PHP HtmlParse Examples

Example #1

File: index.php Project: BigBin/web_crawler

<?php

require_once '../apps/conf_ini.php';
$oParser = new HtmlParse();
// アクセスする URL を指定
$URL = 'http://perldoc.jp/docs/modules/DBD-mysql-2.1026/DBD/mysql/INSTALL.pod';
$sHtml = getHtmlData($URL);
//UTF-8にエンコード
$enc = mb_detect_encoding($sHtml);
$sHtml = mb_convert_encoding($sHtml, "UTF-8", $enc);
//解析
$rtn = $oParser->execHtmlParse($sHtml);
if ($rtn !== false) {
    list($aSubject, $aUrl, $aNonTagHtml) = $rtn;
    $fp = fopen("C:/body.txt", 'w');
    $sLine = implode('', $aNonTagHtml);
    fwrite($fp, mb_convert_encoding($sLine, "SJIS", "UTF-8"));
    $flag = fclose($fp);
}

Example #2

File: get_html_url.php Project: BigBin/web_crawler

<?php

// Include
require_once '../apps/conf_ini.php';
require_once 'apps/class/Process/CollectUrl/CollectUrlDao_cls.php';
// 初期化
$oDb = new CollectUrlDao($oDbConnMng);
$oParser = new HtmlParse();
//
for ($iHierarchy = 0; $iHierarchy < 3; $iHierarchy++) {
    echo "Hierarchy:" . $iHierarchy . "\n";
    // i階層のURLを取得する
    $aUrlHeader = $oDb->getUrlByHierarchy($iHierarchy);
    for ($iCnt = 0; $iCnt < count($aUrlHeader); $iCnt++) {
        // アクセスする URL を指定
        echo $aUrlHeader[$iCnt]['url'] . "\n";
        // HTMLデータ取得
        $sHtml = getHtmlData($aUrlHeader[$iCnt]['url']);
        if (!$sHtml) {
            continue;
        }
        // UTF-8にエンコード
        $enc = mb_detect_encoding($sHtml);
        $sHtml = mb_convert_encoding($sHtml, "UTF-8", $enc);
        // 解析
        $oParser->execHtmlParse($sHtml);
        $rtn = $oParser->getResult();
        if ($rtn !== false) {
            list($aSubject, $aUrl) = $rtn;
            foreach ($aUrl as $iUrlNo => $sUrl) {
                if ($sUrl != '') {