From 7bd1e680c347a40308cd4344b9aa19630a423fca Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Sat, 10 Jan 2015 14:20:22 +0100 Subject: Update and rename online.wsj.com.txt to wsj.com.txt --- online.wsj.com.txt | 25 ------------------------- wsj.com.txt | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 25 deletions(-) delete mode 100644 online.wsj.com.txt create mode 100644 wsj.com.txt diff --git a/online.wsj.com.txt b/online.wsj.com.txt deleted file mode 100644 index 448bb7e..0000000 --- a/online.wsj.com.txt +++ /dev/null @@ -1,25 +0,0 @@ -title: //meta[@property="og:title"]/@content -body: //div[@id='article_story_body'] - -author: //h3[@class='byline']/a -# for slide 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'))] -strip: //div[contains(@class, 'carousel')] - -prune: no -tidy: no - -test_url: http://online.wsj.com/news/articles/SB10001424052702304626304579509100018004342 -test_url: http://online.wsj.com/article/SB10001424052970203363504577185322849515102.html -# slide show -test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html diff --git a/wsj.com.txt b/wsj.com.txt new file mode 100644 index 0000000..467c39c --- /dev/null +++ b/wsj.com.txt @@ -0,0 +1,29 @@ +title: //meta[@property="og:title"]/@content +body: //div[@id='wsj-article-wrap'] +# is this still used? +body: //div[@id='article_story_body'] + +author: //h3[@class='byline']/a +# for slide 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'))] +strip: //div[contains(@class, 'carousel')] + +prune: no +tidy: no + +test_url: http://www.wsj.com/articles/airasia-flight-8501-tail-recovered-1420878809 +test_contains: Saturday evening that the black boxes +test_url: http://www.wsj.com/news/articles/SB10001424052702304626304579509100018004342 +test_url: http://www.wsj.com/article/SB10001424052970203363504577185322849515102.html +# slide show +test_url: http://www.wsj.com/article/SB10001424052970204791104577110550376458164.html -- cgit v1.3.1