ACA20201112

<?php

/*
include => warning
include "fich";
include_once "caminho/fich";

require => error
require "fich/sdsd/sdsD/f";
*/
require_once "AmUtil.php";

//https://codeshare.luismeneses.pt/
//https://curl.haxx.se/docs/sslcerts.html
//https://curl.se/docs/caextract.html

//edit php.ini and add
//curl.cainfo="C:/<path to my php installation folder>/cacert.pem"

define ("TEST_URL", "https://apod.nasa.gov/apod/ap141231.html");
// ... "<IMG SRC="image/2011/M78... "
//https://apod.nasa.gov/apod/image/2011/M78_LDN1622_BarnardsLoop_SEP27_28_Oct15_final1024.jpg

class ApodBot{
    //consts?
    const APOD_URL = "https://apod.nasa.gov/apod/";
    const DESIRED_NUMBER_OF_DIGITS = 2;
    //const BOT_SIGNATURE = "For educational tests only";
    /*
     * the structure of an APOD URL:
     * https://apod.nasa.gov/apod/apYYMMDD.html
     * e.g.: https://apod.nasa.gov/apod/ap141231.html
     */

    private
        $mCurrentYear,
        $mCurrentMonth,
        $mCurrentDay;

    public function __construct(){
        /*
         * Y - format for year with 4 digits
         * m - format for month with 2 digits
         * d - format for day with 2 digits
         */
        $strYMD = date("Y-m-d"); //"2020-11-05"

        $aDateParts = explode("-", $strYMD);
        /*
         * $aDateParts = [
         * 0 => "2020", 1 => "11", 2 => "05"
         * ];
         */

        $this->mCurrentYear =
            intval($aDateParts[0]);

        $this->mCurrentMonth =
            intval($aDateParts[1]);

        $this->mCurrentDay =
            intval($aDateParts[2]);
    }//__construct

    //data members?

    //methods?
    //https://apod.nasa.gov/apod/ap141231.html

    /*
     * receives 3 ints: year, month, day
     * returns a string in the format
     * https://apod.nasa.gov/apod/apYYMMDD.html
     */
    public function urlForDay(
        int $pYear=0, //2020
        int $pMonth=0, //12->"12" 5->"05"
        int $pDay=0 //31->"31" 1->"01"
    ){
        $strUrlForDay = "";
        $strYear=$strMonth=$strDay="";

        //pattern for default values for parameters
        $pYear = empty($pYear) ?
            $this->mCurrentYear
            :
            $pYear;

        $pMonth =
            empty($pMonth) ?
            $this->mCurrentMonth
            :
            $pMonth;

        $pDay =
            empty($pDay) ?
            $this->mCurrentDay
            :
            $pDay;
        /*
        293029 (6 excede 2 = 6-2=4)
        9999 (4 excede 2 em 4-2=2)
        999 (3 excede 2 em 3-2=1)
        */

        $strYear = $pYear . "";
        if (
            $iSizeOfYear=strlen($strYear)
            >
            self::DESIRED_NUMBER_OF_DIGITS
        ){
            $iExcessDigits =
                $iSizeOfYear
                -
                self::DESIRED_NUMBER_OF_DIGITS;
            $strYear = substr(
                $strYear,
                $iExcessDigits-1, //start position
                self::DESIRED_NUMBER_OF_DIGITS //2 symbols
            );
        }//if there is need to fix the string for year

        $strMonth = $pMonth<10 ? "0".$pMonth : $pMonth."";

        $strDay = $pDay<10 ? "0".$pDay : $pDay."";

        /*
         * sprintf is "print into a string following a format"
         * https://apod.nasa.gov/apod/apYYMMDD.html
         */
        $strUrlForDay = sprintf(
            "%sap%s%s%s.html",
            self::APOD_URL, //"https://apod.nasa.gov/apod/"
            $strYear,
            $strMonth,
            $strDay
        );

        return $strUrlForDay;
    }//urlForDay

    const IMAGE_MARK = "<img src=\"";
    public function identifyImgInSourceCode(
        $pSrcCode
    ){
        $iWhereDoesImgElementStart =
            stripos(
                $pSrcCode,
                self::IMAGE_MARK
            );

