From 90a1a78b1e2f4d40e1d9b8e6f46aca129a9d7bcf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Mon, 27 Oct 2014 06:46:13 +0100 Subject: updated site_config --- inc/3rdparty/site_config/standard/foreignpolicy.com.txt | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'inc/3rdparty/site_config/standard/foreignpolicy.com.txt') diff --git a/inc/3rdparty/site_config/standard/foreignpolicy.com.txt b/inc/3rdparty/site_config/standard/foreignpolicy.com.txt index 4e84b989..853a5b7b 100755 --- a/inc/3rdparty/site_config/standard/foreignpolicy.com.txt +++ b/inc/3rdparty/site_config/standard/foreignpolicy.com.txt @@ -1,15 +1,19 @@ title: //div[@class='translateHead']//h1 | //div[@id='art-mast']//h1 author: substring-after(//span[@id='by-line'], 'BY ') date: //span[@id='pub-date'] -body: //div[@id='art-mast']/h2 | //div[@class='translateBody'] | //div[@id='art-body'] +body: (//article//img[contains(@class, 'main_photo')])[1] | (//article//div[contains(@class, 'full_post_content')])[1] +#body: //div[@id='art-mast']/h2 | //div[@class='translateBody'] | //div[@id='art-body'] #Strip inside article content strip: //div[@id='share-box'] -strip: //div[@id='special-box'] +strip: //div[@id='special-box + +strip_id_or_class: side_panel prune: no single_page_link: //span[@id='controls']/a[contains(@href, 'print=yes')] single_page_link: //a[text()='SINGLE PAGE'] +test_url: http://www.foreignpolicy.com/articles/2014/07/22/the_end_game_in_gaza_netanyahu_hamas test_url: http://www.foreignpolicy.com/articles/2011/08/01/a_murderers_manifesto_and_me test_url: http://www.foreignpolicy.com/articles/2012/02/29/five_years_in_damascus \ No newline at end of file -- cgit v1.2.3