From 7fc2d11d8b0c639f876168fb3d817f0266fefebe Mon Sep 17 00:00:00 2001 From: Angelo Prado Date: Sat, 11 Oct 2014 20:44:10 -0700 Subject: Additional cleanup for theverge.com --- theverge.com.txt | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/theverge.com.txt b/theverge.com.txt index 1e1ce58..78f8654 100644 --- a/theverge.com.txt +++ b/theverge.com.txt @@ -15,6 +15,11 @@ strip: //nav strip: //img[contains(@class, 'vox-lazy-load')] # deal with bad parsing strip: //div[contains(@class, 'story-image')]//div[contains(., 'function(')] +strip: //div[contains(@class, 'm-linkset')] +strip: //div[contains(@class, 'm-entry__sidebar')] +strip: //ul[contains(@class, 'm-article__sources')] +strip: //div[contains(@class, 'chorus-emc__content')] + strip_id_or_class: gallery strip_id_or_class: article-meta @@ -45,4 +50,4 @@ test_url: http://www.theverge.com/2012/2/29/2821763/lytro-review test_url: http://www.theverge.com/2011/11/3/2534861/nokia-lumia-800-review test_url: http://www.theverge.com/2013/2/24/4026114/barnes-noble-shifting-focus-away-from-nook-hardware test_url: http://www.theverge.com/2014/6/19/5824072/top-shelf-living-the-dream -test_url: http://www.theverge.com/rss/frontpage \ No newline at end of file +test_url: http://www.theverge.com/rss/frontpage -- cgit v1.3.1