presse/epub.php

<!DOCTYPE html>
<html>
<head>
	<meta charset="utf-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=0">
	<title>Revue de presse - Epub</title>
	<link rel="icon" type="image/png" href="1F4F0_color.png" /></head>
<body>

<div>
	Quick link: <a href="epub.php?mp">All Mediapart home page with renewed authent</a>
</div>

<?php

	require 'settings.php';
	require 'TPEpubCreator.php';

	function get_clean_html($node)
	{
		// todo check words with "-" (like "sous-traitance")
		$innerHTM = '';
		foreach ($node->childNodes as $childNode){
			$nodeHTML = $childNode->ownerDocument->saveHTML($childNode);

			$nodeHTML = str_replace('<aside', '<b><i', $nodeHTML);
			$nodeHTML = str_replace('</aside', '</i></b', $nodeHTML);

			$nodeHTML = str_replace('<blockquote', '<b><i', $nodeHTML);
			$nodeHTML = str_replace('</blockquote', '</i></b', $nodeHTML);

			$innerHTML .= $nodeHTML;
		}
		return '<div>' . strip_tags($innerHTML, '<p><b><h2><i><strong>') . '</div>';
	}

	function add_mp_article($url, $context, $epub)
	{
		if (isset($_POST['mptoday']) && $_POST['mptoday'] && !str_contains($url, (new DateTime('today'))->format('dmy')))
		{
			return;
		}
		// todo filter on "A la une" ? in rss item dc:subject contains "A la Une"

		$article = file_get_contents($url, false, $context);
		$doc = new DOMDocument();
		$doc->loadHTML($article);
		$finder = new DomXPath($doc);

		$title = $finder->query('//h1')->item(0)->textContent;
		$author = $finder->query('//a[contains(@href, "biographie")]')->item(0)->textContent;
		$date = trim($finder->query('//time')->item(1)->textContent);
		$summary = $finder->query('//p[contains(@class, "news__heading__top__intro")]')->item(0)->textContent;
		$category = trim($finder->query('//p[contains(@class,"news__heading__top__kicker")]')->item(0)->textContent);

		// strip images
		$toremove = $finder->query('//svg');
		foreach ($toremove as $elt)
		{
			$elt->parentNode->removeChild($elt);
		}
		$toremove = $finder->query('//figure');
		foreach ($toremove as $elt)
		{
			$elt->parentNode->removeChild($elt);
		}
		$toremove = $finder->query('//span[@class="screen-reader-only"]');
		foreach ($toremove as $elt)
		{
			$elt->parentNode->removeChild($elt);
		}

		$result = '<h1>' . $title . '</h1>';
		$result .= '<p><em>' . $category . '</em></p>';
		$result .= '<p>' . $author . '</p>';
		$result .= '<p>' . $date . '</p>';
		$result .= '<p><b>' . $summary . '</b></p>';

		$nodes = $finder->query('//div[contains(@class, "paywall-restricted-content")]');
		if (!$nodes->length)
		{
			// articles accès libre
			$nodes = $finder->query('//div[contains(@class, "news__body__center__article")]');
		}

		if (!$nodes->length)
		{
			echo 'warning: could not get content of "' . $title . '"<br>';
		}
		else
		{
			$node = $nodes->item(0);
			$nodehtml = get_clean_html($node);
			$result .= $nodehtml;

			// add boite noire
			$nodes = $finder->query('//aside[contains(@class, "_black")]');
			if ($nodes->length)
			{
				$node = $nodes->item(0);
				$nodehtml = get_clean_html($node);
				$result .= '<div>' . $nodehtml . '</div>';
			}
			$epub->AddPage($result, false, $title);
		}
	}

	function get_mp_cookie()
	{
		global $mp_user;
		global $mp_password;

		$url = 'https://www.mediapart.fr/login_check';
		$postfields = 'email=' . $mp_user . '&password=' . $mp_password . '&submitButton=&_target_path=https%3A%2F%2Fwww.mediapart.fr%2F';

		$ch = curl_init($url);
		curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
		curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
		curl_setopt($ch, CURLOPT_AUTOREFERER, false);

		curl_setopt($ch, CURLOPT_HEADER, 1);
		curl_setopt($ch, CURLOPT_POST, 1);
		curl_setopt($ch, CURLOPT_POSTFIELDS, $postfields);

		$result = curl_exec($ch);
		$sessid = '';

		preg_match_all('/^Set-Cookie:\s*([^;]*)/mi', $result, $matches);
		foreach($matches[1] as $item)
		{
			if (str_starts_with($item, 'MPSESSID='))
			{
				$sessid = str_replace('MPSESSID=', '', $item);
			}
		}
		return $sessid;
	}

	function write_epub($epub)
	{
		if (file_exists($epub->epub_file))
		{
			unlink($epub->epub_file);
		}

		if (!$epub->error)
		{
			$epub->CreateEPUB();

			if (!$epub->error)
			{
				echo 'Success: <a href="' . $epub->epub_file . '">' . $epub->epub_file . '</a> created.<br>';
			}
			else
			{
				echo $epub->error;
			}

		}
		else
		{
			echo $epub->error;
		}
	}

	function lm_download_image($base_url, $url_part, $id)
	{
		$image_url = preg_replace('/GetPublicationContentItems-.*\.json/', $url_part . $id . '.jpg', $base_url);
		$temp_img_path = './temp/' . $id . '.jpg';
		$temp_content = file_get_contents($image_url);
		file_put_contents($temp_img_path, $temp_content);
		return $temp_img_path;
	}

	function get_json($url)
	{
		// cache json in case url expires
		$tempjsonpath = 'temp/' . hash('md5', $url) . '.json';
		$json = '';
		if (file_exists($tempjsonpath))
		{
			$json = file_get_contents($tempjsonpath);
		}
		else
		{
			$json = file_get_contents($url);
			file_put_contents($tempjsonpath, $json);
		}
		return json_decode($json);
	}

	// quick scenario
	if (isset($_GET['mp']))
	{
		$_POST['forcempcookies'] = 1;
		$_POST['mphome'] = 1;
	}

	date_default_timezone_set('Europe/Paris');
	$today = (new DateTime('today'))->format('Ymd');

	if (isset($_POST['emptycache']) && $_POST['emptycache'])
	{
		$files = glob('temp/*');
		foreach($files as $file)
		{
			if(is_file($file))
			{
				unlink($file);
			}
		}
	}

	// Cafeyn
	if (isset($_POST['cafeyn']) && $_POST['cafeyn'])
	{
		$url = $_POST['cafeyn'];

		// extract url from curl command
		if (str_starts_with($url, 'curl '))
		{
			$url = explode("'", $url)[1];
			echo '<p>extracted url from curl command:</p><p>' . $url . '</p>';
		}

		// cache json in case url expires
		$publication = get_json($url);
		$pubname = $publication->metadata->title;

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/' . $pubname . 'cafeyn.epub';
		$epub->title = $pubname . ' Cafeyn - ' . $today ;

		$list = (array)$publication->articles;
		$page = 1;
		foreach ($list as $entry)
		{
			$articleurl = str_replace('material', 'article/' . $entry->hash . '.json', $url);
			$article = get_json($articleurl);

