $DocInfo->http_status_code . ")" . PHP_EOL;
     if ($DocInfo->http_status_code == '200' and $DocInfo->received and $DocInfo->content_type == 'text/html' and isset($DocInfo->content)) {
         $html = $DocInfo->content;
         $host = $DocInfo->host;
         $urlPosted = $DocInfo->url;
         $htmldom = new simple_html_dom();
         $htmldom->load($html);
         $data = array();
         $images = $htmldom->find('.pinHolder img');
         echo 'Total Images ' . count($images) . PHP_EOL;
         $i = intval(Date("YmdHis"));
         foreach ($images as $raw_links) {
             $data['items'][] = array("title" => $raw_links->alt, "img" => $raw_links->src);
             copy($raw_links->src, 'downloads/' . $i . '.jpg');
             $i++;
         }
         echo json_encode($data) . PHP_EOL;
         //$writer->writeRow(json_encode($data));
         unset($data);
         unset($htmldom);
     }
 }

 private function parsing($scrappedData)
 {
     $result = [];
     //Create a DOM parser object
     $html = new simple_html_dom();
     //Parse the HTML from Amazon.
     $html->load($scrappedData);
     # Iterate over all the  tags
     foreach ($html->find('li[class=s-result-item]') as $key => $innerData) {
         //image
         foreach ($innerData->find('img[class=s-access-image]') as $img) {
             $atmp['image'] = $img->getAttribute('src');
         }
         //title
         foreach ($innerData->find('h2[class=s-access-title]') as $title) {
             $atmp['title'] = $title->innertext();
         }
         //price
         foreach ($innerData->find('span[class=s-price]') as $price) {
             $price = $price->innertext();
             $atmp['price'] = $price;
             $atmp['numPrice'] = str_replace(",", '', substr($price, 1));
         }
         //total page
         foreach ($html->find('span[class=pagnDisabled]') as $maxPage) {
             $atmp['totalPage'] = $maxPage->innertext();
         }
         # Show the <a href>
         if (isset($atmp)) {
             $result[$key] = $atmp;
         }
     }
     return $this->aResult = $result;
 }