PHP simple_html_dom::find方法代码示例

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);
        }
    }
}

 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;
 }

function clubURL($url)
{
    $html = scraperwiki::scrape($url);
    $dom = new simple_html_dom();
    $dom->load($html);
    $clubName = trim(str_replace(' ', '', $dom->find('table', 0)->find('tr', 2)->plaintext));
    $formatClubName = trim(preg_replace('/\\s+/', ' ', $clubName));
    $_GLOBAL['clubs'][] = $formatClubName;
    echo 'running ' . $formatClubName . "\n";
    foreach ($dom->find('table', 2)->find('tr') as $row) {
        if (is_numeric($row->find('td', 0)->plaintext)) {
            $year = trim($row->find('td', 0)->plaintext);
            $position = trim(str_replace(' ', '', $row->find('td', 1)->plaintext));
            if (trim($position) == 'Champion') {
                $position = 1;
            }
            $leagueLevel = trim($row->find('td', 2)->plaintext);
            $overallPosition = trim($row->find('td', 3)->plaintext);
            $avgAttendance = trim(str_replace('.', '', $row->find('td', 4)->plaintext));
            $totalAttendance = trim(str_replace('.', '', $row->find('td', 12)->plaintext));
            $dataset = array('club' => $formatClubName, 'year' => $year, 'finishedPosition' => $position, 'league' => $leagueLevel, 'overallPosition' => $overallPosition, 'avgAttendance' => $avgAttendance, 'totalAttendance' => $totalAttendance);
            scraperwiki::save(array('club', 'year'), $dataset);
        }
    }
    /*
     * The next to lines stop a memory leak in Simple XML as per http://simplehtmldom.sourceforge.net/manual_faq.htm#memory_leak
     */
    $dom->clear();
    unset($dom);
}

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;
    }
}

function getCategories($u)
{
    global $baseurl, $f;
    $path = "";
    $d = new simple_html_dom();
    $d->load(scraperwiki::scrape($u));
    echo "Loaded URL: " . $u . "\n";
    if ($d->find('div[id=ctl00_cphContent_gsaCatFacetContainer]')) {
        $breadcrumb = $d->find('div[id=breadcrumb]', 0);
        //foreach($breadcrumb as $b) {
        //echo "Breadcrumb = " . $b;}
        if (!is_null($breadcrumb)) {
            foreach ($breadcrumb->children() as $crumb) {
                $path .= trim($crumb->innertext) . "/";
            }
            $path .= trim(strrchr($breadcrumb->innertext, ">"), "> ");
        }
        foreach ($d->find('div[id=ctl00_cphContent_gsaCatFacetContainer]', 0)->find('div[class=S2refinementsContainer]', 0)->children() as $div) {
            $name = trim(strstr($div->children(0)->innertext, "(", true));
            $url = $baseurl . $div->children(0)->href;
            $data = array("Name" => $name, "Path" => $path, "URL" => $url);
            echo $path . "/" . $name . "\n";
            if ($local) {
                fputcsv($f, array($name, $path, $url));
            } else {
                scraperwiki::save_sqlite(array("URL"), $data);
            }
            getCategories($url);
        }
    }
}

