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/expressen.se.txt | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/expressen.se.txt (limited to 'inc/3rdparty/site_config/standard/expressen.se.txt') diff --git a/inc/3rdparty/site_config/standard/expressen.se.txt b/inc/3rdparty/site_config/standard/expressen.se.txt new file mode 100644 index 00000000..d0cb283e --- /dev/null +++ b/inc/3rdparty/site_config/standard/expressen.se.txt @@ -0,0 +1,9 @@ +title: //div[@id='article']/div[contains(@class, 'content')]/h1 +body: //div[@id='article']/div[contains(@class, 'content')] +date: //div[contains(@class, 'article-slot')]/descendant::div[contains(@id, 'articledates')] + +strip: //img[contains(@src, 'img/px.gif')] +prune: no +# remove Facebook banner and obtrusive ad +strip: //div[@id='article']/div[contains(@class, 'content')]/div[contains(@class, 'art-right')] +test_url: http://www.expressen.se/kultur/1.2683904/medan-natet-dras-at \ No newline at end of file -- cgit v1.2.3