Cleanup the HTML before parsing it.
This commit is contained in:
parent
c398974918
commit
620ee6be0b
1 changed files with 5 additions and 0 deletions
|
@ -263,6 +263,11 @@ function scrape_feed($url) {
|
||||||
}
|
}
|
||||||
|
|
||||||
try {
|
try {
|
||||||
|
// Cleanup invalid HTML
|
||||||
|
$doc = new DOMDocument();
|
||||||
|
@$doc->loadHTML($s);
|
||||||
|
$s = $doc->saveHTML();
|
||||||
|
|
||||||
$dom = HTML5_Parser::parse($s);
|
$dom = HTML5_Parser::parse($s);
|
||||||
} catch (DOMException $e) {
|
} catch (DOMException $e) {
|
||||||
logger('scrape_feed: parse error: ' . $e);
|
logger('scrape_feed: parse error: ' . $e);
|
||||||
|
|
Loading…
Reference in a new issue