From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/spectator.co.uk.txt | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/spectator.co.uk.txt (limited to 'inc/3rdparty/site_config/standard/spectator.co.uk.txt') diff --git a/inc/3rdparty/site_config/standard/spectator.co.uk.txt b/inc/3rdparty/site_config/standard/spectator.co.uk.txt old mode 100644 new mode 100755 index a05c8395..d0605ed2 --- a/inc/3rdparty/site_config/standard/spectator.co.uk.txt +++ b/inc/3rdparty/site_config/standard/spectator.co.uk.txt @@ -1,7 +1,7 @@ -author: /html/body/div[@id='wrapper']/div[@id='main-content']/div[@class='article_body']/a[@class='author-link']/child::text() - -body: /html/body/div[@id='wrapper']/div[@id='main-content']/div[@class='article_body'] - -# Not very helpfull, the title and author are container by the same element that contains the body +author: /html/body/div[@id='wrapper']/div[@id='main-content']/div[@class='article_body']/a[@class='author-link']/child::text() + +body: /html/body/div[@id='wrapper']/div[@id='main-content']/div[@class='article_body'] + +# Not very helpfull, the title and author are container by the same element that contains the body strip: /html/body/div[@id='wrapper']/div[@id='main-content']/div[@class='article_body']/h2 | /html/body/div[@id='wrapper']/div[@id='main-content']/div[@class='article_body']/a[@class='author-link'] test_url: http://www.spectator.co.uk/arts-and-culture/night-and-day/7449683/spotify-sunday-my-personal-soundtrack.thtml \ No newline at end of file -- cgit v1.2.3