*
* ```
*
* @param string $htmlContent The HTML content
* @return string The HTML content with all ocurrences replaced
*/
function backgroundToImg($htmlContent) {
$regex = '/background-image[ ]{0,}:[ ]{0,}url\([\'"]{0,}(.*?)[\'"]{0,}\)/';
$htmlContent = str_get_html($htmlContent);
/*
* Notice: simple_html_dom currently doesn't support "->find(*)", which is a
* known issue: https://sourceforge.net/p/simplehtmldom/bugs/157/
*
* A solution to this is to find all nodes WITHOUT a specific attribute. If
* the attribute is very unlikely to appear in the DOM, this is essentially
* returning all nodes.
*
* "*[!b38fd2b1fe7f4747d6b1c1254ccd055e]" is doing exactly that. The attrib
* "b38fd2b1fe7f4747d6b1c1254ccd055e" is very unlikely to appear in any DOM.
*/
foreach($htmlContent->find('*[!b38fd2b1fe7f4747d6b1c1254ccd055e]') as $element) {
if(preg_match($regex, $element->style, $matches) > 0) {
$element->outertext = 'ads
ads`
* @return string Cleaned String, e.g. `foobar`
*
* @todo This function needs more documentation to make it maintainable.
*/
function stripRecursiveHTMLSection($string, $tag_name, $tag_start){
$open_tag = '<' . $tag_name;
$close_tag = '';
$close_tag_length = strlen($close_tag);
if(strpos($tag_start, $open_tag) === 0) {
while(strpos($string, $tag_start) !== false) {
$max_recursion = 100;
$section_to_remove = null;
$section_start = strpos($string, $tag_start);
$search_offset = $section_start;
do {
$max_recursion--;
$section_end = strpos($string, $close_tag, $search_offset);
$search_offset = $section_end + $close_tag_length;
$section_to_remove = substr($string, $section_start, $section_end - $section_start + $close_tag_length);
$open_tag_count = substr_count($section_to_remove, $open_tag);
$close_tag_count = substr_count($section_to_remove, $close_tag);
} while ($open_tag_count > $close_tag_count && $max_recursion > 0);
$string = str_replace($section_to_remove, '', $string);
}
}
return $string;
}
/**
* Convert Markdown into HTML. Only a subset of the Markdown syntax is implemented.
*
* @link https://daringfireball.net/projects/markdown/ Markdown
* @link https://github.github.com/gfm/ GitHub Flavored Markdown Spec
*
* @param string $string Input string in Markdown format
* @return string output string in HTML format
*/
function markdownToHtml($string) {
//For more details about how these regex work:
// https://github.com/RSS-Bridge/rss-bridge/pull/802#discussion_r216138702
// Images: https://regex101.com/r/JW9Evr/1
// Links: https://regex101.com/r/eRGVe7/1
// Bold: https://regex101.com/r/2p40Y0/1
// Italic: https://regex101.com/r/xJkET9/1
// Separator: https://regex101.com/r/ZBEqFP/1
// Plain URL: https://regex101.com/r/2JHYwb/1
// Site name: https://regex101.com/r/qIuKYE/1
$string = preg_replace('/\!\[([^\]]+)\]\(([^\) ]+)(?: [^\)]+)?\)/', '
', $string);
$string = preg_replace('/\[([^\]]+)\]\(([^\)]+)\)/', '$1', $string);
$string = preg_replace('/\*\*(.*)\*\*/U', '$1', $string);
$string = preg_replace('/\*(.*)\*/U', '$1', $string);
$string = preg_replace('/__(.*)__/U', '$1', $string);
$string = preg_replace('/_(.*)_/U', '$1', $string);
$string = preg_replace('/[-]{6,99}/', '
', $string); $string = str_replace(' ', '
', $string); $string = preg_replace('/([^"])(https?:\/\/[^ "<]+)([^"])/', '$1$2$3', $string . ' '); $string = preg_replace('/([^"\/])(www\.[^ "<]+)([^"])/', '$1$2$3', $string . ' '); //As the regex are not perfect, we need to fix and that are introduced in URLs // Fixup regex : https://regex101.com/r/NTRPf6/1 // Fixup regex : https://regex101.com/r/aNklRp/1 $count = 1; while($count > 0) { $string = preg_replace('/ (src|href)="([^"]+)([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count); } $count = 1; while($count > 0) { $string = preg_replace('/ (src|href)="([^"]+)<\/i>([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count); } return '
', $string); $string = str_replace(' ', '
', $string); $string = preg_replace('/([^"])(https?:\/\/[^ "<]+)([^"])/', '$1$2$3', $string . ' '); $string = preg_replace('/([^"\/])(www\.[^ "<]+)([^"])/', '$1$2$3', $string . ' '); //As the regex are not perfect, we need to fix and that are introduced in URLs // Fixup regex : https://regex101.com/r/NTRPf6/1 // Fixup regex : https://regex101.com/r/aNklRp/1 $count = 1; while($count > 0) { $string = preg_replace('/ (src|href)="([^"]+)([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count); } $count = 1; while($count > 0) { $string = preg_replace('/ (src|href)="([^"]+)<\/i>([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count); } return '
' . trim($string) . '
';
}