updated specific configuration for parsing

1 files changed, 21 insertions, 16 deletions

diff --git a/inc/3rdparty/site_config/standard/huffingtonpost.com.txt b/inc/3rdparty/site_config/standard/huffingtonpost.com.txt
index d40513b2..d4618c14 100644..100755
--- a/inc/3rdparty/site_config/standard/huffingtonpost.com.txt
+++ b/inc/3rdparty/site_config/standard/huffingtonpost.com.txt
@@ -1,16 +1,21 @@
-title: //meta[@property="og:title"]/@content

-body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | //div[contains(@class, 'entry_body_text')]

-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:')]

-# 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
+title: //meta[@property="og:title"]/@content
+body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | //div[contains(@class, 'entry_body_text')]
+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