 /**
  * 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 getCardInfo($url)
{
    $baseURL = 'http://gatherer.wizards.com/Pages/Card/';
    $html = scraperWiki::scrape($url);
    $dom = new simple_html_dom();
    $dom->load($html);
    $cardImage = $dom->find('img[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_cardImage]', 0)->src;
    $cardImage = str_replace("amp;", "", $cardImage);
    $imgURL = $baseURL . $cardImage;
    $name = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_nameRow] div[class=value]', 0)->plaintext;
    $name = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $name);
    $mana = "";
    $manaImages = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_manaRow] div[class=value] img');
    foreach ($manaImages as $manaItem) {
        $mana .= substr($manaItem->alt, 0, 1);
    }
    $mana = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $mana);
    $cmc = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_cmcRow] div[class=value]', 0);
    $cmc = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $cmc);
    $type = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_typeRow] div[class=value]', 0);
    $type = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $type);
    $text = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_textRow] div[class=value]', 0);
    $text = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $text);
    $flavor = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_flavorRow] div[class=value]', 0);
    $flavor = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $flavor);
    $cardNumber = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_numberRow] div[class=value]', 0);
    $cardNumber = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $cardNumber);
    $artist = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_artistRow] div[class=value]', 0);
    $artist = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $artist);
    $rarity = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_rarityRow] div[class=value]', 0);
    $rarity = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $rarity);
    $set = $dom->find('div[id=ctl00_ctl00_ctl00_MainContent_SubContent_SubContent_setRow] div[class=value]', 0);
    $set = iconv("UTF-8", "ISO-8859-1//TRANSLIT", $set);
    scraperwiki::save_sqlite(array("card"), array("Card" => trim($name), "Image" => $imgURL, "Mana" => trim($mana), "CMC" => trim($cmc), "Type" => trim($type), "Card Text" => trim($text), "Flavor Text" => trim($flavor), "Artist" => trim($artist), "Card Number" => trim($cardNumber), "Rarity" => trim($rarity), "Expansion" => trim($set)));
}

 public static function absolutizeHtml($sBaseUrl, $sHtml)
 {
     $oHtml = new simple_html_dom();
     $oHtml->load($sHtml);
     $aTags = $oHtml->find('a');
     foreach ($aTags as $oTag) {
         $oTag->href = self::absolutizeUrl($sBaseUrl, $oTag->href);
     }
     $aTags = $oHtml->find('img');
     foreach ($aTags as $oTag) {
         $oTag->src = self::absolutizeUrl($sBaseUrl, $oTag->src);
     }
     $aTags = $oHtml->find('script');
     foreach ($aTags as $oTag) {
         $oTag->src = self::absolutizeUrl($sBaseUrl, $oTag->src);
     }
     $aTags = $oHtml->find('link');
     foreach ($aTags as $oTag) {
         $oTag->href = self::absolutizeUrl($sBaseUrl, $oTag->href);
     }
     // Parse url() in inline css
     $aTags = $oHtml->find('style');
     foreach ($aTags as $oTag) {
         $oTag->innertext = preg_replace_callback('|url\\s*\\(\\s*[\'"]?([^\'"\\)]+)[\'"]?\\s*\\)|', function ($aMatches) use($sBaseUrl) {
             return 'url("' . trim(self::absolutizeUrl($sBaseUrl, $aMatches[1])) . '")';
         }, $oTag->innertext);
     }
     return $oHtml . '';
 }

 /**
  * 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];
 }

function scraper($url_search, $country_id)
{
    $has_next = false;
    $base_url = "http://ec.europa.eu/eures/eures-searchengine/servlet";
    $html = scraperwiki::scrape($url_search);
    $dom = new simple_html_dom();
    $dom->load($html);
    foreach ($dom->find('table[class=JResult]') as $result) {
        foreach ($result->find('td[class=JRTitle] a') as $job_page) {
            $chars = explode("'", $job_page->onclick);
            $url_job = $base_url . substr($chars[1], 1);
            $url_id = strstr($url_job, 'uniqueJvId=');
            $url_id = str_replace('uniqueJvId=', "", $url_id);
            echo "JOB: " . $url_job . "<br />";
        }
        foreach ($result->find('th') as $data) {
            $text = trim($data->plaintext);
            if ($text == 'Description:') {
                $description = trim($data->next_sibling()->plaintext);
                echo "DESCRIPTION: " . $description . "<br />";
            }
            if ($text == 'Source:') {
                $source = trim($data->next_sibling()->plaintext);
                $source = str_replace("'", "\\'", $source);
                if ($source != '' && $source != '&nbsp;') {
                    $source_id = insert_name('source', $source);
                    echo "SOURCE: " . $source . "<br /><br />";
                }
            }
        }
        $description = str_replace("'", "\\'", $description);
        $description = str_replace("</BR>", "", $description);
        $sql = mysql_query("SELECT * FROM job WHERE url = '{$url_job}'");
        $cont = mysql_num_rows($sql);
        if ($cont == 0) {
            mysql_query("INSERT INTO job SET \n\t\t\t\t\turl = '{$url_job}', \n\t\t\t\t\turl_id = '{$url_id}', \n\t\t\t\t\tdescription = '{$description}', \n\t\t\t\t\tsource_id = '{$source_id}', \n\t\t\t\t\turl_search = '{$url_search}', \n\t\t\t\t\tcountry_id='{$country_id}',\n\t\t\t\t\turl_scraper_date = SYSDATE(),\t \n\t\t\t\t\turl_scraper_hour = SYSDATE()");
        } else {
            echo "Job URL already extracted: " . $url_job . "<br /><br />";
        }
    }
    foreach ($dom->find('div[class=prevNext] a') as $next_page) {
        $text = $next_page->plaintext;
        if ($text == "Next page") {
            $url_next = substr($next_page->href, 1);
            $url_next = $base_url . $url_next;
            $has_next = true;
            print "<br /><br />NEXT: " . $url_next . "<br /><br />";
        }
    }
    unset($html, $dom, $result, $job_page, $data, $next_page, $text, $url_id, $url_job, $description, $source, $source_id, $url_search);
    //Comment this for tests, uncomment this to get all data
    //	if ($has_next == true){
    //		sleep(1);
    //		scraper($url_next, $country_id);
    //	}
}

