火车头伪原创，火车头采集器php插件

火车头伪原创之所以使用多个NLP项目，是因为百度AI本来就是用来完成整个项目的。但是由于火车头采集器php插件的自然语言处理API，对于普通用户来说，通话次数是有限制的，超出部分是要收费的，所以数据量大的处理会交给HanLP项目。减少数据量分词交给百度AI处理。

至于同义词库文件的位置，不建议移动或更改。文件夹和名称都一样。有时间跟进，再优化这个问题。

火车头采集器php插件源码：

<?php


set_time_limit(270);
error_reporting(E_ERROR | E_WARNING | E_PARSE);

define('TITLE_SEPAR', 'xxx**xxx');
define('TITLE_SEPAR2', '262661');


$url = 'http://api-2.xiaofamao.com/api.php?json=0&v=1&key=aa740455217';

$content_tag_name = '内容';
$realtime_keyword = '锁词'; // 关键词,小发猫,伪原创     用英文逗号隔开
$title_tag_name = '标题';



$headdd = '';
$taill = '';



switch($LabelArray['PageType'])
{
    case 'List'://处理列表页，只能处理html
        break;
    case 'Pages'://处理多页，只能处理html
        break;
    case 'Content'://处理默认页，只能处理html
        break;
    case 'Save'://只有保存时是可以处理标签值的
        // 保存原文

    try {
    /**********************************************************************/
    // 这一步用来获取伪原创文章
    /**********************************************************************/
    $title = $LabelArray[$title_tag_name];
    $title = '标题：'.$title;

    $content = $LabelArray[$content_tag_name];


    $realtime_keyword = $LabelArray[$realtime_keyword]; // 动态锁词



    $article_src = compose_article($title, $content);
    $article_src_b = $article_src;

    $article_new = get_wyc_article($article_src, $realtime_keyword);


    $title_wyc = trim($article_new[0]);
    $content_wyc = trim($article_new[1]);

    $content_wyc = fix_newline($content_wyc);
    $content_wyc = str_replace('标签：', '标签:', $content_wyc);
    $LabelArray[$content_tag_name] = $headdd. $content_wyc. $taill;

    $title_wyc = str_replace(array('。','，','％'), array(' ',' ',' '), $title_wyc);
    $LabelArray[$title_tag_name] = $title_wyc;

    }
    catch (Exception $e) {
        $LabelArray['标题'] .= $e->getMessage();
        $LabelArray[$content_tag_name] .= $e->getMessage();
    }
        break;
    default:
        //$LabelArray[$content_tag_name]=curl_request($url, array('wenzhang'=>$LabelArray[$content_tag_name] ));
}

echo serialize($LabelArray);



function compose_article($title, $content) {
    $separator = compose_separator();
    return $title.$separator.$content;
}

function compose_separator() {
    return PHP_EOL.'('.TITLE_SEPAR2.')'.PHP_EOL;
}


function fix_separator($article) {
    return $article;
}


function get_wyc_article($str, $realtime_keyword) {
    global $url;
    $separator = compose_separator();
    $separator = str_replace(PHP_EOL, '', $separator);
    $wyc = curl_request($url, array('wenzhang'=>$str, 'keywords'=>$realtime_keyword));

    $wyc_f = $wyc;
    $wyc = fix_separator($wyc);
    $wyc = explode($separator, $wyc);

    if (isset($wyc[0])){
        $wyc[0] = str_replace('标题：', '', $wyc[0]);
        $wyc[0] = str_replace('标题:', '', $wyc[0]);
        $wyc[0] = str_replace('目：', '', $wyc[0]);
        $wyc[0] = str_replace('目:', '', $wyc[0]);
        $wyc[0] = 'xx`xx'.$wyc[0];
        $wyc[0] = str_replace('xx`xx题', '', $wyc[0]);
        $wyc[0] = str_replace('xx`xx', '', $wyc[0]);
    }

    //if (isset($wyc[1])) $wyc[1] = trim($wyc[1]);
    //$wyc[1] = $wyc_f.'jjjjjjjj'.$wyc[1];
    return $wyc;
}


function get_wyc_title($str) {
    $title = get_wyc_article($str.PHP_EOL.PHP_EOL.PHP_EOL.$str.PHP_EOL.PHP_EOL.PHP_EOL.$str);
    $title = fix_newline($title);
    $title = explode(PHP_EOL, $title);
    return $title[0];
}

function get_keywords($title, $contents) {
    $url_kw = 'http://api-2.78tp.com/nlp/kws.php?appid=';
    $kws = curl_request($url_kw, array(
    'title'=>$title,
    'len'=>100,
    'text'=>$contents));

    return $kws;
}


function remove_alt($contents) {
    $contents = preg_replace('/alt="(.*)"/', '', $contents);
    return $contents;
}


function fix_title($contents) {
    $punctuation_symbol = array('。', '？', '，', '：', '；', '、', '！',
                                '.',  '?',  ',',  ':',  ';', '!');

