报错界面如下:

主要错误就是:在我的代码第三行,有一个require错误

require.'../vendor/owner888/phpspider/autoloader.php';

原先我是这样写的,但是使用命令行去跑,就出错了,原因就在于这个require在dos的情况下,phpspider的引入的路径不对

然后后面改成了下面这样子,吧目录给定义成绝对目录,这样就木有问题了.

require__DIR__.'/../vendor/owner888/phpspider/autoloader.php';

这样子,就可以继续接着跑啦.

附带采集源码一份.

require __DIR__.'/../vendor/owner888/phpspider/autoloader.php';

require_once 'config.php';

use phpspider\core\phpspider;

use phpspider\core\db;

//下面这个注释删了就跑不起来.....

/* Do NOT delete this comment */

/* 不要删除这段注释 */

$configs = array(

'name' => '特玩',

'log_show' => true,

'tasknum' => 3,//爬虫任务数

'output_encoding' => 'UTF-8',

//'save_running_state' => true,

//主域名

'domains' =>[

'www.te5.com',

'te5.com'

],

//入口地址

'scan_urls' => [

'http://www.te5.com/btgame/zkyx/',//折扣游戏

'http://www.te5.com/btgame/h5/',//h5

],

//列表url 匹配规则

'list_url_regexes' => [

// "/btshouyou/list_\d+_\d+.html",

],

//详情页url 匹配规则

'content_url_regexes' =>[

"/btshouyou/\d+.html"

],

'db_config' => $config,

'fields' => [

[

'name' => "type_name",//类型

'selector' => "//div[@class='bread']/a[last()-1]",

'required' => true,

],

[

'name' => "tags_name",//标签

'selector' => "//div[@id='tezheng']/@data-tezheng",

'required' => false,

],

[

'name' => "title",//标题

'selector' => "//div[@class='left']//h1",

'required' => true,

],

[

'name' => "time",//时间

'selector' => "//ul[@class='i1']//li[i='日期：']/span",

'required' => true,

],

[

'name' => "size",//大小

'selector' => "//ul[@class='i1']//li[i='大小：']/span",

'required' => false,

],

[

'name' => "content",//内容

'selector' => "//div[@class='game_content']",

'required' => true,

],

[

'name' => "and_url",//安卓下载路径

'selector' => "//a[@class='and_btn']/@href",

'required' => false,

],

[

'name' => "ios_url",//苹果下载路径

'selector' => "//a[@class='ios_btn']/@href",

'required' => false,

],

[

'name' => "pc_url",//pc端下载路径

'selector' => "//a[@class='pc_btn']/@href",

'required' => false,

],

[

'name' => "img",//图片

'selector' => "//div[@class='img']//img/@src",

'required' => false,

],

[

'name' => "keywords",//关键词

'selector' => "//meta[@name='Keywords']/@content",

'required' => false,

],

[

'name' => "description",//描述

'selector' => "//meta[@name='description']/@content",

'required' => false,

],

[

'name' => "comments",//评论

'selector' => "//div[@class='comments']",

'required' => false,

],

],

);

//实例化蜘蛛

$spider=new phpspider($configs);

//采集初始=>数据库初始化

$spider->on_start = function($phpspider)

{

$db_config = $phpspider->get_config("db_config");

// 数据库连接

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

db::_init();

};

//详情页=>提取字段=>处理字段

$spider->on_extract_field = function($fieldname, $data, $page)

{

if ($fieldname == 'content' || $fieldname == 'comments')

{

$content = json_encode($data,JSON_UNESCAPED_UNICODE);

$content_gz = gzcompress($content);

$data = base64_encode($content_gz);

}

return $data;

};

//详情页=>提取最终的数据=>入库

$spider->on_extract_page = function($page, $data)

{

$savedata =[];

$savedata["cate_name"]="BT";

$savedata["app_name"]=$data["title"];

$savedata["type_name"]=$data["type_name"];

$savedata["tags_name"]=$data["tags_name"];

$savedata['create_time'] =$data["time"];

$savedata["content"]=$data["content"];

$savedata["comments"]=$data["comments"];

$savedata["and_btn"]=$data["and_url"];

$savedata["ios_btn"]=$data["ios_url"];

$savedata["pc_btn"]=$data["pc_url"];

$savedata["img"]=$data["img"];

$savedata["keywords"]=$data["keywords"];

$savedata["description"]=$data["description"];

$savedata["size"]=$data["size"];

$savedata['status'] = 1;//状态

$kwds1="传奇";

$kwds2="sf";

$str=strip_tags($savedata['app_name']);

$has_kwds=false;

if(strpos($str,$kwds1)!==false){

$has_kwds=true;

}

if(strpos($str,$kwds2)!==false){

$has_kwds=true;

}

//如果采集的数据content字段不为空,直接插入数据库

if($savedata['content']!==''&&$has_kwds===false){

$sql = "SELECT id from yx_app WHERE app_name='".$savedata['app_name']."';";

$row = db::get_one($sql);

if(empty($row)){

db::insert("yx_app", $savedata);//数据库保存

echo "数据已入库";

}else{

echo '数据重复，已跳过。。。。。';

}

}

return $data;

};

$spider->on_list_page = function($page, $content, $phpspider)

{

echo 'on_list_page:'.var_dump($page);

};

$spider->start();