 /**
  * 创建表结构
  * @param $configs
  */
 private static function createTables($configs)
 {
     $tables = self::$XML->find("table");
     foreach ($tables as $value) {
         $tableName = $configs["table-prefix"] . $value->name;
         self::query("DROP TABLE IF EXISTS `{$tableName}`");
         $sql = "CREATE TABLE `{$tableName}`(";
         $pk = $value->find("pk", 0);
         if ($pk) {
             $sql .= "`{$pk->name}` {$pk->type} NOT NULL ";
             if ($pk->ai) {
                 $sql .= "AUTO_INCREMENT ";
             }
             $sql .= "COMMENT '主键',";
         }
         //添加字段
         $fields = $value->find("fields", 0);
         if ($fields) {
             foreach ($fields->children() as $fd) {
                 if ($fd->default || $fd->default === "0") {
                     //has default value
                     if (in_array($fd->default, self::$DEFAULT_VALUE_KEYWORD)) {
                         $sql .= "`{$fd->name}` {$fd->type} NOT NULL DEFAULT {$fd->default} COMMENT '{$fd->comment}',";
                     } else {
                         $sql .= "`{$fd->name}` {$fd->type} NOT NULL DEFAULT '{$fd->default}' COMMENT '{$fd->comment}',";
                     }
                 } else {
                     //has not default value
                     $sql .= "`{$fd->name}` {$fd->type} NOT NULL COMMENT '{$fd->comment}',";
                 }
                 //创建索引
                 if ($fd->getAttribute("add-index") == "true") {
                     $indexType = $fd->getAttribute("index-type");
                     if ($indexType == "normal") {
                         $sql .= "KEY `{$fd->name}` (`{$fd->name}`), ";
                     } elseif ($indexType == "unique") {
                         $sql .= "UNIQUE KEY `{$fd->name}` (`{$fd->name}`),";
                     }
                 }
             }
         }
         if ($pk) {
             $sql .= "PRIMARY KEY (`{$pk->name}`)";
         }
         $sql .= ") ENGINE={$value->engine}  DEFAULT CHARSET={$configs['charset']} COMMENT='{$value->comment}' AUTO_INCREMENT=1 ;";
         if (self::query($sql) !== false) {
             tprintOk("create table '{$tableName}' successfully.");
         } else {
             tprintError("create table '{$tableName}' faild.");
             tprintError(self::$DB_CONN->error);
         }
     }
 }

