parent
289a867789
commit
1135e41203
116
epub.php
116
epub.php
|
@ -205,9 +205,6 @@
|
|||
foreach ($node->childNodes as $childNode){
|
||||
$innerHTML .= $childNode->ownerDocument->saveHTML($childNode);
|
||||
}
|
||||
$outerHTML = $node->ownerDocument->saveHTML($node);
|
||||
$textcontent = $node->textContent;
|
||||
|
||||
$result .= '<div>' . strip_tags($innerHTML, '<p><b><h2><i>') . '</div>';
|
||||
|
||||
$epub->AddPage($result, false, $title);
|
||||
|
@ -220,7 +217,6 @@
|
|||
// New York Times
|
||||
if (isset($_POST['nyt']) && $_POST['nyt'])
|
||||
{
|
||||
|
||||
$feedurl = 'https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml';
|
||||
$opts = [
|
||||
'http' => [
|
||||
|
@ -276,11 +272,6 @@
|
|||
$result .= '<p><b>' . $summary . '</b></p>';
|
||||
|
||||
$nodes = $finder->query('//section[@name="articleBody"]');
|
||||
/*if (!$nodes->length)
|
||||
{
|
||||
// articles accès libre
|
||||
$nodes = $finder->query('//div[contains(@class, "news__body__center__article")]');
|
||||
}*/
|
||||
|
||||
if (!$nodes->length)
|
||||
{
|
||||
|
@ -294,8 +285,6 @@
|
|||
foreach ($node->childNodes as $childNode){
|
||||
$innerHTML .= $childNode->ownerDocument->saveHTML($childNode);
|
||||
}
|
||||
$outerHTML = $node->ownerDocument->saveHTML($node);
|
||||
$textcontent = $node->textContent;
|
||||
|
||||
$result .= '<div>' . strip_tags($innerHTML, '<p><b><h2><i>') . '</div>';
|
||||
|
||||
|
@ -306,23 +295,112 @@
|
|||
write_epub($epub);
|
||||
}
|
||||
|
||||
if (isset($_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);
|
||||
|
||||
// list existing files
|
||||
echo '<div>';
|
||||
$epub = new TPEpubCreator();
|
||||
$epub->temp_folder = 'temp/';
|
||||
$epub->epub_file = 'epub/newyorktimestoday.epub';
|
||||
$epub->title = 'The New York Times today\'s paper ' . $date;
|
||||
|
||||
// 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>' . $title . '</h1>';
|
||||
|
||||
// todo
|
||||
//$result .= '<p>' . $author . '</p>';
|
||||
//$result .= '<p>' . $item->pubDate . '</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);
|
||||
|
||||
$innerHTML = '';
|
||||
foreach ($node->childNodes as $childNode){
|
||||
$innerHTML .= $childNode->ownerDocument->saveHTML($childNode);
|
||||
}
|
||||
|
||||
$result .= '<div>' . strip_tags($innerHTML, '<p><b><h2><i>') . '</div>';
|
||||
|
||||
$epub->AddPage($result, false, $title);
|
||||
}
|
||||
}
|
||||
}
|
||||
write_epub($epub);
|
||||
}
|
||||
?>
|
||||
|
||||
<h3>Existing Files</h3>
|
||||
<div>
|
||||
<?php
|
||||
$files = glob('epub/*');
|
||||
foreach ($files as $file)
|
||||
{
|
||||
echo '<a href="' . $file . '">' . str_replace('epub/', '', $file) . '</a> ' . date('F d Y H:i:s', filemtime($file)) . '<br>';
|
||||
echo date('F d Y H:i:s', filemtime($file)) . ' <a href="' . $file . '">' . str_replace('epub/', '', $file) . '</a><br>';
|
||||
}
|
||||
echo '</div>';
|
||||
?>
|
||||
</div>
|
||||
|
||||
<h3>Generate epub</h3>
|
||||
<div>
|
||||
Generate epub:<br>
|
||||
<form method="post">
|
||||
<input input name="lemonde" type="checkbox">Le Monde - GetPublicationContentItems url: <input name="lmurl"><br>
|
||||
<input input name="mediapart" type="checkbox">Mediapart<br>
|
||||
<input input name="nyt" type="checkbox">The New York Times<br>
|
||||
|
||||
Parameters:
|
||||
<br>
|
||||
GetPublicationContentItems url: <input name="lmurl"><br>
|
||||
<br>
|
||||
|
||||
Newspapers:
|
||||
<br>
|
||||
<input id="lemonde" name="lemonde" type="checkbox">
|
||||
<label for="lemonde">Le Monde</label>
|
||||
<br>
|
||||
|
||||
<input id="mediapart" name="mediapart" type="checkbox">
|
||||
<label for="mediapart">Mediapart</label>
|
||||
<br>
|
||||
|
||||
<input id="nyt" name="nyt" type="checkbox">
|
||||
<label for="nyt">The New York Times</label>
|
||||
<br>
|
||||
|
||||
<input id="nyttoday" name="nyttoday" type="checkbox">
|
||||
<label for="nyttoday">The New York Times - today's paper (beta)</label>
|
||||
<br>
|
||||
|
||||
<input type="submit">
|
||||
</form>
|
||||
</div>
|
||||
|
|
|
@ -52,7 +52,7 @@
|
|||
- <a href="https://nouveau.europresse.com/Pdf">Autre publications</a><br>
|
||||
<a href="https://www.cairn.info/">Cairn</a>
|
||||
- <a href="https://www.cairn.info/revue-ecologie-et-politique.htm">Écologie & politique</a><br>
|
||||
<a href="epub.php">Fichiers epub</a>
|
||||
<a href="./epub">Fichiers epub</a>
|
||||
</p>
|
||||
</body>
|
||||
</html>
|
||||
|
|
Loading…
Reference in New Issue