diff options
| -rw-r--r-- | huffingtonpost.com.txt | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/huffingtonpost.com.txt b/huffingtonpost.com.txt index fb990a7..d4618c1 100644 --- a/huffingtonpost.com.txt +++ b/huffingtonpost.com.txt @@ -3,14 +3,19 @@ body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | date: //meta[@name="publish_date"]/@content author: //a[@rel="author"] author: //meta[@name="author"]/@content + prune: no tidy: no + strip: //footer strip_id_or_class: ps-slideshow strip_id_or_class: fs-slideshow strip: //p[contains(., 'Related on HuffPost:')] +strip_id_or_class: contribute-story +strip_id_or_class: promo_holder + # end early replace_string(<div class="sbm-main): </body></html><div class="not-interested test_url: http://www.huffingtonpost.com/mitch-moxley/tracking-beijings-boom-th_b_1209828.html -test_url: http://www.huffingtonpost.com/2012/09/11/president-obama-iphone-throwdown_n_1873826.html
\ No newline at end of file +test_url: http://www.huffingtonpost.com/2012/09/11/president-obama-iphone-throwdown_n_1873826.html |