From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- online.wsj.com.txt | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 online.wsj.com.txt (limited to 'online.wsj.com.txt') diff --git a/online.wsj.com.txt b/online.wsj.com.txt new file mode 100644 index 0000000..d20d1d2 --- /dev/null +++ b/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 v1.3.1