火车头采集器伪原创插件【php源码】

火车头采集是一款基于Python语言开发的网络爬虫工具，用于快速高效地从互联网上采集数据并存储到本地或远程数据库。它简单易用且功能强大，在各行各业广泛应用。

火车头采集器AI伪原创PHP源码：

<?php
header("Content-type: text/html; charset=gb2312");
set_time_limit(0);
 
error_reporting(E_ALL); 
ini_set('display_errors', '1'); 
 
define ("CUR_DIR", '../');
define('TITLE_SEPAR', 'xxxxx');
 
 
// 这里是你的API地址，需要到 www.xiaofamao.com 申请
define('API_URL', 'http://api.xiaofamao.com/api.php?json=0&v=2&key=yuyu');
 
 
// 待执行目录
define('CUR_FOLDER', CUR_DIR.'word');
// 执行后保存目录
define('DEST_FOLDER', CUR_DIR.'xiaofamao');
// 执行后保存目录 失败
define('DEST_FOLDER_FAIL', CUR_DIR.'xiaofamao_fail');
 
 
$one_file = get_one_file();
 
 
// 判断是否还有任务
if (!$one_file){
    echo PHP_EOL.'* 任务数为0, 程序已退出';
    exit;
}
 
while ($one_file) {
 
    echo PHP_EOL.'* 正在执行：' . PHP_EOL. file_path($one_file);
 
    echo PHP_EOL.'* 请耐心等候...';
 
    $data_arr = get_contents_filter(file_path($one_file));
 
    $title = $data_arr['title'];
    $title_src = $data_arr['title'];
 
    $content = $data_arr['content'];
    $content = replace_shuminghao($content);
    $content = get_utf8_data($content);
 
    $new_content = curl_request(API_URL, array('wenzhang'=>$content));
    $new_content = get_gbk_data($new_content);
    $new_content = restore_shuminghao($new_content);
 
#var_dump($new_content);
 
    $new_content = content_format($new_content);
    $new_content = $new_content;
 
    #$new_title = get_ai_title($title);
	$title = get_utf8_data($title);
    $new_title = $title;
    //$new_title =curl_request(API_URL, array('wenzhang'=>$title));
	//$new_title = get_gbk_data($new_title);
    #echo $new_title;
 
    # 如果标题伪原创成功
    if ($new_title === 'xx'.$title) {
        $new_title = get_gbk_data($title);
        //save_new_file(DEST_FOLDER_FAIL.DIRECTORY_SEPARATOR.$new_title.'.txt', $new_content);
        save_new_file(DEST_FOLDER_FAIL.DIRECTORY_SEPARATOR.$title_src.'.txt', $new_content);
    }
    else {
        $new_title = strip_tags($new_title);
        $new_title = str_replace(':', "：", $new_title);
        $new_title = str_replace('?', "？", $new_title);
        $new_title = str_replace(array('*','"','<','>','|'),'_', $new_title);
        $new_title = get_gbk_data($new_title);
 
        #$title = get_gbk_data($title);
        #save_new_file(DEST_FOLDER.DIRECTORY_SEPARATOR.$new_title.'.txt', $new_content);
        save_new_file(DEST_FOLDER.DIRECTORY_SEPARATOR.$title_src.'.txt', $new_content);
        #save_new_file(DEST_FOLDER.DIRECTORY_SEPARATOR.$new_title.'.txt', $content);
    }
 
    //
    //
 
    #save_new_file(DEST_FOLDER.DIRECTORY_SEPARATOR.$title.'.txt', $new_content);
    file_ok($one_file);
 
    //show_info_gb2312('伪原创结果：'.PHP_EOL. $final_data);
    //save_new_file(DEST_FOLDER.DIRECTORY_SEPARATOR.$new_title, $new_content);
 
//var_dump($final_data);
 
//    sleep(3);
 
    $one_file = get_one_file();
//    show_reflesh();
}
 
show_info_gb2312(PHP_EOL.'任务完成'.PHP_EOL);
 
 
 
 
 
function replace_shuminghao($content) {
    $content = str_replace('![](', '<(', $content);
    $count = preg_match_all("/<\((.*?)\)/", $content, $matches);
    #var_dump($matches[0]);
    if (isset($matches[0][0]))
    {
        foreach ($matches[0] as $key => $value) {
	#echo $value;
            $new_val = '《'.$matches[1][$key].'》';
            $content = str_replace($value, $new_val, $content);
        }
    }
#echo $content;
    return $content;
}
 
 
function restore_shuminghao($content) {
    $count = preg_match_all("/《http(.*?)》/", $content, $matches);
    #var_dump($matches[0]);
    if (isset($matches[0][0]))
    {
        foreach ($matches[0] as $key => $value) {
            $new_val = '![](http'.$matches[1][$key].')';
            $content = str_replace($value, $new_val, $content);
        }
        #return $matches[0];
    }
    return $content;
}
 
 
 
function content_rewrite($content) {
    $data = curl_request(API_URL, array('wenzhang'=>$content));
    return $data;
}
 
function content_format($data) {
 
	$data = fix_newline($data);
	$data_arr = explode(PHP_EOL, $data);
	$ret_str = '';
	foreach($data_arr as $key =>