/**
* Scrape the given topic url for all the posts in a topic and return as xml.
*/
private function scrape_topic($link)
{
$scraper = new Scraper($link);
$scraper->run();
$topic_scraper = new GoogleGroupsTopicScraper($scraper->html);
$topic = $topic_scraper->run();
$i = 0;
$xml = '';
if (is_array($topic)) {
foreach ($topic as $detail) {
$xml .= " <post idx=\"{$i}\">\n";
$xml .= ' <author>' . $detail['author'] . "</author>\n";
$xml .= ' <email>' . $detail['email'] . "</email>\n";
$xml .= ' <date>' . $detail['date'] . "</date>\n";
$xml .= ' <timestamp>' . $detail['timestamp'] . "</timestamp>\n";
$xml .= " <body>\n";
$xml .= "<![CDATA[\n" . $detail['body'] . "\n]]>\n";
$xml .= " </body>\n";
$xml .= " </post>\n";
$i++;
}
} else {
print "ERROR: bad topic (url={$link})\n";
}
return $xml;
}
//
curl_setopt($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
//
curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, true);
curl_setopt($ch, CURLOPT_CURLOPT_MAXREDIRS, 10);
$this->result = curl_exec($ch);
curl_close($ch);
}
private function exec_FGC()
{
$this->result = file_get_contents($this->url);
}
public function run()
{
switch (CURL_ENABLED) {
case true:
$this->exec_CURL();
break;
case false:
$this->exec_FGC();
break;
}
}
}
$url = $_GET['url'];
$scraper = new Scraper($url);
$scraper->run();
echo '<pre>';
print_r($scraper->result);
echo '</pre>';