package Torello.Browser;


// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// UNIX Terminal Shell Colors (Text Colors)
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

import static Torello.Java.C.BPURPLE_BKGND;
import static Torello.Java.C.BRED;
import static Torello.Java.C.BCYAN;
import static Torello.Java.C.BYELLOW_BKGND;
import static Torello.Java.C.RESET;


// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// Browser-API, JavaScript-API Commands
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

import Torello.Browser.JavaScriptAPI.RunTime;

import Torello.Browser.BrowserAPI.DOM;
import Torello.Browser.BrowserAPI.Target;
import Torello.Browser.BrowserAPI.Page;


// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// Misc Torello.Java
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

import Torello.Java.StrIndent;
import Torello.Java.StringParse;
import Torello.Java.EXCC;
import Torello.Java.Verbosity;

import Torello.Java.Additional.Ret2;

import Torello.HTML.Tools.Images.Request;
import Torello.HTML.Tools.Images.Results;
import Torello.HTML.Tools.Images.ImageScraper;


// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// Parsing the Output of this program
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

import Torello.HTML.HTMLPage;
import Torello.HTML.HTMLNode;
import Torello.HTML.Attributes;
import Torello.HTML.TC;

import Torello.HTML.NodeSearch.TagNodeFind;


// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
// Standard Java Libraries
// *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

import java.util.function.Consumer;

import java.io.IOException;
import java.util.function.Predicate;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import java.util.Arrays;
import java.util.List;
import java.util.Vector;

import javax.json.JsonString;

/**
 * An example of this package's utility.
 * <EMBED CLASS='external-html' DATA-FILE-ID=EXAMPLE>
 */
public class Example01
{
    private Example01() { }

    /** The URL that is being scraped in this example */
    protected static final String samAltmanURL = "https://en.wikipedia.org/wiki/Sam_Altman";

    protected static final ConnRecord connRec = new ConnRecord();

    static 
    {
        connRec.setEventHandler(Printing::printObj);
        connRec.setBrowserErrorHandler(Printing::printObj);
        connRec.setRDPErrorHandler(Printing::printObj);
        connRec.setRawTextReceiver(System.out);
        connRec.setAppTextReceiver(System.out);
        connRec.setErrTextReceiver(System.out);
    }


    // ********************************************************************************************
    // ********************************************************************************************
    // MAIN METHOD
    // ********************************************************************************************
    // ********************************************************************************************


    /** This class is intended to be invoked from the Command Line. */
    public static void main(String[] argv) throws Exception
    {
        // Opening a WebSocket Browser-Connection to the currently running Chrome-Instance
        final WebSocketSender bws = STEP_01_openBrowserWebSocket();

        // Close any currently opened pages / tabs inside the browser
        STEP_02_closeAllPages(bws);

        // Open a Browser-Page (using 'bws') for reading Sam Altman's Wikipedia Profile
        final String targetID = STEP_03_openSamAltmanPage(bws);

        // Create / Build a WebSocket-Connection object to the newly opened Sam Altman Page.
        final WebSocketSender pws = STEP_04_getPageWebSocket(targetID);

        // Execute some Java-Script so that the scrape code may run
        final String html = STEP_05_runJavaScript(pws);

        // Print the Image-URL's, retrieve those URL's too
        final String[] imgURLs = STEP_06_extractImageURLs(html);

        // Download the Images into a download folder
        STEP_07_downloadImages(imgURLs);

        bws.disconnect();
        pws.disconnect();
    }


    // ********************************************************************************************
    // ********************************************************************************************
    // The Steps
    // ********************************************************************************************
    // ********************************************************************************************


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-01: Opening a WebSocket Browser Connection
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /** <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP01> */
    protected static WebSocketSender STEP_01_openBrowserWebSocket() throws Exception
    {
        Printing.notice("Opening a WebSocket Browser Connection...");

        final BrowserConn browserConn = BrowserConn.getBrowserConn(9222, false);