        //it exists!
        if ($iWhereDoesImgElementStart!==false){
            $strContainsTheImgAddress =
                substr(
                    $pSrcCode,
                    $iWhereDoesImgElementStart
                    +
                    strlen(self::IMAGE_MARK)
                );

            $strImgUrl =
                substr(
                    $strContainsTheImgAddress,
                    0,
                    strpos(
                        $strContainsTheImgAddress,
                        "\"" //the closing double-quote
                    )
                );

            return self::APOD_URL.$strImgUrl;
        }
    }//identifyImgInSourceCode

    /*
     * receives the URL of some "image of the day"
     * e.g. https://apod.nasa.gov/apod/image/2011/C2020M3Orion_CharlesBracken1024.jpg
     * returns a valid file name
     * e.g. "C2020M3Orion_CharlesBracken1024.jpg"
     */
    public function extractFileNameForDownload(
        string $pUrl
    ){
        /*
         * trim(" a b c ") --> "a b c"
         * strlen("abc") ---> 3
         */
        $bCheck = trim(strlen($pUrl))>0;

        /*
         * returns the leftmost ocurrence of the 2nd arg on the 1st
         * strpos("ABCDEFBC", "BC") --> 1
         * rightmost sensitive
         * strrpos ("ABCDEFBC", "BC") --> 6
         * strrpos ("ABCDEFBC", "bc") --> false
         * leftmost, insensitive
         * stripos ("ABCDEFBC", "bc") --> 1
         * rightmost, insensitive
         * strripos ("ABCB", "b") --> 3
         */
        if ($bCheck){
            $iWhereDoesTheLastFwSlashBeginOrFalse =
                strripos(
                    $pUrl,
                    "/"
                );

            //if the forward slash occurs in the URL
            if ($iWhereDoesTheLastFwSlashBeginOrFalse!==false){
                $strFileName =
                    substr(
                        $pUrl,
                        $iWhereDoesTheLastFwSlashBeginOrFalse+1
                    );

                return $strFileName;
            }//if
        }//if
        return false;
    }//extractFileNameForDownload

    public function downloadImgForDay(
        $pY=0,
        $pM=0,
        $pD=0
    ){
        $bDownloadTodaysImg = empty($pY) && empty($pM) && empty($pD);

        //e.g. https://apod.nasa.gov/apod/ap201110.html
        $strUrlForTheHtmlPageThatPublishedTheImg = "";
        if ($bDownloadTodaysImg){
            $strUrlForTheHtmlPageThatPublishedTheImg =
                $this->urlForDay();
        }//if
        else{
            $strUrlForTheHtmlPageThatPublishedTheImg =
                $this->urlForDay($pY, $pM, $pD);
        }//else

        //source code of the html page
        $strHtmlSourceCode = AmUtil::consumeUrl($strUrlForTheHtmlPageThatPublishedTheImg);

        //this is the image direct URL
        $strUrlForTheImg = $this->identifyImgInSourceCode(
            $strHtmlSourceCode
        );

        //string/bytes array which is the published image
        //this is the download
        $bytesForTheImg = AmUtil::consumeUrl(
            $strUrlForTheImg
        );

        $strOriginalFilename =
            $this->extractFileNameForDownload($strUrlForTheImg);

        $iBytesWrittenOrFalse =
            file_put_contents(
                //"saved.jpg",
                $strOriginalFilename,
                $bytesForTheImg
            );

        //return $iBytesWrittenOrFalse;
        return [
            self::KEY_SIZE =>  $iBytesWrittenOrFalse,
            self::KEY_FILE_NAME => $strOriginalFilename
        ];
    }//downloadImgForDay
    const KEY_SIZE = "KEY_SIZE";
    const KEY_FILE_NAME = "KEY_FILE_NAME";

    public function downloadAllImagesForMonth(
        $pY,
        $pM,
        $pStartDay = 1,
        $pbFeedback = true
    ){
        for (
            $iCurrentDay = $pStartDay;
            $iCurrentDay<=AmUtil::numberOfDaysInMonth($pY, $pM);
            $iCurrentDay++
        ){
            $oRet = $this->downloadImgForDay($pY, $pM, $iCurrentDay);
            $iImageSizeInBytes = $oRet[self::KEY_SIZE];
            $strFileName = $oRet[self::KEY_FILE_NAME];

            if ($pbFeedback){
                $strMsg = sprintf(
                    "Current date=%d-%d-%d\nSave %d bytes in file: %s".PHP_EOL,
                    $pY, $pM, $iCurrentDay,
                    $iImageSizeInBytes,
                    $strFileName
                );
                echo $strMsg;
            }//if feedback

