From 96204d04d2a8f227140f42ed756200340754de17 Mon Sep 17 00:00:00 2001 From: William Krause Date: Fri, 17 Mar 2017 16:16:05 -1000 Subject: [PATCH] add additional cleaner remove nodes --- newspaper/cleaners.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/newspaper/cleaners.py b/newspaper/cleaners.py index 1ce2e770..c79022cb 100644 --- a/newspaper/cleaners.py +++ b/newspaper/cleaners.py @@ -26,7 +26,8 @@ def __init__(self, config): "|communitypromo|runaroundLeft|subscribe|vcard|articleheadings" "|date|^print$|popup|author-dropdown|tools|socialtools|byline" "|konafilter|KonaFilter|breadcrumbs|^fn$|wp-caption-text" - "|legende|ajoutVideo|timestamp|js_replies" + "|legende|ajoutVideo|timestamp|js_replies|summary-lead|news-author" + "|kicker|author-name|summary" ) self.regexp_namespace = "http://exslt.org/regular-expressions" self.nauthy_ids_re = ("//*[re:test(@id, '%s', 'i')]" %