php爬虫爬取数据并存储至数据库

准备：php环境，phpspider请自行下载

下载地址：https://github.com/owner888/phpspider

文档：https://doc.phpspider.org/configs-members.html

在phpspider，demo文件里面新建一个php文件，my_spider.php，代码复制进去，在命令函下执行php my_spider.php能看到打印信息，数据库文件根据自己需要建一两个字段测试一下就好，这里就不给出数据库sql文件了

直接上代码：

require_once __DIR__ . '/../autoloader.php';

use phpspider\core\requests;

use phpspider\core\selector;

use \phpspider\core\db;

use \phpspider\core\queue;

/* Do NOT delete this comment */

/* 不要删除这段注释 */

//数据库配置

$db_config = array(

'host' => '127.0.0.1',

'port' => 3306,

'user' => 'root',

'pass' => 'root',

'name' => 'news',

);

// 数据库配置

$db = db::set_connect('default', $db_config);

// 数据库链接

//db::init_mysql();

//redis配置

$redis_config = array(

'host' => '127.0.0.1',

'port' => 6379,

'pass' => '',

'db' => 5,

'prefix' => 'phpspider',

'timeout' => 30,

);

queue::set_connect('redis',$redis_config);

queue::select(5);

//抓取虎扑网nba数据

$html = requests::get('https://voice.hupu.com/nba');

获取列表资讯链接

$url = selector::select($html,"//div[@class='voice-main']//li//h4//a/@href");

//$url = array_reverse($url);

//定义数组

$spider_data = [];

foreach ($url as $key => $v){

//通过连接抓取内部内容

$detail_html = requests::get($v);

//保存地址

$spider_data[$key]['url'] = $v;

//抓取标题

$spider_data[$key]['title'] = selector::select($detail_html,"/html/body/div[4]/div[1]/div[1]/h1");;

//获取封面图

$spider_data[$key]['cover'] = selector::select($detail_html,"/html/body/div[4]/div[1]/div[2]/div/div[1]/img/@src");

//图片数组

$spider_data[$key]['imgs'] =selector::select($detail_html,"/html/body/div[4]/div[1]//img/@src");

if(is_array($spider_data[$key]['imgs'])){

$spider_data[$key]['imgs'] = json_encode($spider_data[$key]['imgs']);

}else{

$spider_data[$key]['imgs'] = json_encode([$spider_data[$key]['imgs']]);

}

//获取内容

$spider_data[$key]['content'] = selector::select($detail_html,"/html/body/div[4]/div[1]/div[2]/div");

//获取时间

$spider_data[$key]['create_time'] = strtotime(selector::select($detail_html,"//*[@id=\"pubtime_baidu\"]"));

$spider_data[$key]['update_time'] = strtotime(selector::select($detail_html,"//*[@id=\"pubtime_baidu\"]"));

//获取来源

$spider_data[$key]['source'] = selector::select($detail_html,"//*[@id=\"source_baidu\"]/a");

//频道id

$spider_data[$key]['channel_id'] = 2;

//状态

$spider_data[$key]['status'] = 1;

//类型

$spider_data[$key]['type'] = 1;

//随机获取作者id

$admin_arr = array(23,24,25,26);

$admin_key = array_rand($admin_arr);

$spider_data[$key]['admin_id'] = $admin_arr[$admin_key];

//tag_id nba，先匹配，再分类

if(strpos($spider_data[$key]['content'],'采访') !== false || strpos($spider_data[$key]['content'],'记者') || strpos($spider_data[$key]['content'],'报道')){

$spider_data[$key]['tag_id'] = 103;

}else if(strpos($spider_data[$key]['content'],'伤') !== false){

$spider_data[$key]['tag_id'] = 3;

}else if(strpos($spider_data[$key]['content'],'签下') !== false || strpos($spider_data[$key]['content'],'签约') !== false || strpos($spider_data[$key]['content'],'引援') !== false ||

strpos($spider_data[$key]['content'],'转会') !== false){

$spider_data[$key]['tag_id'] = 1;

}else{

//随机获取分类

$tag_arr = array(5,13);

$tag_key = array_rand($tag_arr);

$spider_data[$key]['tag_id'] = $tag_arr[$tag_key];

}

}

var_dump($spider_data);exit;

本博客爬取的是虎扑资讯信息，如果导致爬取目标网站瘫痪，与本博无关，不做任何责任申明，只为技术。