[PHP　HTML　スクレイピング] あるWEBページの複数データ（例htt.. - 人力検索はてな http://q.hatena.ne.jp/1338651304

log201206030130.csv

sample.php

<?php
require_once 'simplehtmldom/simple_html_dom.php';

header('Content-Type:text/html; charset=UTF-8');
function pr($var) {
	echo '<pre>'; print_r($var); echo '</pre>';
}
function strAbbr($str, $n) {
	$result = mb_substr($str, 0, $n, 'UTF-8');
	if (mb_strlen($str, 'UTF-8') > $n) {
		$result = $result . '...';
	}
	return $result;
}

$baseurl = 'http://ja.wikipedia.org/wiki/';
$csv = '';
for ($i=1; $i<5; $i++) {
	$url = $baseurl . $i;
	$html = file_get_html($url);
	$title = $html->find('#firstHeading', 0)->plaintext;
	$body = $html->find('#mw-content-text p', 0)->plaintext;
	$body = strAbbr($body, 25);
	$csv .= "{$title},{$body}\n";
}
echo $csv;


date_default_timezone_set("Japan");
$mytime = date('YmdHi');
$filename = "./log{$mytime}.csv";
file_put_contents($filename, $csv, FILE_APPEND);