diff options
| -rw-r--r-- | online.wsj.com.txt | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/online.wsj.com.txt b/online.wsj.com.txt index d20d1d2..e0f91ac 100644 --- a/online.wsj.com.txt +++ b/online.wsj.com.txt @@ -2,7 +2,7 @@ title: //meta[@property="og:title"]/@content body: //div[@id='article_story_body'] author: //h3[@class='byline']/a -# for slid show content +# for slide show content body: //ul[@id='imageSlide']//li[@class='firstSlide']//img | (//div[@class='txt_body']//p)[1] date: //li[@class='dateStamp']/small @@ -14,10 +14,11 @@ 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/article/SB10001424052970203363504577185322849515102.html # slide show -test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html
\ No newline at end of file +test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html |