     $contents = str_replace($punctuation_symbol, '', $contents);
    return $contents;
}

function br2newline($contents) {
    $contents = str_replace('<br>', PHP_EOL, $contents);
    $contents = str_replace('<br/>', PHP_EOL, $contents);
    $contents = str_replace('<br />', PHP_EOL, $contents);
    $contents = str_replace('<BR/>', PHP_EOL, $contents);
    $contents = str_replace('<BR>', PHP_EOL, $contents);
    $contents = str_replace('<BR />', PHP_EOL, $contents);

    return $contents;
}

function newline2br($contnets) {
    $contnets = str_replace(PHP_EOL, "<br>", $contnets);
//    $contnets = str_replace('><br><', '><', $contnets);
    $contnets = str_replace('<p><br>', '<p>', $contnets);
    return $contnets;
}


function delete_newline($contents) {
    $contents = fix_newline($contents);
//    $contents = str_replace(PHP_EOL.PHP_EOL, PHP_EOL, $contents);
//    $contents = str_replace('>'.PHP_EOL, '>', $contents);
    return $contents;
}

function reset_newline_win($contents) {
    // 优化换行符
    $contents = str_replace("
", "
", $contents);
    $contents = str_replace("
", "
", $contents);
    $contents = str_replace("
", PHP_EOL, $contents);

    return $contents;
}

function fix_newline($data) {
    $data = str_replace("
", "
", $data);
    while(strpos($data, "

") !== false) {
        $data = str_replace("

", "
", $data);
    }
    $data = str_replace("
", PHP_EOL, $data);

    return $data;
}

function clean_contents($contents) {
//    $str = preg_replace('#<([^>s/]+)[^>]*>#','<$1>', $contents);
//    return $str;
    $sa = new cleanHtml;  
    $sa->allow = array( 'src' );    
    $sa->exceptions = array(  
    'img' => array( 'src', 'alt' ),  
    //'a' => array( 'href', 'title' ),  
    'iframe'=>array('src','frameborder'),  
    ); 
    $str = $sa->strip( $contents );   

    return $str;
}


function xfm_strong_str_replace_once($search, $replace, $subject) {
    $firstChar = strpos($subject, $search);
    if($firstChar !== false) {
        $beforeStr = substr($subject,0,$firstChar);
        $afterStr = substr($subject, $firstChar + strlen($search));
        return $beforeStr.$replace.$afterStr;
    } else {
        return $subject;
    }
}

//参数1：访问的URL，参数2：post数据(不填则为GET)，参数3：提交的$cookies,参数4：是否返回$cookies
function curl_request($url,$post='',$cookie='', $returnCookie=0){
    if (! extension_loaded('curl')) {
        file_exists('./ext/php_curl.dll') && dl('php_curl.dll'); // 加载扩展
    }
    
        $curl = curl_init();
        curl_setopt($curl, CURLOPT_URL, $url);
        curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)');
    if (ini_get('open_basedir') == '' && strtolower(ini_get('safe_mode')) != 'on'){ 
        curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);
    }
        curl_setopt($curl, CURLOPT_AUTOREFERER, 1);
        curl_setopt($curl, CURLOPT_REFERER, "http://XXX");
        if($post) {
            curl_setopt($curl, CURLOPT_POST, 1);
            curl_setopt($curl, CURLOPT_POSTFIELDS, http_build_query($post));
        }
        if($cookie) {
            curl_setopt($curl, CURLOPT_COOKIE, $cookie);
        }
        curl_setopt($curl, CURLOPT_HEADER, $returnCookie);
        curl_setopt($curl, CURLOPT_TIMEOUT, 150);
        curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
        $data = curl_exec($curl);
        if (curl_errno($curl)) {
            return curl_error($curl);
        }
        curl_close($curl);
        if($returnCookie){
            list($header, $body) = explode("

", $data, 2);
            preg_match_all("/Set-Cookie:([^;]*);/", $header, $matches);
            $info['cookie']  = substr($matches[1][0], 1);
            $info['content'] = $body;
            return $info;
        }else{
            return $data;
        }
}

