diff options
| -rw-r--r-- | wsj.com.txt (renamed from online.wsj.com.txt) | 10 |
1 files changed, 7 insertions, 3 deletions
diff --git a/online.wsj.com.txt b/wsj.com.txt index 448bb7e..467c39c 100644 --- a/online.wsj.com.txt +++ b/wsj.com.txt @@ -1,4 +1,6 @@ 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 @@ -19,7 +21,9 @@ 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 +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://online.wsj.com/article/SB10001424052970204791104577110550376458164.html +test_url: http://www.wsj.com/article/SB10001424052970204791104577110550376458164.html |