Programs which reads the HTML file, chunks by tags, write them to file and create JSON file which contains chapter heading.

parseHTML.php

<?php

class parseHTML
{
    //counter appended to chunked file names
    protected $counter = 0;
    //Store book information such as book name, chapter names, version
    protected $bookInfo;
    //Holds filename with no extension
    protected $fileName;
    //Holds the pointer to the opened file
    protected $fileHandle;
    protected $writingFileHandle;
    protected $matchTag;
    protected $chapterHeadTag = "/x-berschrift-1--nur-f-r-Header-/";
    protected $subChapterTag = "/x-berschrift-2/";
    protected $userDefinedToken = "/[CHUNK]/";

    public function __construct($file)
    {
       $this->file = $file; 
       $this->init();
    }

        /**
     * Initialize
     *
     * @return void
     */
    public function init()
    {
        //extract the filename without extension, create a directory with the name and move to it
        $this->extractFileName($this->file);
        $this->makeDirectory($this->fileName);
        $this->fileHandle = $this->openReadFile($this->file); 
        $this->changeDirectory($this->fileName);
        $this->readingFile($this->fileHandle);
        //checks for the matching tag
        // if found close if a file already opened then open new file and start writing to it until you find another same match tag or chuck
        $this->openJSONFile();

    }

    /**
     * Reads line by line in the opened file
     *
     * @return void
     */
    public function readingFile($fHandle)
    {
        while(!feof($fHandle))
        {
            $line = fgets($fHandle);
            $this->checkingMatchTag($line);
        }
    }

    /**
     * This function open the given file
     *
     * @return file pointer
     */

    public function openReadFile($file)
    {
        return fopen($file, 'r');
    }

    /**
     * This function extracts the filename. 
     *(filename is the name of the file without extension part)
     *
     * @return void
     */

    public function extractFileName($file)
    {
        $this->fileName = explode('.', $file)[0];
    }

    /**
     * This function gives the filename 
     * (filename is the name of the file without extension part)
     *
     * @return void
     */

    public function getFileName($file)
    {
        return $this->fileName;
    }

    public function getFile()
    {
        return $this->file;
    }

    /**
     * Checks if the given tag is present in the line if yes return True,
     * otherwise False
     *
     * @return void
     */

    public function checkingMatchTag($line)
    {
        if(preg_match($this->chapterHeadTag, $line))
        {
            //Calling to get chapter heading
            $this->extractTitle($line);
        }
        else if(preg_match($this->subChapterTag, $line) or preg_match($this->userDefinedToken, $line))
        {
            if($this->writingFileHandle and $this->matchTag)
            {
                $this->closeFile($this->writingFileHandle);
                $this->incrementCounter();
                $this->openWriteFile();
                $this->writeLineToFile($line);
            }
            else
            {
                $this->openWriteFile($line);
                $this->matchTag = True;
                $this->writeLineToFile($line);
            }
        }
        else if($this->matchTag)
        {
                $this->writeLineToFile($line);
        }
    }

    /**
     * Creates a directory with $name if it does not exist
     *
     * @return void
     */

    public function makeDirectory($name)
    {
        if(!is_dir($name))
        {
            mkdir($name); 
        }
    }


    public function extractTitle($line)
    {
          $this->bookInfo['chapter'][] = strip_tags($line); 
    }

    /**
     * Changes the current working directry to $name 
     *
     * @return void
     */

    public function changeDirectory($name)
    {
        chdir($name);
    }

    /**
     * Initialize
     *
     * @return void
     */

    public function openJSONFile()
    {
       $handleJSON = fopen('config.json', 'w');
       fwrite($handleJSON, json_encode($this->bookInfo));
       $this->closeFile($handleJSON); 
    }

    public function openWriteFile()
    {
        $this->writingFileHandle = fopen($this->fileName.'000'.$this->counter.'.'.'html','w');
    }

    /**
     * Initialize
     *
     * @return void
     */

    public function setMatchTag($tag)
    {
        $this->tag = $tag;
    }

    /**
     * This function returns match tag
     *
     * @return string
     */

    public function getMatchTag()
    {
        return $this->tag;
    }

    /**
     * Write line to the opened file
     *
     * @return void
     */

    public function writeLineToFile($line)
    {
        fwrite($this->writingFileHandle, $line);
    }
   
    public function setUserDefineToken($token)
    {
        $this->userDefinedToken = $token;
    }

    public function getUserDefineToken()
    {
        return $this->userDefinedToken;
    }
 
    /**
     * Increment the counter
     *
     * @return void
     */

    public function incrementCounter()
    {
            $this->counter++;
    }

    /**
     * This function returns counter
     *
     * @return int
     */

    public function getCounter()
    {
        return $this->counter;
    }

    /**
     * Close the file
     *
     * @return void
     */

    public function closeFile($handle)
    {
       fclose($handle); 
    }
}

new parseHTML('testing1.html');