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 --- .../site_config/standard/online.wsj.com.txt | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/online.wsj.com.txt (limited to 'inc/3rdparty/site_config/standard/online.wsj.com.txt') diff --git a/inc/3rdparty/site_config/standard/online.wsj.com.txt b/inc/3rdparty/site_config/standard/online.wsj.com.txt new file mode 100644 index 00000000..edb52855 --- /dev/null +++ b/inc/3rdparty/site_config/standard/online.wsj.com.txt @@ -0,0 +1,23 @@ +title: //meta[@property="og:title"]/@content +body: //div[@id='article_story_body'] + +author: //h3[@class='byline']/a +# for slid show content +body: //ul[@id='imageSlide']//li[@class='firstSlide']//img | (//div[@class='txt_body']//p)[1] +date: //li[@class='dateStamp']/small + +strip_id_or_class: insetFullBracket +strip_id_or_class: insettipBox +#strip_id_or_class: legacyInset +strip_id_or_class: recipeACShopAndBuyText + +strip: //div[contains(@class, 'insetContent')]//cite +strip: //*[contains(@style, 'visibility: hidden;')] +strip: //div[contains(@class, 'insetContent') and not(contains(@class, 'image'))] + +prune: no +tidy: no + +test_url: http://online.wsj.com/article/SB10001424052970203363504577185322849515102.html +# slide show +test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html \ No newline at end of file -- cgit v1.2.3