LesLibres.org/Rss-Bridge
2
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[html] Use find('*') over custom solution

Browse source 
find('*') wasn't supported in older versions of simplehtmldom but it
is supported now. Thus, all custom implementations can be replaced
by the correct solution.
This commit is contained in:
logmanoriginal 2019-06-01 21:05:10 +02:00
parent 5656792cee
commit 014b698f67
1 changed files with 2 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
lib/html.php
View file

@ -32,18 +32,7 @@ function sanitize($html,
$htmlContent = str_get_html($html); $htmlContent = str_get_html($html);
/* foreach($htmlContent->find('*') as $element) {
* Notice: simple_html_dom currently doesn't support "->find(*)", which is a
* known issue: https://sourceforge.net/p/simplehtmldom/bugs/157/
*
* A solution to this is to find all nodes WITHOUT a specific attribute. If
* the attribute is very unlikely to appear in the DOM, this is essentially
* returning all nodes.
*
* "*[!b38fd2b1fe7f4747d6b1c1254ccd055e]" is doing exactly that. The attrib
* "b38fd2b1fe7f4747d6b1c1254ccd055e" is very unlikely to appear in any DOM.
*/
foreach($htmlContent->find('*[!b38fd2b1fe7f4747d6b1c1254ccd055e]') as $element) {
if(in_array($element->tag, $text_to_keep)) { if(in_array($element->tag, $text_to_keep)) {
$element->outertext = $element->plaintext; $element->outertext = $element->plaintext;
} elseif(in_array($element->tag, $tags_to_remove)) { } elseif(in_array($element->tag, $tags_to_remove)) {
@ -90,18 +79,7 @@ function backgroundToImg($htmlContent) {
$regex = '/background-image[ ]{0,}:[ ]{0,}url\([\'"]{0,}(.*?)[\'"]{0,}\)/'; $regex = '/background-image[ ]{0,}:[ ]{0,}url\([\'"]{0,}(.*?)[\'"]{0,}\)/';
$htmlContent = str_get_html($htmlContent); $htmlContent = str_get_html($htmlContent);
/* foreach($htmlContent->find('*') as $element) {
* Notice: simple_html_dom currently doesn't support "->find(*)", which is a
* known issue: https://sourceforge.net/p/simplehtmldom/bugs/157/
*
* A solution to this is to find all nodes WITHOUT a specific attribute. If
* the attribute is very unlikely to appear in the DOM, this is essentially
* returning all nodes.
*
* "*[!b38fd2b1fe7f4747d6b1c1254ccd055e]" is doing exactly that. The attrib
* "b38fd2b1fe7f4747d6b1c1254ccd055e" is very unlikely to appear in any DOM.
*/
foreach($htmlContent->find('*[!b38fd2b1fe7f4747d6b1c1254ccd055e]') as $element) {
if(preg_match($regex, $element->style, $matches) > 0) { if(preg_match($regex, $element->style, $matches) > 0) {