        System.out.println(
            '\n' + BCYAN + "Example01.java: " + RESET +
            BRED + "Opened Browser Connection:\n" + RESET + browserConn.toString()
        );

        final WebSocketSender bws = browserConn.createSender(Example01.connRec);

        // Chat-GPT once suggested this line. I just haven't removed it.  It's not hurting anyone!
        Thread.sleep(1000);

        return bws;
    }


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-02: Close all Opened Browser Tabs
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /** <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP02> */
    protected static void STEP_02_closeAllPages(WebSocketSender bws) throws Exception
    {
        Printing.notice("Closing All Currently Open Pages, using BrowserConn");


        // This is currently unused.  I used to filter for only the opened Wiki-Pages, but now this
        // method simply closes every open page.  No sense in deleting this line, though

        final Predicate<Target.TargetInfo> isSamAltman = (Target.TargetInfo t) ->
                t.type.equals("page")
            &&  (t.url != null)
            &&  (t.url.startsWith(samAltmanURL));

        System.out.println
            ('\n' + BCYAN + "Example01.java: " + RESET + "Getting all tabs...");
    
        final Target.TargetInfo[] allTabs = Target
            .getTargets(null /* FilterEntry[] */)
            .exec(bws)
            .await();

        System.out.println
            ('\n' + BCYAN + "Example01.java: " + RESET + "Found " + allTabs.length + " tabs.");

        if (allTabs.length > 0)

            for (int i = 0; i < allTabs.length; i++)
            {
                final String tid = allTabs[i].targetId;
                System.out.println(BRED + "Closing Tab: " + RESET + tid);
                Target.closeTarget(tid).exec(bws).await();
            }
    }


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-03: Open a Web-Browser Page / Tab that is reading the Wiki for Open-AI's Sam Altman
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /** <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP03> */
    protected static String STEP_03_openSamAltmanPage(final WebSocketSender bws) throws Exception
    {
        Printing.notice("Opening a Sam Altman Wikipedia Page, using BrowserConn.");

        final String targetID = Target
            .createTarget()
            .accept("url", samAltmanURL)
            .build()
            .exec(bws)
            .await();

        final Target.TargetInfo targetInfo = Target
            .getTargetInfo(targetID)
            .exec(bws)
            .await();

        System.out.println(
            '\n' + BCYAN + "Example01.java: " + RESET +
            BRED + "Created New Tab:\n" + RESET + targetInfo.toString()
        );


        // I leave these one second delays here.  AGAIN - Chat-GPT suggested them to me once.
        // Chat-GPT, in every sense of the word, knows more about my code than I do!  (The CDP 
        // Protocol is a very well understood protocol - just not in Java so much)

        Thread.sleep(1000);

        return targetID;
    }


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-04: Create a "PageConn" Object to the recently opened Sam Altman Wikipedia Page
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /** <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP04> */
    protected static WebSocketSender STEP_04_getPageWebSocket(final String targetID)
        throws Exception
    {
        Printing.notice("Create PageConn Web-Socket Connection to Altman's Wiki");

        // Attach to that Sam Altman Page (switch to tab-level WebSocket)
        final PageConn pageConn = PageConn
            .getAllPageConn(9222, false)
            .filter((PageConn pc) -> pc.id.equals(targetID))
            .findFirst()
            .orElseThrow(() -> new RuntimeException("The Page-Connection was Not found !!!"));

        System.out.println(
            '\n' + BCYAN + "Example01.java: " + RESET +
            BRED + "Found Page Connection to Sam Altman Wiki:\n" + RESET + pageConn.toString()
        );

        final WebSocketSender pws = pageConn.createSender(Example01.connRec);


        // I think this is the last one...  Wait 1 second, it might make a difference while the 
        // page actually loads, and the Web-Socket connects... I have no idea!  It's just 1 second!

