从命令行向脚本传递参数

Question

我正在编写一个程序来抓取以下网站：https://filmstoon.in/

我想从中找到几部电影（蝙蝠侠前传、钢铁侠、敢死队 3）和电视剧（权力的游戏）并抓取标题、主持人 url 和元 url。我设法做到了这一点，但是，它是为特定标题手动制作的。代码：

include  ("simple_html_dom.php");
ini_set('max_execution_time', 0);
date_default_timezone_set('Europe/Vilnius');
$link = "https://filmstoon.in/series/game-of-thrones/";
$link1 = "https://filmstoon.in/batman-begins/";
$link2 = "https://filmstoon.in/iron-man/";
$link3 = "https://filmstoon.in/expendables-3/";

//TV Series
class episode{
  private $title;
  private $host_url;
  private $linking_url;
  public function setTitle($title){
    $this->title = $title;
  }
  public function getTitle(){
    return $this->title;
  }
  public function setHost_url($host_url){
    $this->host_url = $host_url;
  }
  public function getHost_url(){
    return $this->host_url;
  }
  public function setLinking_url($linking_url){
    $this->linking_url = $linking_url;
  }
  public function getLinking_url(){
    return $this->linking_url;
  }
}

function main(){
  $array_url = getting_url();
  foreach($array_url as $single_link){
    $episodeObject = info_from_linking($single_link);
    echo_to_server($episodeObject->getLinking_url(), $episodeObject->getHost_url(),  $episodeObject->getTitle());
    writeToFile($episodeObject->getLinking_url(), $episodeObject->getHost_url(),  $episodeObject->getTitle());
  }
}

function getting_url(){
  global $link;
  $html = file_get_html($link);
  $array_url = array();
  foreach($html->find('.les-content a') as $divClass) {
    $linking_url = $divClass->href;
    array_push($array_url, $linking_url);
  }
  return $array_url;
}

function info_from_linking($episode_link){
  $inside_linking = file_get_html($episode_link);
  $mainDiv = $inside_linking->find('div[class="main-content main-detail"]')[0];
  $title = $mainDiv->find('h3[itemprop="name"]',0)->plaintext;
  $host_url = $mainDiv->find('iframe',1)->src;
  $class = new episode;
  $class->setTitle($title);
  $class->setHost_url($host_url);
  $class->setLinking_url($episode_link);
  return $class;
}

function echo_to_server($linking_url, $host_url, $title){
  $date = date('m/d/Y H:i', time());
  echo "{$date} \t {$linking_url} \t {$host_url} \t {$title} \n";
}

function writeToFile($linking_url, $host_url, $title){
  $date = date('m/d/Y H:i', time());
  $result = array($date, $linking_url, $host_url, $title);
  $output = 'scrape.txt';
  file_put_contents($output, print_r($result, true), FILE_APPEND);
}
main();

//Movies
function get_content_movies($url){
    $htmlContent = file_get_contents($url);
    $dom = new simple_html_dom();
    $dom->load($htmlContent);
    if(count($dom->find('div[class="main-content main-detail"]'))>0){
      $file = $dom->find('div[class="main-content main-detail"]')[0];
      $title = $file->find('h3[itemprop="name"]',0)->plaintext;
      $host_url = $file->find('iframe',1)->src;
      $meta_link = $dom->find('meta[property="og:url"]',0)->content;
      $date = date('m/d/Y H:i', time());
      echo "{$date} \t {$host_url} \t {$meta_link} \t {$title} \n";
      $result = array($title, $host_url, $meta_link, $date);
      $output = 'scrape.txt';
      file_put_contents($output, print_r($result, true), FILE_APPEND);
    }
}
get_content_movies($link1);
get_content_movies($link2);
get_content_movies($link3);

一切正常，但是，我想这样写：

php crawler.php batman begins

或任何其他标题在cmd中执行代码时，它会专门找到movie/tv系列并执行我编写的脚本。

到目前为止，我唯一的想法就是抓取整个页面，将其存储在数据库中（例如 .txt 文件），然后使用 $argc 从中查找内容和 $argv。或者 - 转到主页并使用搜索功能。我在命令行中编写的参数将被传递到搜索表单，然后它将执行脚本。

但是，由于我是新手，所以我无法全神贯注地思考如何实现这些想法。

Answer 1

function getArgumentValues($argv, $seperator){
$values = "$argv[1]";
  foreach($argv as $key=>$value){
    if($key>1){
      $values.="$seperator$value";
      }
    }
return $values;
}

function get_content_movies($linkMovies, $argv){
    $htmlContent = file_get_contents($linkMovies);
    $argvValue = getArgumentValues($argv, " ");
    if(!preg_match("/href\=\"(.*?)\".*?oldtitle\=\"$argvValue/i", $htmlContent, $search)){
      return null;
    };
    $key = array_values($search)[1];
    $htmlContent = file_get_contents($key);
    if(preg_match("/series/", $key)){
      main();
    }
    else{
    preg_match('/\<h3 itemprop\=\"name\"\>(.*)<\/h3>/iSU', $htmlContent, $title);
    preg_match('/<iframe.*data-lazy-src=\"(.*)\".*><\/iframe>/iSU', $htmlContent, $embed_url);
    preg_match('/<meta.*property="og:url".*content="(.*)".*\/>/iSU', $htmlContent, $meta_url);
    $date = date('m/d/Y H:i', time());
    echo "{$date} \t {$embed_url[1]} \t {$meta_url[1]} \t {$title[1]} \n";
    $result = array($date, $embed_url[1], $meta_url[1], $title[1]);
    $output = 'scrape.txt';
    file_put_contents($output, print_r($result, true), FILE_APPEND);
    }
}
get_content_movies($linkMovies, $argv);

从命令行向脚本传递参数

Passing parameters from command line to script

php

screen-scraping

simple-html-dom

web-scraping