//echo $tag;
// 计算中文字符串长度
function utf8_strlen($string = null) {
// 将字符串分解为单元
preg_match_all("/./us", $string, $match);
// 返回单元个数
return count($match[0]);
}


function reg_escape( $str )  
{  
    $conversions = array( "^" => "^", "[" => "[", "." => ".", "$" => "$", "{" => "{", "*" => "*", "(" => "(", "\" => "\\", "/" => "/", "+" => "+", ")" => ")", "|" => "|", "?" => "?", "<" => "<", ">" => ">" );  
    return strtr( $str, $conversions );  
}  
  
/** 
* Strip attribute Class 
* Remove attributes from XML elements 
* @author David (semlabs.co.uk) 
* @version 0.2.1 
*/  
  
class cleanHtml{  
      
    public $str         = '';  
    public $allow       = array();  
    public $exceptions  = array();  
    public $ignore      = array();  
      
    public function strip( $str )  
    {  
        $this->str = $str;  
          
        if( is_string( $str ) && strlen( $str ) > 0 )  
        {  
            $res = $this->findElements();  
            if( is_string( $res ) )  
                return $res;  
            $nodes = $this->findAttributes( $res );  
            $this->removeAttributes( $nodes );  
        }  
          
        return $this->str;  
    }  
      
    private function findElements()  
    {  
        # Create an array of elements with attributes  
        $nodes = array();  
        preg_match_all( "/<([^ !/>
]+)([^>]*)>/i", $this->str, $elements );  
        foreach( $elements[1] as $el_key => $element )  
        {  
            if( $elements[2][$el_key] )  
            {  
                $literal = $elements[0][$el_key];  
                $element_name = $elements[1][$el_key];  
                $attributes = $elements[2][$el_key];  
                if( is_array( $this->ignore ) && !in_array( $element_name, $this->ignore ) )  
                    $nodes[] = array( 'literal' => $literal, 'name' => $element_name, 'attributes' => $attributes );  
            }  
        }  
          
        # Return the XML if there were no attributes to remove  
        if( !$nodes[0] )  
            return $this->str;  
        else  
            return $nodes;  
    }  
      
    private function findAttributes( $nodes )  
    {  
          
        # Extract attributes  
        foreach( $nodes as &$node )  
        {  
            preg_match_all( "/([^ =]+)s*=s*["|']{0,1}([^"']*)["|']{0,1}/i", $node['attributes'], $attributes );  
            if( $attributes[1] )  
            {  
                foreach( $attributes[1] as $att_key => $att )  
                {  
                    $literal = $attributes[0][$att_key];  
                    $attribute_name = $attributes[1][$att_key];  
                    $value = $attributes[2][$att_key];  
                    $atts[] = array( 'literal' => $literal, 'name' => $attribute_name, 'value' => $value );  
                }  
            }  
            else  
                $node['attributes'] = null;  
              
            $node['attributes'] = $atts;  
            unset( $atts );  
        }  
          
        return $nodes;  
    }  
      
    private function removeAttributes( $nodes )  
    {  
          
        # Remove unwanted attributes  
        foreach( $nodes as $node )  
        {  
              
            # Check if node has any attributes to be kept  
            $node_name = $node['name'];  
            $new_attributes = '';  
            if( is_array( $node['attributes'] ) )  
            {  
                foreach( $node['attributes'] as $attribute )  
                {  
                    if( ( is_array( $this->allow ) && in_array( $attribute['name'], $this->allow ) ) || $this->isException( $node_name, $attribute['name'], $this->exceptions ) )  
                        $new_attributes = $this->createAttributes( $new_attributes, $attribute['name'], $attribute['value'] );  
                }  
            }  
            $replacement = ( $new_attributes ) ? "<$node_name $new_attributes>" : "<$node_name>";  
            $this->str = preg_replace( '/'. reg_escape( $node['literal'] ) .'/', $replacement, $this->str );  
        }  
          
    }  
      
    private function isException( $element_name, $attribute_name, $exceptions )  
    {  
        if( array_key_exists($element_name, $this->exceptions) )  
        {  
            if( in_array( $attribute_name, $this->exceptions[$element_name] ) )  
                return true;  
        }  
          
        return false;  
    }  
      
    private function createAttributes( $new_attributes, $name, $value )  
    {  
        if( $new_attributes )  
            $new_attributes .= " ";  
        $new_attributes .= "$name="$value"";  
          
        return $new_attributes;  
    }  
  
}  

?>

我的其他文章：

1、火车头采集伪原创插件PHP版实现

2、火车头伪原创插件使用教程

3、火车头如何调用百度NLP摘要，这里给大家一个PHP示例

4、自然语言处理技术开发的伪原创工具

5、火车头采集标题如何伪原创（附教程）