        Thread.sleep(1000);

        return pws;
    }


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-05: Execute some Java-Script
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /** <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP05> */
    protected static String STEP_05_runJavaScript(final WebSocketSender pws) throws Exception
    {
        Printing.notice("Execute the needed Java Script, so the Scraper can Run");

        // Enable the Page domain
        System.out.println('\n' + BCYAN + "Example01.java: " + RESET + "Page.enable()");
        Page.enable(null /* Boolean */).exec(pws).await();

        // Enable the DOM domain
        System.out.println('\n' + BCYAN + "Example01.java: " + RESET + "DOM.enable()");
        DOM.enable(null /* String */).exec(pws).await();

        // Enable the Runtime domain
        System.out.println('\n' + BCYAN + "Example01.java: " + RESET + "RunTime.enable()");
        RunTime.enable().exec(pws).await();

        // This is the actual last one.  Make sure that the DOM & RunTime modules are running!
        Thread.sleep(1000);

        // 5. Evaluate the HTML via JavaScript
        System.out.println('\n' + BCYAN + "Example01.java: " + RESET + "RunTime.evaluate()");

        final RunTime.evaluate$$RET r = RunTime
            .evaluate()
            .accept("expression", "document.documentElement.outerHTML")
            .accept("returnByValue", true)
            .build()
            .exec(pws)
            .await();

        System.out.println(
            '\n' + BCYAN + "Example01.java: " + RESET + "Response RemoteObject:" + '\n' +
            r.result.toString()
        );

        final String html = ((JsonString) r.result.value).getString();

        return html;
    }


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-06: Print the Image-URL's
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP06>
     * @see HTMLPage#getPageTokens(CharSequence, boolean)
     * @see TagNodeFind
     * @see Attributes#retrieve(Vector, int[], String)
     */
    protected static String[] STEP_06_extractImageURLs(final String html) throws Exception
    {
        Printing.notice("Parsing HTML for Images Printing the URL's");

        final Vector<HTMLNode>      altPage = HTMLPage.getPageTokens(html, false);
        final int[]                 images  = TagNodeFind.all(altPage, TC.OpeningTags, "img");
        final String[]              imgURLs = Attributes.retrieve(altPage, images, "src");
        final int                   numImg  = imgURLs.length;

        System.out.println
            ('\n' + BCYAN + "Example01.java: " + RESET + "Number of Images Found: " + numImg);

        for (int i = 0; i < numImg; i++) System.out.println("    " + imgURLs[i]);

        return imgURLs;
    }


    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***
    // STEP-07: Download the Image's into a folder
    // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=EX01_STEP07>
     * @see ImageScraper#download(Request, Appendable)
     * @see Request
     * @see Results
     * @see ImageScraper#shutdownTOThreads()
     */
    protected static void STEP_07_downloadImages(final String[] imageURLs) throws Exception
    {
        Printing.notice("Download the Image's into a folder");

        final Stream.Builder<String> builder = Stream.builder();

        for (int i = 0; i < imageURLs.length; i++)
            if (imageURLs[i].startsWith("//"))
                builder.accept("https:" + imageURLs[i]);

        // Build a Request-Object
        final List<String>  imgURLsList = builder.build().collect(Collectors.toList());
        final Request       req         = Request.buildFromStrIter(imgURLsList);

        // Add a few more Scraper-Configurations to the Request Object
        req.targetDirectory                     = "image-downloads/";
        req.useDefaultCounterForImageFileNames  = true;
        req.skipOnDownloadException             = true;
        req.verbosity                           = Verbosity.Normal;

        try 
            // Run the scraper, Send all Text-Output to 'System.out' (Ignore / Discard Results)
            { final Results results = ImageScraper.download(req, System.out); }

        catch (Exception e)
            { System.out.println(EXCC.toString(e)); }

        finally 
            // This needs to happen, or this entire program will hang / lock up the terminal
            { ImageScraper.shutdownTOThreads(); }
    }
}