diff options
Diffstat (limited to 'src/Nodes/NodeUtility.php')
| -rw-r--r-- | src/Nodes/NodeUtility.php | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/Nodes/NodeUtility.php b/src/Nodes/NodeUtility.php index 0e1072f..752e9f4 100644 --- a/src/Nodes/NodeUtility.php +++ b/src/Nodes/NodeUtility.php @@ -17,7 +17,7 @@ class NodeUtility * @var array */ public static $regexps = [ - 'unlikelyCandidates' => '/banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|foot|header|legends|menu|modal|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i', + 'unlikelyCandidates' => '/banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|foot|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i', 'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i', 'extraneous' => '/print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i', 'byline' => '/byline|author|dateline|writtenby|p-author/i', @@ -29,7 +29,7 @@ class NodeUtility 'whitespace' => '/^\s*$/', 'hasContent' => '/\S$/', 'positive' => '/article|body|content|entry|hentry|h-entry|main|page|pagination|post|text|blog|story/i', - 'negative' => '/hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|masthead|media|meta|modal|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i', + 'negative' => '/hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|masthead|media|meta|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i', // \x{00A0} is the unicode version of 'onlyWhitespace' => '/\x{00A0}|\s+/u' ]; |