public static function search($key, $next = 1)
{
echo '抓取页面' . PHP_EOL;
self::$key = $key;
httpCls::$response = '';
httpCls::set('host', crawlConf::$host);
httpCls::set('uri', crawlConf::$search . '?word=' . urlencode($key) . '&pn=' . $next . '&ssid=&lc=&from=&bd_page_type=&uid=&pu=&st=&wk=');
httpCls::set('agent', crawlConf::$browser[0]['agent']);
httpCls::set('accept', crawlConf::$browser[0]['accept']);
httpCls::set('cookie', crawlConf::$browser[0]['cookie']);
httpCls::send();
//返回内容
$content = httpCls::$response;
//*获取list
// var_dump($content);
$preg = "/\\<p\\><a href=\"(.*)?\\?ssid\\=(.*)?\"\\>.*?\\.(\\w*?)\\<\\/a\\>/i";
preg_match_all($preg, $content, $matches);
$data = array();
if ($matches) {
foreach ($matches[1] as $k => $id) {
$data[$id] = $matches[3][$k];
}
}
self::log('data', var_export($data, 1));
$next = self::next($content);
if ($next) {
$data = array_merge($data, self::search($key, $next));
}
return $data;
}
$key = '高考数学';
//抓取的分词
$list = crawlCls::search($key);
echo count($list) . PHP_EOL;
foreach ($list as $id => $type) {
switch ($type) {
//根据类型分析内容
case 'doc':
$data = crawlCls::doc($id);
crawlCls::save($data);
break;
case 'pdf':
// crawlCls::pdf($id);
// break;
// crawlCls::pdf($id);
// break;
case 'ppt':
// crawlCls::ppt($id);
// break;
// crawlCls::ppt($id);
// break;
case 'txt':
// crawlCls::txt($id);
// break;
// crawlCls::txt($id);
// break;
default:
crawlCls::log('type', $type . '的文件不可解析');
}
}
echo '抓取完成';