 public function find($url)
 {
     # sanitize url
     $url = strip_tags($url);
     $url = urldecode($url);
     # Remove the end character
     if ($url[strlen($url) - 1] == '/') {
         $url = substr($url, 0, strlen($url) - 1);
     }
     # test if 'http://' is present
     if (strpos($url, 'http://') !== 0) {
         $url = 'http://' . $url;
     }
     # Tabs of rss feeds urls
     $results = array();
     # Try to load the content of url
     $content = @file_get_contents($url);
     if (!empty($content)) {
         $html = new simple_html_dom();
         $html->load($content, true);
         # Check if it is an url to feeds
         if (count($html->find('channel')) > 0) {
             $results[] = array('href' => $url, 'title' => 'RSS');
         } else {
             if (count($html->find('feed')) > 0) {
                 $results[] = array('href' => $url, 'title' => 'Atom');
             } else {
                 # Get links markup
                 $links = $html->find('link');
                 foreach ($links as $link) {
                     $href = $link->href;
                     $title = $link->title;
                     # Fix url to avoid path errors
                     if ($href[0] == '/') {
                         #
                         $href = $url . $href;
                     }
                     # Get the resource type
                     $type = $link->type;
                     # Save only feeds
                     if (!in_array($href, $results) && (ereg('application.*rss', $type) || ereg('application.*atom', $type))) {
                         $results[] = array('href' => $href, 'title' => $title);
                     }
                 }
             }
         }
     }
     # transform results tab into json tab
     echo json_encode($results);
 }

 public function get_images($chapter_url, $prefix, $infix)
 {
     $ifx = Text::create($infix)->pad(3)->to_s();
     $p = new Page($chapter_url);
     $h = new simple_html_dom();
     $h->load($p->content());
     $select = $h->find('select[name="pagejump"]', 0);
     $img = $h->find('#page', 0)->find('img', 0);
     $srcdir = dirname($img->src);
     $pages = array();
     foreach ($select->find('option') as $opt) {
         $pages["{$prefix}-{$infix}-{$opt->value}.jpg"] = $srcdir . '/' . $opt->value . '.jpg';
     }
     return $pages;
 }

function scrappe_offre($html, $reference)
{
    $dom = new simple_html_dom();
    $dom->load($html);
    $div = $dom->find("div.tx-sqliwebServiceanpe-pi5");
    $span = $dom->find("div.tx-sqliwebServiceanpe-pi5 span.texteANPEDetail");
    $actualisation = $span[1]->plaintext;
    foreach ($span as $data) {
        $tds = $data->find("td");
        $record = array('actualiseJJ' => intval($actualisation[29] . $actualisation[30]), 'actualise le' => $actualisation, 'type_contrat' => $span[5]->plaintext, 'analyse_type_contrat' => "", 'experiance' => $span[6]->plaintext);
        print json_encode($record) . "\n";
        #scraperwiki::save(array('contenu_offre'), $record);
    }
    #return ;
}

function scrapeHTML($param, $type)
{
    $html = scraperWiki::scrape(BASE_URL . "?type={$param}");
    $dom = new simple_html_dom();
    $dom->load($html);
    // Iterate over table rows and get flight details.
    foreach ($dom->find("TR[@HEIGHT='25']") as $data) {
        // Flight details.
        $tds = $data->find("td");
        $airline = removeSpaces($tds[0]->plaintext);
        $flight_type = $type;
        $flight_num = removeSpaces($tds[1]->plaintext);
        $destination = removeSpaces($tds[2]->plaintext);
        $time = removeSpaces($tds[3]->plaintext);
        $gate = removeSpaces($tds[4]->plaintext);
        $remarks = removeSpaces($tds[5]->plaintext);
        // Skip header row. Cheesy, but effective.
        if ($airline == "Airline") {
            continue;
        }
        // Set the date.
        $date = date("m.d.y");
        // Build up record to store.
        $flight_data = array("date" => $date, "airline" => $airline, "flight_type" => $flight_type, "flight_num" => $flight_num, "destination" => $destination, "time" => $time, "gate" => $gate, "remarks" => $remarks);
        // Save the record.
        saveData(array("date", "airline", "flight_type", "flight_num"), $flight_data);
    }
    $dom->clear();
}