VerifiedJoseph/get-playstv-video-list.php

## get-playstv-video-list.php
<?php
/*
PHP script for extracting video details from an archived Plays.tv profile and checking their archive status.
*/
/* Dependencies
	PHP Simple HTML DOM Parser https://simplehtmldom.sourceforge.io/
	php-curl-class (via Composer) https://github.com/php-curl-class/php-curl-class
*/
require __DIR__ . '/simple_html_dom.php';
require __DIR__ . '/vendor/autoload.php';

$outputFile = 'video-list.csv';

/*
	Saved version of the user profile videos page
	(e.g https://web.archive.org/web/20191210184635if_/https://plays.tv/u/Daricx/videos)

	Load profile videos page in brower, scroll down to end of page and keep scrolling until the infinite scrolling stop
	and then copy the HTML from brower's developer tools Inspector (called Elements in Chrome) into the HTML file.
*/
$htmlFile = 'profile-page.html';

$html = file_get_contents($htmlFile);

$html = str_get_html($html);

$output = fopen($outputFile, 'w');

$row = array('Title', 'Date', 'Game', 'Duration', 'Page URL', 'Video URL');
fputcsv($output, $row, ',');

$div = $html->find('div#B', 0);
foreach ($div->find('li.video-item') as $index => $item) {
	$title = $item->find('a.title', 0)->plaintext;
	$game = '';

	if ($item->find('a.hashtag.no-wrap', 0)) {
		$game = $item->find('a.hashtag.no-wrap', 0)->plaintext;
	}

	$duration = $item->find('span.duration.no-wrap', 0)->plaintext;
	$date = $item->find('span.created', 0)->plaintext;

	//$views = $item->find('span.view-count', 0)->plaintext;
	//$likes = $item->find('span.like-count', 0)->plaintext;

	$url = explode('?', $item->find('a.title', 0)->href);

	$PageUrl = 'https://web.archive.org' .  $url[0];

	echo $index . ' - ' . $title . "\n";

	$curl = new Curl\Curl();
	$curl->setOpt(CURLOPT_FOLLOWLOCATION, true);
	$curl->get($PageUrl);

	echo $PageUrl . ' ('. $curl->getHttpStatusCode() .')'  . "\n";;

	if ($curl->error || $curl->getHttpStatusCode() != 200) {
		$PageUrl = 'Not archived';
		$videoURL = 'Not archived';

	} else {
		$html = str_get_html($curl->response);
		$video = $html->find('video', 0);

		foreach ($video->find('source') as $source) {

			if ($source->res == '480') {
				$videoURL = $source->src;
			}

			if ($source->res == '720') {
				$videoURL = $source->src;
				break;
			}
		}
	}

	echo $videoURL;
	echo "\n \n";

	$row = array(
		$title,
		$date,
		$game,
		$duration,
		//$views,
		//$likes,
		$PageUrl,
		$videoURL,
	);

	fputcsv($output, $row, ',');
}

fclose($output);

## profile-page.html
<html>
</html>
	<?php
	/*
	PHP script for extracting video details from an archived Plays.tv profile and checking their archive status.
	*/
	/* Dependencies
	PHP Simple HTML DOM Parser https://simplehtmldom.sourceforge.io/
	php-curl-class (via Composer) https://github.com/php-curl-class/php-curl-class
	*/
	require __DIR__ . '/simple_html_dom.php';
	require __DIR__ . '/vendor/autoload.php';

	$outputFile = 'video-list.csv';

	/*
	Saved version of the user profile videos page
	(e.g https://web.archive.org/web/20191210184635if_/https://plays.tv/u/Daricx/videos)

	Load profile videos page in brower, scroll down to end of page and keep scrolling until the infinite scrolling stop
	and then copy the HTML from brower's developer tools Inspector (called Elements in Chrome) into the HTML file.
	*/
	$htmlFile = 'profile-page.html';

	$html = file_get_contents($htmlFile);

	$html = str_get_html($html);

	$output = fopen($outputFile, 'w');

	$row = array('Title', 'Date', 'Game', 'Duration', 'Page URL', 'Video URL');
	fputcsv($output, $row, ',');

	$div = $html->find('div#B', 0);
	foreach ($div->find('li.video-item') as $index => $item) {
	$title = $item->find('a.title', 0)->plaintext;
	$game = '';

	if ($item->find('a.hashtag.no-wrap', 0)) {
	$game = $item->find('a.hashtag.no-wrap', 0)->plaintext;
	}

	$duration = $item->find('span.duration.no-wrap', 0)->plaintext;
	$date = $item->find('span.created', 0)->plaintext;

	//$views = $item->find('span.view-count', 0)->plaintext;
	//$likes = $item->find('span.like-count', 0)->plaintext;

	$url = explode('?', $item->find('a.title', 0)->href);

	$PageUrl = 'https://web.archive.org' . $url[0];

	echo $index . ' - ' . $title . "\n";

	$curl = new Curl\Curl();
	$curl->setOpt(CURLOPT_FOLLOWLOCATION, true);
	$curl->get($PageUrl);

	echo $PageUrl . ' ('. $curl->getHttpStatusCode() .')' . "\n";;

	if ($curl->error \|\| $curl->getHttpStatusCode() != 200) {
	$PageUrl = 'Not archived';
	$videoURL = 'Not archived';

	} else {
	$html = str_get_html($curl->response);
	$video = $html->find('video', 0);

	foreach ($video->find('source') as $source) {

	if ($source->res == '480') {
	$videoURL = $source->src;
	}

	if ($source->res == '720') {
	$videoURL = $source->src;
	break;
	}
	}
	}

	echo $videoURL;
	echo "\n \n";

	$row = array(
	$title,
	$date,
	$game,
	$duration,
	//$views,
	//$likes,
	$PageUrl,
	$videoURL,
	);

	fputcsv($output, $row, ',');
	}

	fclose($output);