diff options
Diffstat (limited to 'wsj.com.txt')
| -rw-r--r-- | wsj.com.txt | 29 |
1 files changed, 29 insertions, 0 deletions
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 |