			$content = '<h1>' . $article->title . '</h1>';
			//$content .= '<b>' . $article->abstract . '</b>';
			$content .= '<div>Page ' . $article->page . '</div>';

			if (count($article->rubrics))
			{
				$content .= '<div>Rubriques: ' . implode(',', $article->rubrics) . '</div>';
			}
			if (count($article->authors))
			{
				$content .= '<div>Auteurs: ' . implode(',', $article->authors) . '</div>';
			}

			foreach ($article->content->sections as $section)
			{
				$dropcap = '';
				foreach ($section->items as $item)
				{
					if ($item->type == 'text')
					{
						if ($item->class == 'quote')
						{
							$content .= '<blockquote>' .$item->content . '</blockquote>';
						}
						else if ($item->class == 'paragraphTitle')
						{
							$content .= '<h2>' .$item->content . '</h2>';
						}
						else if ($item->class == 'introduction')
						{
							$content .= '<p><b>' .$item->content . '</b></p>';
						}
						else if ($item->class == 'dropcap')
						{
							$dropcap = $item->content;
						}
						else
						{
							if ($dropcap)
							{
								$item->content = '<b>' . $dropcap . '</b>' . $item->content;
								$dropcap = '';
							}
							$content .= '<p>' . $item->content . '</p>';
						}
					}
				}
			}

			while ($article->page >= $page)
			{
				$path = $publication->pages[$page - 1]->tn;
				$path = str_replace('material', $path, $url);
				$path = str_replace('api.', 'content.', $path);
				if ($page == 1)
				{
					// cover
					$epub->AddImage($path, 'image/jpeg', true);
				}
				else
				{
					$epub->AddPage('<img style="width: 100%" src="' . $path . '">', false, 'Page ' . $page, true);
				}
				$page++;
			}
			$epub->AddPage($content, false, $article->title);

		}
		write_epub($epub);
	}

	// Le Monde
	if (isset($_POST['lemonde']) && $_POST['lemonde'])
	{
		$url = $_POST['lemonde'];

		// extract url from curl command
		if (str_starts_with($url, 'curl '))
		{
			$url = explode("'", $url)[1];
			echo '<p>extracted url from curl command:</p><p>' . $url . '</p>';
		}

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/lemonde.epub';
		$epub->title = 'Le Monde ' . $today;

		$publication = get_json($url);
		$content = array_filter($publication->Content, function($item) { return $item->Category == 'Le Monde'; });
		usort($content, function ($a, $b) { return $a->PageNumber - $b->PageNumber; });

		$pageindex = get_json(str_replace('GetPublicationContentItems', 'GetPublicationPages', $url));

		$page = 0;
		foreach ($content as $article)
		{
			if ($article->PageNumber > $page)
			{
				$page = $article->PageNumber;
				$pageobj = array_values(array_filter($pageindex->Page, function($p)
				{
					global $page;
					return $page == $p->PageNumber;
				}))[0];
				$pageid = $pageobj->PublicationPageID;

				$path = lm_download_image($url, 'Preview-MEDIUM-', $pageid);

				if ($page == 1)
				{
					// cover
					$epub->AddImage($path, 'image/jpeg', true);
				}
				else
				{
					$epub->AddPage('<img style="width: 100%" src="' . $path . '">', false, 'Page ' . $page, true);
				}
			}

			$articlebody = array_filter($article->ContentItem, function($item) { return $item->ContentType == 'text/xml'; });
			$articlebody = array_values($articlebody)[0];

			if ($articlebody->Title && $articlebody->HtmlText)
			{
				$pagecontent = '<h1>'. strip_tags($articlebody->Title) . '</h1>';
				$pagecontent .= '<p>Page ' . $article->PageNumber . '</p>';

				$author = array_filter($article->ContentItem, function($item) { return $item->ContentType == 'author/xml'; });
				$author = array_values($author)[0];
				if ($author->Author)
				{
					$pagecontent .= $author->Author;
				}

				if ($articlebody->Introduction)
				{
					$pagecontent .= '<b>' . $articlebody->Introduction . '</b>';
				}
				$pagecontent .= $articlebody->HtmlText;

				$epub->AddPage($pagecontent, false, str_replace('&nbsp;', ' ', strip_tags($articlebody->Title)), true);
			}
		}
		write_epub($epub);
	}

	if (isset($_POST['forcempcookies']) && $_POST['forcempcookies'])
	{
		$old = $mp_sessionid;
		$mp_sessionid = get_mp_cookie();
		$settings = file_get_contents('settings.php');
		$settings = str_replace($old, $mp_sessionid, $settings);
		file_put_contents('settings.php', $settings);
		echo '<div>Updated mpsessid in settings.</div>';
	}

	// Mediapart RSS
	if (isset($_POST['mediapart']) && $_POST['mediapart'])
	{
		$feedurl = 'https://www.mediapart.fr/articles/feed';
		$opts = [
		'http' => [
			'method' => "GET",
			'header' => "Accept-language: en\nCookie: MPSESSID=" . $mp_sessionid,
		]
		];
		$context = stream_context_create($opts);

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/mediapart.epub';
		$epub->title = 'Mediapart - RSS ' . $today;

		// load feeds
		$feed = file_get_contents($feedurl);
		$xml = new SimpleXMLElement($feed);
		$items = $xml->xpath("/rss/channel/item");

		foreach (array_reverse($items) as $item)
		{
			add_mp_article($item->link, $context, $epub);
		}

		write_epub($epub);
	}

	// Politis RSS
	if (isset($_POST['politis']) && $_POST['politis'])
	{
		$issuenb = $_POST['politis'];
		$feedurl = 'https://www.politis.fr/flux-rss-politis-fr/';
		$opts = [
		'http' => [
			'method' => "GET",
			//'header' => "Accept-language: en\nCookie: MPSESSID=" . $mp_sessionid, // todo?
		]
		];
		$context = stream_context_create($opts);

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/politis' . $issuenb . '.epub';
		$epub->title = 'Politis ' . $issuenb . ' - RSS ' . $today;

		// find cover
		$issues = file_get_contents('https://www.politis.fr/boutique/magazines-unite/');
		$doc = new DOMDocument();
		$doc->loadHTML($issues);
		$finder = new DomXPath($doc);
		$cover = $finder->query('//img[contains(@src, "' . $issuenb . '_")]');
		if ($cover->length)
		{
			$epub->AddImage($cover->item(0)->getAttribute('src'), 'image/jpeg', true);
		}
		else
		{
			echo 'warning: no cover for issue ' . $issuenb . '<br>';
		}

		// load feeds
		$feed = file_get_contents($feedurl);
		$xml = new SimpleXMLElement($feed);
		$items = $xml->xpath("/rss/channel/item");

		foreach (array_reverse($items) as $item)
		{
			$url = $item->link;
			$article = file_get_contents($url, false, $context);

			if (!str_contains($article, ' dans l’hebdo N° ' . $issuenb))
			{
				continue;
			}

			$doc = new DOMDocument();
			$doc->loadHTML($article);
			$finder = new DomXPath($doc);

			$title = $finder->query('//h1')->item(0)->textContent;
			$author = $finder->query('//span[@class="nom"]')->item(0)->textContent;
			$date = $finder->query('//span[@class="date"]')->item(0)->textContent;
			$summary = $finder->query('//div[@class="extrait"]')->item(0)->textContent;

			// transform "zoom" divs into aside tags
			$zooms =  $finder->query('//div[contains(@class,"gt_zoom")]');
			foreach ($zooms as $zoom)
			{
				$aside = $doc->createElement('aside');
				while ($zoom->childNodes->length > 0)
				{
					$aside->appendChild($zoom->childNodes->item(0));
				}
				$zoom->parentNode->replaceChild($aside, $zoom);
			}

			$result = '<h1>' . $title . '</h1>';
			$result .= '<p>' . $author . '</p>';
			$result .= '<p>' . $date . '</p>';
			$result .= '<p><b>' . $summary . '</b></p>';

			$nodes = $finder->query('//div[@id="content"]');
			$node = $nodes->item(0);
			$nodehtml = get_clean_html($node);
			$result .= $nodehtml;
			$epub->AddPage($result, false, $title);

		}

		write_epub($epub);
	}

	// Mediapart home page
	if (isset($_POST['mphome']) && $_POST['mphome'])
	{
		$homeurl = 'https://www.mediapart.fr';
		$opts = [
		'http' => [
			'method' => "GET",
			'header' => "Accept-language: en\nCookie: MPSESSID=" . $mp_sessionid,
		]
		];
		$context = stream_context_create($opts);

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/mediaparthome.epub';
		$epub->title = 'Mediapart - A la une ' . $today;

		$home = file_get_contents($homeurl, false, $context);
		$doc = new DOMDocument();
		$doc->loadHTML($home);
		$finder = new DomXPath($doc);

		$xpath = '//a[@data-js = "teaser-link" and contains(@href, "/journal/") and not(contains(@href, "/dossier/")) and not(contains(@href, "/studio/")) and not(contains(@href, "fil-")) and (@href != "/journal/series")]/@href';

		$links = $finder->query($xpath);

		foreach ($links as $link)
		{
			add_mp_article('https://www.mediapart.fr' . $link->value, $context, $epub);
		}

		write_epub($epub);
	}

	// New York Times RSS
	if (isset($_POST['nyt']) && $_POST['nyt'])
	{
		$feedurl = 'https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml';
		$opts = [
		'http' => [
			'method' => "GET",
			'header' => "Accept-language: en\nCookie: NYT-S=" . $nyt_sessionid,
		]
		];
		$context = stream_context_create($opts);

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/newyorktimes.epub';
		$epub->title = 'The New York Times ' . $today;

		// load feeds
		$feed = file_get_contents($feedurl);
		$xml = new SimpleXMLElement($feed);
		$items = $xml->xpath("/rss/channel/item");

		foreach (array_reverse($items) as $item)
		{
			$title = $item->title;
			$author = $item->xpath('dc:creator')[0];
			$summary = $item->description;

			$article = file_get_contents($item->link, false, $context);
			$doc = new DOMDocument();
			$doc->loadHTML($article);
			$finder = new DomXPath($doc);

			$result = '<h1>' . $title . '</h1>';
			$result .= '<p>' . $author . '</p>';
			$result .= '<p>' . $item->pubDate . '</p>';
			$result .= '<p><b>' . $summary . '</b></p>';

			$nodes = $finder->query('//section[@name="articleBody"]');

			if (!$nodes->length)
			{
				echo 'warning: could not get content of "' . $title . '"<br>';
			}
			else
			{
				$node = $nodes->item(0);
				$nodehtml = get_clean_html($node);
				$result .= $nodehtml;
				$epub->AddPage($result, false, $title);
			}
		}

		write_epub($epub);
	}

	// New York Times today's paper
	if (isset($_POST['nyttoday']) && $_POST['nyttoday'])
	{
		$todaypage = file_get_contents("https://www.nytimes.com/section/todayspaper");
		$opts = [
		'http' => [
			'method' => "GET",
			'header' => "Accept-language: en\nCookie: NYT-S=" . $nyt_sessionid,
		]
		];
		$context = stream_context_create($opts);

		$epub = new TPEpubCreator();
		$epub->temp_folder = 'temp/';
		$epub->epub_file = 'epub/newyorktimestoday.epub';
		$epub->title = 'The New York Times today\'s paper ' . $today;

		// grab today's paper
		$start = strpos($todaypage, "window.__preloadedData = ") + 25;
		$end = strpos($todaypage, "};", $start) + 1;
		$json = str_replace(":undefined", ":null", substr($todaypage, $start, $end - $start));
		$data = json_decode($json);

		foreach($data->initialState as $item)
		{
			if ($item->__typename == "Article")
			{
				$headline = ($data->initialState->{ $item->headline->id });

				$title = $headline->default;
				$summary = $item->summary;

				$result = '<h1>' . $title . '</h1>';

				// authors
				$result .= '<p>';
				$creators = ($data->initialState->{ $item->bylines[0]->id })->creators;
				foreach ($creators as $creator)
				{
					$author = $data->initialState->{ $creator->id };
					$result .= $author->displayName . '&nbsp;';
				}
				$result .= '</p>';

				$result .= '<p>' . $item->lastMajorModification . '</p>';
				$result .= '<p><b>' . $summary . '</b></p>';

				$article = file_get_contents($item->url, false, $context);
				$doc = new DOMDocument();
				$doc->loadHTML($article);
				$finder = new DomXPath($doc);
				$nodes = $finder->query('//section[@name="articleBody"]');

				if (!$nodes->length)
				{
					echo 'warning: could not get content of "' . $title . '"<br>';
				}
				else
				{
					$node = $nodes->item(0);
					$nodehtml = get_clean_html($node);
					$result .= $nodehtml;
					$epub->AddPage($result, false, $title);
				}
			}
		}
		write_epub($epub);
	}
?>

<h1>Generate epub</h1>
<div>
<form method="post">

	<input type="submit">

	<h2>Mediapart</h2>
	<input id="mediapart" name="mediapart" type="checkbox">
	<label for="mediapart">From RSS</label>
	<br>
	<input id="mphome" name="mphome" type="checkbox">
	<label for="mphome">From home page</label>
	<br>
	<input id="forcempcookies" name="forcempcookies" type="checkbox">
	<label for="forcempcookies">Force cookies</label>
	<br>
	<input id="mptoday" name="mptoday" type="checkbox">
	<label for="mptoday">Today only</label>

	<h2>Le Monde</h2>
	<label for="lemonde">"GetPublicationContentItems" json url: </label>
	<input id="lemonde" name="lemonde">

	<h2>Cafeyn</h2>
	<label for="cafeyn">"material" json url: </label>
	<input id="cafeyn" name="cafeyn">

	<h2>The New York Times</h2>
	<input id="nyt" name="nyt" type="checkbox">
	<label for="nyt">From RSS</label>
	<br>
	<input id="nyttoday" name="nyttoday" type="checkbox">
	<label for="nyttoday">From today's paper embedded script</label>

	<h2>Politis</h2>
	<label for="politis">Issue number: </label><input id="politis" name="politis">

	<h2>Admin</h2>
	<input id="emptycache" name="emptycache" type="checkbox" checked>
	<label for="emptycache">Empty cache</label>
	<br><br>

	<input type="submit">
</form>
</div>

<h1>Available files</h1>
<?php
	if ($handle = opendir('epub')) {
	    echo "<ul>";
	    while (false !== ($file = readdir($handle))) {
	        if ($file != "." && $file != "..") {
	            $filePath = 'epub/' . $file;
	            $modTime = date("F d Y H:i:s.", filemtime($filePath));
	            echo "<li><a href='$filePath' download>$file</a> - $modTime</li>";
	        }
	    }
	    echo "</ul>";
	    closedir($handle);
	}
?>

<h1>Mediapart RSS summary</h1>
<?php
	$mprss = file_get_contents('https://www.mediapart.fr/articles/feed', false, $context);
	$xml = new SimpleXMLElement($mprss);
	$items = $xml->xpath("/rss/channel/item");
	foreach ($items as $item)
	{
		echo '<div><a href="'.$item->link.'">'.$item->pubDate. ' '.$item->title.'</a></div>';
	}
?>

<h1>Links</h1>
<a href="../epub">Generated files</a><br>
<a href="../">Press review</a><br>

</body>
</html>
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+								<!DOCTYPE html>
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+								<html>
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+								<head>
-												ux

											
										
										
											2024-06-04 13:51:27 +02:00
+									<meta charset="utf-8">
 									<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=0">
 									<title>Revue de presse - Epub</title>
 									<link rel="icon" type="image/png" href="1F4F0_color.png" /></head>
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+								<body>
-												add quick scenario for mediapart home page

											
										
										
											2024-09-25 21:41:09 +02:00
+								<div>
 									Quick link: <a href="epub.php?mp">All Mediapart home page with renewed authent</a>
 								</div>
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+								<?php
-												mp: ass param to force mpsessid
lm: handle curl commands

											
										
										
											2024-05-28 16:13:52 +02:00
-												lm refactor

											
										
										
											2024-06-03 17:03:19 +02:00
+									require 'settings.php';
-												refactor

											
										
										
											2024-06-03 17:29:30 +02:00
+									require 'TPEpubCreator.php';
-												lm refactor

											
										
										
											2024-06-03 17:03:19 +02:00
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+									function get_clean_html($node)
 									{
-												todos and comments

											
										
										
											2024-09-05 14:07:27 +02:00
+										// todo check words with "-" (like "sous-traitance")
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+										$innerHTM = '';
 										foreach ($node->childNodes as $childNode){
 											$nodeHTML = $childNode->ownerDocument->saveHTML($childNode);
-												fix blockquotes

											
										
										
											2024-09-04 18:20:01 +02:00
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+											$nodeHTML = str_replace('<aside', '<b><i', $nodeHTML);
 											$nodeHTML = str_replace('</aside', '</i></b', $nodeHTML);
-												fix blockquotes

											
										
										
											2024-09-04 18:20:01 +02:00
 											$nodeHTML = str_replace('<blockquote', '<b><i', $nodeHTML);
 											$nodeHTML = str_replace('</blockquote', '</i></b', $nodeHTML);
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+											$innerHTML .= $nodeHTML;
 										}
-												keep strong tag

											
										
										
											2024-09-04 17:43:37 +02:00
+										return '<div>' . strip_tags($innerHTML, '<p><b><h2><i><strong>') . '</div>';
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+									}
-												prepare mp refactor home and rss

											
										
										
											2024-08-26 18:10:14 +02:00
+									function add_mp_article($url, $context, $epub)
 									{
-												add today only for mp

											
										
										
											2024-08-27 10:40:26 +02:00
+										if (isset($_POST['mptoday']) && $_POST['mptoday'] && !str_contains($url, (new DateTime('today'))->format('dmy')))
 										{
 											return;
 										}
-												add todo

											
										
										
											2024-09-06 09:26:46 +02:00
+										// todo filter on "A la une" ? in rss item dc:subject contains "A la Une"
-												add today only for mp

											
										
										
											2024-08-27 10:40:26 +02:00
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+										$article = file_get_contents($url, false, $context);
 										$doc = new DOMDocument();
 										$doc->loadHTML($article);
 										$finder = new DomXPath($doc);
 										$title = $finder->query('//h1')->item(0)->textContent;
 										$author = $finder->query('//a[contains(@href, "biographie")]')->item(0)->textContent;
-												add today only for mp

											
										
										
											2024-08-27 10:40:26 +02:00
+										$date = trim($finder->query('//time')->item(1)->textContent);
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+										$summary = $finder->query('//p[contains(@class, "news__heading__top__intro")]')->item(0)->textContent;
-												mp add category

											
										
										
											2024-09-13 11:35:56 +02:00
+										$category = trim($finder->query('//p[contains(@class,"news__heading__top__kicker")]')->item(0)->textContent);
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
-												Revert "remove useless code"

This reverts commit a9308fe161475348eb2ecbc13b56705fca7da89d.

											
										
										
											2024-09-02 18:22:50 +02:00
+										// strip images
 										$toremove = $finder->query('//svg');
 										foreach ($toremove as $elt)
 										{
 											$elt->parentNode->removeChild($elt);
 										}
 										$toremove = $finder->query('//figure');
 										foreach ($toremove as $elt)
 										{
 											$elt->parentNode->removeChild($elt);
 										}
 										$toremove = $finder->query('//span[@class="screen-reader-only"]');
 										foreach ($toremove as $elt)
 										{
 											$elt->parentNode->removeChild($elt);
 										}
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+										$result = '<h1>' . $title . '</h1>';
-												mp add category

											
										
										
											2024-09-13 11:35:56 +02:00
+										$result .= '<p><em>' . $category . '</em></p>';
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+										$result .= '<p>' . $author . '</p>';
 										$result .= '<p>' . $date . '</p>';
 										$result .= '<p><b>' . $summary . '</b></p>';
 										$nodes = $finder->query('//div[contains(@class, "paywall-restricted-content")]');
 										if (!$nodes->length)
 										{
 											// articles accès libre
 											$nodes = $finder->query('//div[contains(@class, "news__body__center__article")]');
 										}
 										if (!$nodes->length)
 										{
 											echo 'warning: could not get content of "' . $title . '"<br>';
 										}
 										else
 										{
 											$node = $nodes->item(0);
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+											$nodehtml = get_clean_html($node);
-												fix missing article header

											
										
										
											2024-08-28 16:55:33 +02:00
+											$result .= $nodehtml;
-												add mp boite noire

											
										
										
											2024-09-05 17:48:36 +02:00
 											// add boite noire
 											$nodes = $finder->query('//aside[contains(@class, "_black")]');
 											if ($nodes->length)
 											{
 												$node = $nodes->item(0);
 												$nodehtml = get_clean_html($node);
 												$result .= '<div>' . $nodehtml . '</div>';
 											}
-												fix missing article header

											
										
										
											2024-08-28 16:55:33 +02:00
+											$epub->AddPage($result, false, $title);
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+										}
-												prepare mp refactor home and rss

											
										
										
											2024-08-26 18:10:14 +02:00
+									}
-												add get mp cookie
refactor form

											
										
										
											2024-07-07 15:01:30 +02:00
+									function get_mp_cookie()
 									{
 										global $mp_user;
 										global $mp_password;
 										$url = 'https://www.mediapart.fr/login_check';
 										$postfields = 'email=' . $mp_user . '&password=' . $mp_password . '&submitButton=&_target_path=https%3A%2F%2Fwww.mediapart.fr%2F';
 										$ch = curl_init($url);
 										curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
 										curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
 										curl_setopt($ch, CURLOPT_AUTOREFERER, false);
 										curl_setopt($ch, CURLOPT_HEADER, 1);
 										curl_setopt($ch, CURLOPT_POST, 1);
 										curl_setopt($ch, CURLOPT_POSTFIELDS, $postfields);
 										$result = curl_exec($ch);
 										$sessid = '';
 										preg_match_all('/^Set-Cookie:\s*([^;]*)/mi', $result, $matches);
 										foreach($matches[1] as $item)
 										{
 											if (str_starts_with($item, 'MPSESSID='))
 											{
 												$sessid = str_replace('MPSESSID=', '', $item);
 											}
 										}
 										return $sessid;
 									}
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+									function write_epub($epub)
 									{
-												fix cumulative effect

											
										
										
											2024-06-12 10:54:32 +02:00
+										if (file_exists($epub->epub_file))
 										{
 											unlink($epub->epub_file);
 										}
 										if (!$epub->error)
 										{
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+											$epub->CreateEPUB();
-												fix cumulative effect

											
										
										
											2024-06-12 10:54:32 +02:00
+											if (!$epub->error)
 											{
-												improve output

											
										
										
											2024-06-06 10:08:33 +02:00
+												echo 'Success: <a href="' . $epub->epub_file . '">' . $epub->epub_file . '</a> created.<br>';
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+											}
 											else
 											{
 												echo $epub->error;
 											}
-												fix cumulative effect

											
										
										
											2024-06-12 10:54:32 +02:00
+										}
 										else
 										{
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+											echo $epub->error;
 										}
 									}
-												refactor image download

											
										
										
											2024-06-13 09:42:57 +02:00
+									function lm_download_image($base_url, $url_part, $id)
 									{
 										$image_url = preg_replace('/GetPublicationContentItems-.*\.json/', $url_part . $id . '.jpg', $base_url);
 										$temp_img_path = './temp/' . $id . '.jpg';
 										$temp_content = file_get_contents($image_url);
 										file_put_contents($temp_img_path, $temp_content);
 										return $temp_img_path;
 									}
-												refactor json caching

											
										
										
											2024-07-09 16:42:49 +02:00
+									function get_json($url)
 									{
 										// cache json in case url expires
 										$tempjsonpath = 'temp/' . hash('md5', $url) . '.json';
 										$json = '';
 										if (file_exists($tempjsonpath))
 										{
 											$json = file_get_contents($tempjsonpath);
 										}
 										else
 										{
 											$json = file_get_contents($url);
 											file_put_contents($tempjsonpath, $json);
 										}
 										return json_decode($json);
 									}
-												add quick scenario for mediapart home page

											
										
										
											2024-09-25 21:41:09 +02:00
+									// quick scenario
 									if (isset($_GET['mp']))
 									{
 										$_POST['forcempcookies'] = 1;
 										$_POST['mphome'] = 1;
 									}
-												fix timezone

											
										
										
											2024-06-04 09:21:33 +02:00
+									date_default_timezone_set('Europe/Paris');
-												refactor

											
										
										
											2024-08-29 14:44:35 +02:00
+									$today = (new DateTime('today'))->format('Ymd');
-												mp: ass param to force mpsessid
lm: handle curl commands

											
										
										
											2024-05-28 16:13:52 +02:00
-												add option to empty cache

											
										
										
											2024-07-09 17:14:54 +02:00
+									if (isset($_POST['emptycache']) && $_POST['emptycache'])
 									{
 										$files = glob('temp/*');
 										foreach($files as $file)
 										{
 											if(is_file($file))
 											{
 												unlink($file);
 											}
 										}
 									}
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+									// Cafeyn
 									if (isset($_POST['cafeyn']) && $_POST['cafeyn'])
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
+									{
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+										$url = $_POST['cafeyn'];
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
 										// extract url from curl command
 										if (str_starts_with($url, 'curl '))
 										{
 											$url = explode("'", $url)[1];
 											echo '<p>extracted url from curl command:</p><p>' . $url . '</p>';
 										}
 										// cache json in case url expires
-												refactor json caching

											
										
										
											2024-07-09 16:42:49 +02:00
+										$publication = get_json($url);
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+										$pubname = $publication->metadata->title;
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
-												change cafeyn file name

											
										
										
											2024-09-05 14:07:45 +02:00
+										$epub->epub_file = 'epub/' . $pubname . 'cafeyn.epub';
 										$epub->title = $pubname . ' Cafeyn - ' . $today ;
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+										$list = (array)$publication->articles;
-												add page images for cafeyn

											
										
										
											2024-07-08 16:48:19 +02:00
+										$page = 1;
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+										foreach ($list as $entry)
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
+										{
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+											$articleurl = str_replace('material', 'article/' . $entry->hash . '.json', $url);
-												refactor json caching

											
										
										
											2024-07-09 16:42:49 +02:00
+											$article = get_json($articleurl);
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
 											$content = '<h1>' . $article->title . '</h1>';
-												improve cafeyn
fix le monde broken toc

											
										
										
											2024-07-09 14:57:24 +02:00
+											//$content .= '<b>' . $article->abstract . '</b>';
-												add page images for cafeyn

											
										
										
											2024-07-08 16:48:19 +02:00
+											$content .= '<div>Page ' . $article->page . '</div>';
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+											if (count($article->rubrics))
 											{
 												$content .= '<div>Rubriques: ' . implode(',', $article->rubrics) . '</div>';
 											}
 											if (count($article->authors))
 											{
 												$content .= '<div>Auteurs: ' . implode(',', $article->authors) . '</div>';
 											}
 											foreach ($article->content->sections as $section)
 											{
-												cafeyn improve dropcap

											
										
										
											2024-08-30 11:33:59 +02:00
+												$dropcap = '';
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+												foreach ($section->items as $item)
 												{
 													if ($item->type == 'text')
 													{
 														if ($item->class == 'quote')
 														{
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+															$content .= '<blockquote>' .$item->content . '</blockquote>';
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+														}
 														else if ($item->class == 'paragraphTitle')
 														{
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+															$content .= '<h2>' .$item->content . '</h2>';
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+														}
-												improve cafeyn
fix le monde broken toc

											
										
										
											2024-07-09 14:57:24 +02:00
+														else if ($item->class == 'introduction')
 														{
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+															$content .= '<p><b>' .$item->content . '</b></p>';
-												improve cafeyn
fix le monde broken toc

											
										
										
											2024-07-09 14:57:24 +02:00
+														}
-												cafeyn improve dropcap

											
										
										
											2024-08-30 11:33:59 +02:00
+														else if ($item->class == 'dropcap')
 														{
 															$dropcap = $item->content;
 														}
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+														else
 														{
-												cafeyn improve dropcap

											
										
										
											2024-08-30 11:33:59 +02:00
+															if ($dropcap)
 															{
 																$item->content = '<b>' . $dropcap . '</b>' . $item->content;
 																$dropcap = '';
 															}
 															$content .= '<p>' . $item->content . '</p>';
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+														}
 													}
 												}
 											}
-												add page images for cafeyn

											
										
										
											2024-07-08 16:48:19 +02:00
+											while ($article->page >= $page)
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+											{
-												add page images for cafeyn

											
										
										
											2024-07-08 16:48:19 +02:00
+												$path = $publication->pages[$page - 1]->tn;
 												$path = str_replace('material', $path, $url);
 												$path = str_replace('api.', 'content.', $path);
 												if ($page == 1)
 												{
 													// cover
 													$epub->AddImage($path, 'image/jpeg', true);
 												}
 												else
 												{
 													$epub->AddPage('<img style="width: 100%" src="' . $path . '">', false, 'Page ' . $page, true);
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+												}
-												add page images for cafeyn

											
										
										
											2024-07-08 16:48:19 +02:00
+												$page++;
 											}
-												implement cafeyn

											
										
										
											2024-07-08 15:07:27 +02:00
+											$epub->AddPage($content, false, $article->title);
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
+										}
 										write_epub($epub);
-												start to implement cafeyn

											
										
										
											2024-07-08 11:47:56 +02:00
+									}
-												start to add socialter

											
										
										
											2024-07-07 15:12:56 +02:00
-												refactor

											
										
										
											2024-06-03 17:29:30 +02:00
+									// Le Monde
 									if (isset($_POST['lemonde']) && $_POST['lemonde'])
 									{
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+										$url = $_POST['lemonde'];
-												mp: ass param to force mpsessid
lm: handle curl commands

											
										
										
											2024-05-28 16:13:52 +02:00
 										// extract url from curl command
 										if (str_starts_with($url, 'curl '))
 										{
 											$url = explode("'", $url)[1];
 											echo '<p>extracted url from curl command:</p><p>' . $url . '</p>';
 										}
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+										$epub->epub_file = 'epub/lemonde.epub';
-												refactor

											
										
										
											2024-08-29 14:44:35 +02:00
+										$epub->title = 'Le Monde ' . $today;
-												mp: ass param to force mpsessid
lm: handle curl commands

											
										
										
											2024-05-28 16:13:52 +02:00
-												json cache refactor for le monde

											
										
										
											2024-07-09 16:50:16 +02:00
+										$publication = get_json($url);
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+										$content = array_filter($publication->Content, function($item) { return $item->Category == 'Le Monde'; });
 										usort($content, function ($a, $b) { return $a->PageNumber - $b->PageNumber; });
-												mp: ass param to force mpsessid
lm: handle curl commands

											
										
										
											2024-05-28 16:13:52 +02:00
-												json cache refactor for le monde

											
										
										
											2024-07-09 16:50:16 +02:00
+										$pageindex = get_json(str_replace('GetPublicationContentItems', 'GetPublicationPages', $url));
-												le monde add each page preview + cover

											
										
										
											2024-06-12 10:54:18 +02:00
 										$page = 0;
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+										foreach ($content as $article)
 										{
-												fix pages

											
										
										
											2024-07-08 11:50:57 +02:00
+											if ($article->PageNumber > $page)
-												le monde add each page preview + cover

											
										
										
											2024-06-12 10:54:18 +02:00
+											{
 												$page = $article->PageNumber;
 												$pageobj = array_values(array_filter($pageindex->Page, function($p)
 												{
 													global $page;
 													return $page == $p->PageNumber;
 												}))[0];
 												$pageid = $pageobj->PublicationPageID;
-												remove lm parameters

											
										
										
											2024-07-08 11:46:51 +02:00
+												$path = lm_download_image($url, 'Preview-MEDIUM-', $pageid);
-												le monde add each page preview + cover

											
										
										
											2024-06-12 10:54:18 +02:00
 												if ($page == 1)
 												{
-												le monde add experimental image only mode

											
										
										
											2024-06-14 12:21:54 +02:00
+													// cover
-												refactor image download

											
										
										
											2024-06-13 09:42:57 +02:00
+													$epub->AddImage($path, 'image/jpeg', true);
-												le monde add each page preview + cover

											
										
										
											2024-06-12 10:54:18 +02:00
+												}
-												le monde add experimental image only mode

											
										
										
											2024-06-14 12:21:54 +02:00
+												else
 												{
 													$epub->AddPage('<img style="width: 100%" src="' . $path . '">', false, 'Page ' . $page, true);
 												}
-												le monde add each page preview + cover

											
										
										
											2024-06-12 10:54:18 +02:00
+											}
-												le monde add author, compute date, attempt to add images

											
										
										
											2024-05-29 21:35:13 +02:00
+											$articlebody = array_filter($article->ContentItem, function($item) { return $item->ContentType == 'text/xml'; });
 											$articlebody = array_values($articlebody)[0];
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+											if ($articlebody->Title && $articlebody->HtmlText)
 											{
 												$pagecontent = '<h1>'. strip_tags($articlebody->Title) . '</h1>';
-												lm refactor

											
										
										
											2024-06-03 17:03:19 +02:00
+												$pagecontent .= '<p>Page ' . $article->PageNumber . '</p>';
-												le monde add author, compute date, attempt to add images

											
										
										
											2024-05-29 21:35:13 +02:00
 												$author = array_filter($article->ContentItem, function($item) { return $item->ContentType == 'author/xml'; });
 												$author = array_values($author)[0];
 												if ($author->Author)
 												{
 													$pagecontent .= $author->Author;
 												}
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+												if ($articlebody->Introduction)
 												{
 													$pagecontent .= '<b>' . $articlebody->Introduction . '</b>';
 												}
 												$pagecontent .= $articlebody->HtmlText;
-												le monde add each page preview + cover

											
										
										
											2024-06-12 10:54:18 +02:00
-												improve cafeyn
fix le monde broken toc

											
										
										
											2024-07-09 14:57:24 +02:00
+												$epub->AddPage($pagecontent, false, str_replace('&nbsp;', ' ', strip_tags($articlebody->Title)), true);
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+											}
 										}
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+										write_epub($epub);
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+									}
-												mp: ass param to force mpsessid
lm: handle curl commands

											
										
										
											2024-05-28 16:13:52 +02:00
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+									if (isset($_POST['forcempcookies']) && $_POST['forcempcookies'])
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
+									{
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+										$old = $mp_sessionid;
 										$mp_sessionid = get_mp_cookie();
 										$settings = file_get_contents('settings.php');
 										$settings = str_replace($old, $mp_sessionid, $settings);
 										file_put_contents('settings.php', $settings);
 										echo '<div>Updated mpsessid in settings.</div>';
 									}
-												add get mp cookie
refactor form

											
										
										
											2024-07-07 15:01:30 +02:00
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+									// Mediapart RSS
 									if (isset($_POST['mediapart']) && $_POST['mediapart'])
 									{
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
+										$feedurl = 'https://www.mediapart.fr/articles/feed';
 										$opts = [
 										'http' => [
 											'method' => "GET",
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+											'header' => "Accept-language: en\nCookie: MPSESSID=" . $mp_sessionid,
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
+										]
 										];
 										$context = stream_context_create($opts);
 										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+										$epub->epub_file = 'epub/mediapart.epub';
-												refactor

											
										
										
											2024-08-29 14:44:35 +02:00
+										$epub->title = 'Mediapart - RSS ' . $today;
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
 										// load feeds
 										$feed = file_get_contents($feedurl);
 										$xml = new SimpleXMLElement($feed);
 										$items = $xml->xpath("/rss/channel/item");
-												parse rss in reverse to respect timing

											
										
										
											2024-09-05 14:08:06 +02:00
+										foreach (array_reverse($items) as $item)
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
+										{
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+											add_mp_article($item->link, $context, $epub);
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
+										}
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+										write_epub($epub);
-												merge le monde and mediapart

											
										
										
											2024-06-03 17:38:46 +02:00
+									}
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+									// Politis RSS
 									if (isset($_POST['politis']) && $_POST['politis'])
 									{
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+										$issuenb = $_POST['politis'];
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+										$feedurl = 'https://www.politis.fr/flux-rss-politis-fr/';
 										$opts = [
 										'http' => [
 											'method' => "GET",
-												todos and comments

											
										
										
											2024-09-05 14:07:27 +02:00
+											//'header' => "Accept-language: en\nCookie: MPSESSID=" . $mp_sessionid, // todo?
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+										]
 										];
 										$context = stream_context_create($opts);
 										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
 										$epub->epub_file = 'epub/politis' . $issuenb . '.epub';
 										$epub->title = 'Politis ' . $issuenb . ' - RSS ' . $today;
-												add politis cover

											
										
										
											2024-09-05 14:08:19 +02:00
+										// find cover
 										$issues = file_get_contents('https://www.politis.fr/boutique/magazines-unite/');
 										$doc = new DOMDocument();
 										$doc->loadHTML($issues);
 										$finder = new DomXPath($doc);
-												fix crash when politis cover not found

											
										
										
											2024-09-11 10:52:41 +02:00
+										$cover = $finder->query('//img[contains(@src, "' . $issuenb . '_")]');
 										if ($cover->length)
 										{
 											$epub->AddImage($cover->item(0)->getAttribute('src'), 'image/jpeg', true);
 										}
 										else
 										{
 											echo 'warning: no cover for issue ' . $issuenb . '<br>';
 										}
-												add politis cover

											
										
										
											2024-09-05 14:08:19 +02:00
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+										// load feeds
 										$feed = file_get_contents($feedurl);
 										$xml = new SimpleXMLElement($feed);
 										$items = $xml->xpath("/rss/channel/item");
 										foreach (array_reverse($items) as $item)
 										{
 											$url = $item->link;
 											$article = file_get_contents($url, false, $context);
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+											if (!str_contains($article, ' dans l’hebdo N° ' . $issuenb))
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+											{
 												continue;
 											}
 											$doc = new DOMDocument();
 											$doc->loadHTML($article);
 											$finder = new DomXPath($doc);
 											$title = $finder->query('//h1')->item(0)->textContent;
 											$author = $finder->query('//span[@class="nom"]')->item(0)->textContent;
 											$date = $finder->query('//span[@class="date"]')->item(0)->textContent;
 											$summary = $finder->query('//div[@class="extrait"]')->item(0)->textContent;
-												mp add category

											
										
										
											2024-09-13 11:35:56 +02:00
+											// transform "zoom" divs into aside tags
-												politis: tranform zoom divs into aside tags

											
										
										
											2024-09-11 15:45:11 +02:00
+											$zooms =  $finder->query('//div[contains(@class,"gt_zoom")]');
 											foreach ($zooms as $zoom)
 											{
 												$aside = $doc->createElement('aside');
 												while ($zoom->childNodes->length > 0)
 												{
 													$aside->appendChild($zoom->childNodes->item(0));
 												}
 												$zoom->parentNode->replaceChild($aside, $zoom);
 											}
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+											$result = '<h1>' . $title . '</h1>';
 											$result .= '<p>' . $author . '</p>';
 											$result .= '<p>' . $date . '</p>';
 											$result .= '<p><b>' . $summary . '</b></p>';
 											$nodes = $finder->query('//div[@id="content"]');
 											$node = $nodes->item(0);
 											$nodehtml = get_clean_html($node);
 											$result .= $nodehtml;
 											$epub->AddPage($result, false, $title);
 										}
 										write_epub($epub);
 									}
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+									// Mediapart home page
 									if (isset($_POST['mphome']) && $_POST['mphome'])
 									{
 										$homeurl = 'https://www.mediapart.fr';
 										$opts = [
 										'http' => [
 											'method' => "GET",
 											'header' => "Accept-language: en\nCookie: MPSESSID=" . $mp_sessionid,
 										]
 										];
 										$context = stream_context_create($opts);
 										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
 										$epub->epub_file = 'epub/mediaparthome.epub';
-												refactor

											
										
										
											2024-08-29 14:44:35 +02:00
+										$epub->title = 'Mediapart - A la une ' . $today;
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
 										$home = file_get_contents($homeurl, false, $context);
 										$doc = new DOMDocument();
 										$doc->loadHTML($home);
 										$finder = new DomXPath($doc);
-												simplify mp home xpath, more inclusive

											
										
										
											2024-08-23 09:31:16 +02:00
+										$xpath = '//a[@data-js = "teaser-link" and contains(@href, "/journal/") and not(contains(@href, "/dossier/")) and not(contains(@href, "/studio/")) and not(contains(@href, "fil-")) and (@href != "/journal/series")]/@href';
-												add option to include mp cold articles from home
fix article date

											
										
										
											2024-08-22 14:23:30 +02:00
-												simplify mp home xpath, more inclusive

											
										
										
											2024-08-23 09:31:16 +02:00
+										$links = $finder->query($xpath);
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
 										foreach ($links as $link)
 										{
-												refactor mp

											
										
										
											2024-08-26 18:15:17 +02:00
+											add_mp_article('https://www.mediapart.fr' . $link->value, $context, $epub);
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+										}
 										write_epub($epub);
 									}
-												todos and comments

											
										
										
											2024-09-05 14:07:27 +02:00
+									// New York Times RSS
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+									if (isset($_POST['nyt']) && $_POST['nyt'])
 									{
 										$feedurl = 'https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml';
 										$opts = [
 										'http' => [
 											'method' => "GET",
 											'header' => "Accept-language: en\nCookie: NYT-S=" . $nyt_sessionid,
 										]
 										];
 										$context = stream_context_create($opts);
 										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
 										$epub->epub_file = 'epub/newyorktimes.epub';
-												refactor

											
										
										
											2024-08-29 14:44:35 +02:00
+										$epub->title = 'The New York Times ' . $today;
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
 										// load feeds
 										$feed = file_get_contents($feedurl);
 										$xml = new SimpleXMLElement($feed);
 										$items = $xml->xpath("/rss/channel/item");
-												parse rss in reverse to respect timing

											
										
										
											2024-09-05 14:08:06 +02:00
+										foreach (array_reverse($items) as $item)
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+										{
 											$title = $item->title;
 											$author = $item->xpath('dc:creator')[0];
 											$summary = $item->description;
 											$article = file_get_contents($item->link, false, $context);
 											$doc = new DOMDocument();
 											$doc->loadHTML($article);
 											$finder = new DomXPath($doc);
 											$result = '<h1>' . $title . '</h1>';
 											$result .= '<p>' . $author . '</p>';
 											$result .= '<p>' . $item->pubDate . '</p>';
 											$result .= '<p><b>' . $summary . '</b></p>';
 											$nodes = $finder->query('//section[@name="articleBody"]');
 											if (!$nodes->length)
 											{
 												echo 'warning: could not get content of "' . $title . '"<br>';
 											}
 											else
 											{
 												$node = $nodes->item(0);
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+												$nodehtml = get_clean_html($node);
-												fix missing article header

											
										
										
											2024-08-28 16:55:33 +02:00
+												$result .= $nodehtml;
 												$epub->AddPage($result, false, $title);
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+											}
 										}
-												small fix and refactor

											
										
										
											2024-06-04 09:42:41 +02:00
+										write_epub($epub);
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+									}
-												add comment

											
										
										
											2024-06-05 12:14:44 +02:00
+									// New York Times today's paper
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+									if (isset($_POST['nyttoday']) && $_POST['nyttoday'])
 									{
 										$todaypage = file_get_contents("https://www.nytimes.com/section/todayspaper");
 										$opts = [
 										'http' => [
 											'method' => "GET",
 											'header' => "Accept-language: en\nCookie: NYT-S=" . $nyt_sessionid,
 										]
 										];
 										$context = stream_context_create($opts);
 										$epub = new TPEpubCreator();
 										$epub->temp_folder = 'temp/';
 										$epub->epub_file = 'epub/newyorktimestoday.epub';
-												refactor

											
										
