php模拟登陆，网络爬虫

最新推荐文章于 2024-05-04 15:02:21 发布

yhz1209

最新推荐文章于 2024-05-04 15:02:21 发布

阅读量1.3k

点赞数

文章标签：爬虫

本文链接：https://blog.csdn.net/yhz1209/article/details/8945085

版权

private function findBook($data,$msg,$user){
		$html = new simple_html_dom();
		$post_fields=array(
				"bor_id"=>$user["patron_barcode"],
				"bor_verification"=>$user["patron_password"]
		);
		$login_url="";
		$cookie_file = tempnam('temp','cookie');
		//模拟登陆
		$ch = curl_init($login_url);
		curl_setopt($ch, CURLOPT_HEADER, 0);
		curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
		curl_setopt($ch, CURLOPT_POST, 1);
		curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
		curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
		$contents = curl_exec($ch);
		
		//获取数据
		$ch = curl_init('');
		curl_setopt($ch, CURLOPT_HEADER, 0);
		curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
		curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
		$contents = curl_exec($ch);
		curl_close($ch);
		
		
		
		$back = array("data"=>array());
		$i = 0;
		$type="news";
		$html->load($contents);
		
		foreach($html->find('table[class=items]') as $item){
			$tit=$item->find('div.itemtitle a',0);
			$des=$item->find('td.col2 table tbody tr',0);
			$mes=$item->find('td.libs a',0);
			$img=$item->find('td img',-1);
			$back['data'][$i++] = array (
					"Title" => str_replace(" ","",$tit->plaintext)."\n".$mes->plaintext,
					"Url" => $tit->href,
					"Description"=>str_replace(" ","",$des->plaintext),
					"PicUrl"=>$img->src
			);
		}
		
		return new back($msg->getToUsername(),$msg->getFromUsername(),$back, $type, $msg->getCreateTime(),0);
	}

html解析用PHP Simple HTML DOM Parser