wp-plugins/fourth-wall-embed-wp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 7 Wiki Activity

Update for FW switching to sending Binary instead of raw html

Browse Source
This commit is contained in:
Josh Knapp 2025-04-22 10:48:19 -07:00
parent be7db52eec
commit 1bdae9a815
1 changed files with 43 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
libs/shortcode.php
View File

@ -1,13 +1,53 @@
<?php
function fwembed_parse_html($url = null) {
if ($url === null) {
if ($url === null) {
throw new ValueError("Missing URL");
}
$ch = curl_init();
// More complete browser-like headers
$headers = [
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language: en-US,en;q=0.5',
'Connection: keep-alive',
'Upgrade-Insecure-Requests: 1',
'Cache-Control: max-age=0'
];
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_ENCODING, "");
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0');
curl_setopt($ch, CURLOPT_TIMEOUT, 30);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); // Only if necessary for testing
curl_setopt($ch, CURLOPT_COOKIEJAR, '/tmp/cookies.txt'); // Store cookies
curl_setopt($ch, CURLOPT_COOKIEFILE, '/tmp/cookies.txt'); // Use cookies
$html_content = curl_exec($ch);
if (curl_errno($ch)) {
$error = curl_error($ch);
curl_close($ch);
return "Error fetching URL: " . $error;
}
$status_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
if ($status_code == 403) {
curl_close($ch);
return "Access forbidden (403). The website may be blocking automated requests.";
}
curl_close($ch);
$html = null;
libxml_use_internal_errors(true);
$dom = new DOMDocument();
@$dom->loadHTML(loadHTML5(file_get_contents($url)), LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
@$dom->loadHTML(loadHTML5($html_content), LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
$dom->documentURI = $url;
$divs = $dom->getElementsByTagName('div');
foreach ($divs as $div) {