From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/spectator.co.uk.txt | 7 +++++++ 1 file changed, 7 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..a05c8395 --- /dev/null +++ b/inc/3rdparty/site_config/standard/spectator.co.uk.txt @@ -0,0 +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 +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