时间:2021-07-01 10:21:17 帮助过:8人阅读
[],
'link' => [],
'content' => [],
'source' => [],
'date' => [],
];
public function __construct()
{
try {
$this->_client = new Client();
$this->_crawler = $this->_client->request('GET', 'http://www.ningshan.gov.cn/Category_90/Index.aspx');
// $client->getClient()->setDefaultOption('config/curl/'.CURLOPT_TIMEOUT, 10);
} catch (Exception $e) {
throw new \Exception($e->getMessage(), 1);
}
}
public function getDate()
{
$this->_crawler->filter('div#list>ul>li>span')->each(function ($node) {
$this->_news['date'][] = $node->text();
});
}
public function getTitle()
{
$link = $this->_crawler->selectLink('宁陕县召开政协八届二十二次次常委会')->link();
var_dump($link->getUri);die;
$this->_crawler->filter('div#list>ul>li>a')->each(function ($node) {
if ($node->text() !== '宁陕要闻') {
$this->_news['title'][] = $node->text();
$this->_news['link'][] = $node->link();
$this->_news['source'][] = '宁陕要闻';
}
});
}
}
//-----------------------------------
try {
$spider = new Spider();
$spider->getDate();
$spider->getTitle();
echo json_encode($spider->_news, JSON_UNESCAPED_UNICODE);
} catch (Exception $e) {
echo $e->getMessage();
}
Goutte怎么获取a标签里面的url?或者好用的PHP爬虫库,谢谢
[],
'link' => [],
'content' => [],
'source' => [],
'date' => [],
];
public function __construct()
{
try {
$this->_client = new Client();
$this->_crawler = $this->_client->request('GET', 'http://www.ningshan.gov.cn/Category_90/Index.aspx');
// $client->getClient()->setDefaultOption('config/curl/'.CURLOPT_TIMEOUT, 10);
} catch (Exception $e) {
throw new \Exception($e->getMessage(), 1);
}
}
public function getDate()
{
$this->_crawler->filter('div#list>ul>li>span')->each(function ($node) {
$this->_news['date'][] = $node->text();
});
}
public function getTitle()
{
$link = $this->_crawler->selectLink('宁陕县召开政协八届二十二次次常委会')->link();
var_dump($link->getUri);die;
$this->_crawler->filter('div#list>ul>li>a')->each(function ($node) {
if ($node->text() !== '宁陕要闻') {
$this->_news['title'][] = $node->text();
$this->_news['link'][] = $node->link();
$this->_news['source'][] = '宁陕要闻';
}
});
}
}
//-----------------------------------
try {
$spider = new Spider();
$spider->getDate();
$spider->getTitle();
echo json_encode($spider->_news, JSON_UNESCAPED_UNICODE);
} catch (Exception $e) {
echo $e->getMessage();
}
现找的
$crawler = $client->request('GET', 'http://www.symfony.com/blog/');
$link = $crawler->selectLink('Security Advisories')->link();
print_r($link->getUri());
手册:http://symfony.com/doc/curren...
GIT:https://github.com/FriendsOfP...
采集类参考:http://flc.ren/2016/06/528.html