Created
October 12, 2012 15:35
-
-
Save cherenkov/3879812 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
//PHP5.3でパーサーを作る勉強をしています。 http://ja.wikipedia.. - 人力検索はてな | |
//http://q.hatena.ne.jp/1350045786 | |
function pr($var) { | |
echo '<pre>'; print_r($var); echo '</pre>'; | |
} | |
header('Content-Type:text/html; charset=UTF-8'); | |
require_once("./simplehtmldom/simple_html_dom.php"); | |
/* | |
function getWikiSummary($keyword) { | |
$result = ''; | |
$url = 'http://ja.wikipedia.org/wiki/' . urlencode($keyword); | |
$url = preg_replace('/%28/u', '(', $url); //括弧はこの処理をしないとダメみたい。 | |
$url = preg_replace('/%29/u', ')', $url); | |
$html = file_get_html($url); | |
$ps = $html->find('#mw-content-text > p'); | |
for ($i = 0, $n = count($ps); $i < $n; $i++) { | |
if (preg_match('/' . preg_replace('/_\(.+?\)/u' , '', $keyword) . '/u', $ps[$i]->innertext)) { | |
pr($ps[$i]->innertext); | |
$result .= $ps[$i]->innertext; | |
if ($ps[$i]->nextSibling()->tag === 'table') { | |
break; | |
} | |
} | |
} | |
$html->clear(); | |
return $result; | |
} | |
*/ | |
function getWikiSummary($keyword) { | |
$result = ''; | |
$url = 'http://ja.wikipedia.org/wiki/' . urlencode($keyword); | |
$url = preg_replace('/%28/u', '(', $url); //括弧はこの処理をしないとダメみたい。 | |
$url = preg_replace('/%29/u', ')', $url); | |
$html = file_get_html($url); | |
$ps = $html->find('#mw-content-text > p'); | |
for ($i = 0, $n = count($ps); $i < $n; $i++) { | |
$result .= $ps[$i]->innertext; | |
if ($ps[$i]->nextSibling()->tag === 'table') { | |
break; | |
} | |
} | |
$html->clear(); | |
return $result; | |
} | |
$keywords = array('東京太・ゆめ子', 'カナリア_(お笑い)'); | |
echo '<dl>'; | |
foreach ($keywords as $keyword) { | |
$summary = getWikiSummary($keyword); | |
echo '<dt>' . $keyword . '</dt>'; | |
echo '<dd>' . $summary . '</dd>'; | |
} | |
echo '</dl>'; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment