extracted url from curl command:
' . $url . '
'; } $epub = new TPEpubCreator(); $epub->temp_folder = 'temp/'; $epub->epub_file = 'epub/lemonde.epub'; $epub->title = 'Le Monde ' . $date ; if ($includecover) { // todo get correct cover according to date and time $coverurl = 'https://www.lemonde.fr/thumbnail/journal/'. $date .'/1000/1490'; $epub->AddImage( $coverurl, 'image/jpeg', true ); } // 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); } $publication = json_decode($json); $content = array_filter($publication->Content, function($item) { return $item->Category == 'Le Monde'; }); usort($content, function ($a, $b) { return $a->PageNumber - $b->PageNumber; }); foreach ($content as $article) { $articlebody = array_filter($article->ContentItem, function($item) { return $item->ContentType == 'text/xml'; }); $articlebody = array_values($articlebody)[0]; if ($articlebody->Title && $articlebody->HtmlText) { $pagecontent = 'Page ' . $article->PageNumber . '
'; $author = array_filter($article->ContentItem, function($item) { return $item->ContentType == 'author/xml'; }); $author = array_values($author)[0]; if ($author->Author) { $pagecontent .= $author->Author; } if ($articlebody->Introduction) { $pagecontent .= '' . $articlebody->Introduction . ''; } if ($includeimages) { $images = array_values(array_filter($article->ContentItem, function($item) { return $item->ContentType == 'graphic/jpeg' || $item->ContentType == 'image/jpeg'; })); foreach ($images as $image) { $imageid = $image->ContentItemId; $imageurl = preg_replace('/GetPublicationContentItems-.*\.json/', 'Image-MEDIUM-' . $imageid . '.jpg', $url); // Download image from source, put it in temp and include it into article main html content. // Then pass true to last AddPage param to download image to epub. $tempimgpath = './temp/' . $imageid . '.jpg'; $tempcontent = file_get_contents($imageurl); file_put_contents($tempimgpath, $tempcontent); $pagecontent .= ''; } } $pagecontent .= $articlebody->HtmlText; $epub->AddPage($pagecontent, false, strip_tags($articlebody->Title), true); } } write_epub($epub); } // Mediapart 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 ' . $date; // load feeds $feed = file_get_contents($feedurl); $xml = new SimpleXMLElement($feed); $items = $xml->xpath("/rss/channel/item"); foreach ($items as $item) { $title = $item->title; $category = $item->xpath('dc:subject')[0]; $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); // 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 = '' . $author . '
'; $result .= '' . $item->pubDate . '
'; $result .= '' . $summary . '
'; $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 . '"') . '
' . $author . '
'; $result .= '' . $item->pubDate . '
'; $result .= '' . $summary . '
'; $nodes = $finder->query('//section[@name="articleBody"]'); if (!$nodes->length) { echo 'warning: could not get content of "' . $title . '"') . '
'; $creators = ($data->initialState->{ $item->bylines[0]->id })->creators; foreach ($creators as $creator) { $author = $data->initialState->{ $creator->id }; $result .= $author->displayName . ' '; } $result .= '
'; $result .= '' . $item->lastMajorModification . '
'; $result .= '' . $summary . '
'; $article = file_get_contents($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 . '"') . '