										
											2024-08-29 14:44:35 +02:00
+										$epub->title = 'The New York Times today\'s paper ' . $today;
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
 										// grab today's paper
 										$start = strpos($todaypage, "window.__preloadedData = ") + 25;
 										$end = strpos($todaypage, "};", $start) + 1;
 										$json = str_replace(":undefined", ":null", substr($todaypage, $start, $end - $start));
 										$data = json_decode($json);
 										foreach($data->initialState as $item)
 										{
 											if ($item->__typename == "Article")
 											{
 												$headline = ($data->initialState->{ $item->headline->id });
 												$title = $headline->default;
 												$summary = $item->summary;
 												$result = '<h1>' . $title . '</h1>';
-												add authors and date to nyt today

											
										
										
											2024-06-05 12:51:50 +02:00
+												// authors
 												$result .= '<p>';
 												$creators = ($data->initialState->{ $item->bylines[0]->id })->creators;
 												foreach ($creators as $creator)
 												{
 													$author = $data->initialState->{ $creator->id };
 													$result .= $author->displayName . '&nbsp;';
 												}
 												$result .= '</p>';
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
-												add authors and date to nyt today

											
										
										
											2024-06-05 12:51:50 +02:00
+												$result .= '<p>' . $item->lastMajorModification . '</p>';
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+												$result .= '<p><b>' . $summary . '</b></p>';
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+												$article = file_get_contents($item->url, false, $context);
 												$doc = new DOMDocument();
 												$doc->loadHTML($article);
 												$finder = new DomXPath($doc);
 												$nodes = $finder->query('//section[@name="articleBody"]');
 												if (!$nodes->length)
 												{
 													echo 'warning: could not get content of "' . $title . '"<br>';
 												}
 												else
 												{
 													$node = $nodes->item(0);
-												handle aside tag

											
										
										
											2024-08-28 15:57:56 +02:00
+													$nodehtml = get_clean_html($node);
-												fix missing article header

											
										
										
											2024-08-28 16:55:33 +02:00
+													$result .= $nodehtml;
 													$epub->AddPage($result, false, $title);
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+												}
 											}
 										}
 										write_epub($epub);
 									}
 								?>
-												styling

											
										
										
											2024-08-27 11:13:26 +02:00
+								<h1>Generate epub</h1>
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+								<div>
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+								<form method="post">
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
-												duplicate submit button on top

											
										
										
											2024-09-04 18:25:42 +02:00
+									<input type="submit">
-												styling

											
										
										
											2024-08-27 11:13:26 +02:00
+									<h2>Mediapart</h2>
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+									<input id="mediapart" name="mediapart" type="checkbox">
-												add get mp cookie
refactor form

											
										
										
											2024-07-07 15:01:30 +02:00
+									<label for="mediapart">From RSS</label>
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+									<br>
-												add mediapart from home page

											
										
										
											2024-08-22 12:08:39 +02:00
+									<input id="mphome" name="mphome" type="checkbox">
 									<label for="mphome">From home page</label>
 									<br>
-												enabled mp cookie update

											
										
										
											2024-07-08 09:12:26 +02:00
+									<input id="forcempcookies" name="forcempcookies" type="checkbox">
-												add get mp cookie
refactor form

											
										
										
											2024-07-07 15:01:30 +02:00
+									<label for="forcempcookies">Force cookies</label>
-												add mp rss summary

											
										
										
											2024-08-26 11:01:20 +02:00
+									<br>
-												add today only for mp

											
										
										
											2024-08-27 10:40:26 +02:00
+									<input id="mptoday" name="mptoday" type="checkbox">
-												prepare mp refactor home and rss

											
										
										
											2024-08-26 18:10:14 +02:00
+									<label for="mptoday">Today only</label>
-												add get mp cookie
refactor form

											
										
										
											2024-07-07 15:01:30 +02:00
-												change order and fix typo

											
										
										
											2024-08-27 15:16:34 +02:00
+									<h2>Le Monde</h2>
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+									<label for="lemonde">"GetPublicationContentItems" json url: </label>
 									<input id="lemonde" name="lemonde">
-												change order and fix typo

											
										
										
											2024-08-27 15:16:34 +02:00
 									<h2>Cafeyn</h2>
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+									<label for="cafeyn">"material" json url: </label>
 									<input id="cafeyn" name="cafeyn">
-												change order and fix typo

											
										
										
											2024-08-27 15:16:34 +02:00
-												styling

											
										
										
											2024-08-27 11:13:26 +02:00
+									<h2>The New York Times</h2>
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+									<input id="nyt" name="nyt" type="checkbox">
-												add get mp cookie
refactor form

											
										
										
											2024-07-07 15:01:30 +02:00
+									<label for="nyt">From RSS</label>
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
+									<br>
 									<input id="nyttoday" name="nyttoday" type="checkbox">
-												change order and fix typo

											
										
										
											2024-08-27 15:16:34 +02:00
+									<label for="nyttoday">From today's paper embedded script</label>
-												add nyt today's paper
add epub link on index

											
										
										
											2024-06-04 17:19:23 +02:00
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
+									<h2>Politis</h2>
-												simplify params

											
										
										
											2024-09-04 18:20:11 +02:00
+									<label for="politis">Issue number: </label><input id="politis" name="politis">
-												add politis

											
										
										
											2024-09-04 17:43:51 +02:00
-												styling

											
										
										
											2024-08-27 11:13:26 +02:00
+									<h2>Admin</h2>
-												empty cache by default

											
										
										
											2024-07-19 09:30:09 +02:00
+									<input id="emptycache" name="emptycache" type="checkbox" checked>
-												add option to empty cache

											
										
										
											2024-07-09 17:14:54 +02:00
+									<label for="emptycache">Empty cache</label>
-												mp remove cover image
change order and ui

											
										
										
											2024-08-27 13:51:43 +02:00
+									<br><br>
-												add option to empty cache

											
										
										
											2024-07-09 17:14:54 +02:00
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+									<input type="submit">
 								</form>
-												refactor and add nyt

											
										
										
											2024-06-03 21:28:52 +02:00
+								</div>
-												styling

											
										
										
											2024-08-27 11:13:26 +02:00
-												add available files on epub tool

											
										
										
											2024-09-16 16:35:26 +02:00
+								<h1>Available files</h1>
 								<?php
 									if ($handle = opendir('epub')) {
 									    echo "<ul>";
 									    while (false !== ($file = readdir($handle))) {
 									        if ($file != "." && $file != "..") {
 									            $filePath = 'epub/' . $file;
 									            $modTime = date("F d Y H:i:s.", filemtime($filePath));
 									            echo "<li><a href='$filePath' download>$file</a> - $modTime</li>";
 									        }
 									    }
 									    echo "</ul>";
 									    closedir($handle);
 									}
 								?>
-												styling

											
										
										
											2024-08-27 11:13:26 +02:00
-												mp remove cover image
change order and ui

											
										
										
											2024-08-27 13:51:43 +02:00
+								<h1>Mediapart RSS summary</h1>
-												add mp rss summary

											
										
										
											2024-08-26 11:01:20 +02:00
+								<?php
 									$mprss = file_get_contents('https://www.mediapart.fr/articles/feed', false, $context);
 									$xml = new SimpleXMLElement($mprss);
 									$items = $xml->xpath("/rss/channel/item");
 									foreach ($items as $item)
 									{
 										echo '<div><a href="'.$item->link.'">'.$item->pubDate. ' '.$item->title.'</a></div>';
 									}
 								?>
-												add available files on epub tool

											
										
										
											2024-09-16 16:35:26 +02:00
 								<h1>Links</h1>
 								<a href="../epub">Generated files</a><br>
 								<a href="../">Press review</a><br>
-												add script to get le monde as epub

											
										
										
											2024-05-27 13:28:36 +02:00
+								</body>
 								</html>