        }
    }//downloadAllImagesForMonth

    //**
    //June 16 1995
    public function ripThemAll(){
        $this->downloadAllImagesForMonth
        (1996, 1, 16);

        for(
            $iYear=1997;
            $iYear<=2019;
            $iYear++
        ){
            for ($iMonth=1; $iMonth<=12; $iMonth++)
                $this->downloadAllImagesForMonth($iYear, $iMonth);
        }//for

        //TODO: current year
    }//ripThemAll
}//ApodBot

$bot = new ApodBot(); //constructor

/*
//$bot->getImageOfTheDay(); //image of the day (today)
$strUrl = $bot->urlForDay();
echo $strUrl.PHP_EOL;

$strUrl = $bot->urlForDay(2019, 12, 25);
echo $strUrl.PHP_EOL;

//$sourceCode = ApodBot::consumeUrl(TEST_URL);
$sourceCode = AmUtil::consumeUrl($bot->urlForDay());
echo $sourceCode;

$urlForTodaysImg = $bot->identifyImgInSourceCode(
    $sourceCode
);

echo $urlForTodaysImg.PHP_EOL;

/*
$bot->getImageOfTheDay(2019, 12, 25);//image on that date
$bot->getEntireCollection();
$bot->getAllImagemFromYear(2000);
$bot->getAllImagemFromMonth(2000, 4);
*/
//echo $bot->downloadImgForDay(2015, 12, 23);

//$bot->downloadAllImagesForMonth(1999, 1);
//single threaded

//$bot->ripThemAll();

while(1){
    /*
    $pedido = obterPedido();
    reagirPedido();
    */
    $bot->downloadImgForDay();
    echo "Will continue in 24 hours time".PHP_EOL;
    sleep(60*60*24); //1 day pause
}//while


**

<?php

class AmUtil{
    const IMPOSSIBLE_MONTH = -1;
    const BOT_SIGNATURE = "For educational tests only";

    public static function leapYear(
        $pY
    ){
        return ($pY%400 === 0) || ($pY%4===0 && ($pY%100!==0));
    }//leapYear

    public static function numberOfDaysInMonth(
        $pY,
        $pM
    ){
        switch($pM){
            case 1: case 3:case 5:case 7:case 8: case 10;case 12: return 31;
            case 4: case 6:case 9:case 11: return 30;
            case 2: return (self::leapYear($pY) ? 29 :  28);
            default: return self::IMPOSSIBLE_MONTH;
        }//switch
    }//numberOfDaysInMonth

    public static function consumeUrl(
        $pUrl //can be an HTML page, can be a JPG, ...
    ){
        //$bValid = is_string($pUrl) && strlen($pUrl);
        $ch = curl_init($pUrl);
        if ($ch){
            //curl_setopt(CURLOPT_URL, $pUrl);
            /*
             * makes it explic that the request
             * will happen using HTTP GET
             */
            curl_setopt(
                $ch,
                CURLOPT_HTTPGET,
                true
            );

            /*
             * disables the verification of SSL
             * certificates
             * useful when not using cacert.pem
             */
            curl_setopt(
                $ch,
                CURLOPT_SSL_VERIFYPEER,
                true
            );

            /*
             * sets a user agent string for our
             * software
             */
            curl_setopt(
                $ch,
                CURLOPT_USERAGENT,
                self::BOT_SIGNATURE
            );

            //if set to true, curl_exec will return
            //the data consumed at the URL
            //instead of just true/false
            curl_setopt(
                $ch,
                CURLOPT_RETURNTRANSFER,
                true
            );

            /*
             * makes it clear that we want all the bytes
             */
            curl_setopt(
                $ch,
                CURLOPT_BINARYTRANSFER, //deprecated
                true
            );

            /*
             * sets automatic handling of the encoded
             * data
             */
            curl_setopt(
                $ch,
                CURLOPT_ENCODING,
                ""
            );

            $bin = curl_exec($ch);

            return $bin;
        }//if
        return false;
    }//consumeUrl
}//AmUtil