From e184e405774b1519e964fc2a39475e9dbb47dbc8 Mon Sep 17 00:00:00 2001 From: Lukas Anzinger Date: Sat, 16 Jan 2016 20:09:46 +0100 Subject: LWN.net: Fix author and date parsing for special articles. --- lwn.net.txt | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lwn.net.txt b/lwn.net.txt index 82c6e1a..06a6dc6 100644 --- a/lwn.net.txt +++ b/lwn.net.txt @@ -13,6 +13,9 @@ title: //h1 author: //div[@class='FeatureByline']/strong date: //div[@class='FeatureByline']/text()[preceding-sibling::br] strip: //div[@class='FeatureByline'] +author: substring-after(//div[@class='GAByline']/p[2], 'by ') +date: //div[@class='GAByline']/p[1] +strip: //div[@class='GAByline'] # tidy will take care of fixing the tag mess that we make here. replace_string(

):

@@ -33,3 +36,4 @@ test_url: http://lwn.net/Articles/669114/ test_url: http://lwn.net/Articles/670209/ test_url: http://lwn.net/Articles/670209/rss test_url: http://lwn.net/Articles/668318/rss +test_url: http://lwn.net/Articles/670062/ -- cgit v1.3.1