From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- .../site_config/standard/csnphilly.com.txt | 42 +++++++++++----------- 1 file changed, 21 insertions(+), 21 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/csnphilly.com.txt (limited to 'inc/3rdparty/site_config/standard/csnphilly.com.txt') diff --git a/inc/3rdparty/site_config/standard/csnphilly.com.txt b/inc/3rdparty/site_config/standard/csnphilly.com.txt old mode 100644 new mode 100755 index 0df72c32..c14a934a --- a/inc/3rdparty/site_config/standard/csnphilly.com.txt +++ b/inc/3rdparty/site_config/standard/csnphilly.com.txt @@ -1,22 +1,22 @@ -# author's name is not isolated as a tag.... ugh -convert_double_br_tags: yes -body: //csn_blogST_main - -#junk above and around the article -strip: /html/body/div[4]/div[3]/div/div/div/section/div/div/div/div/div/div -strip: /html/body/div[4]/header -strip_id_or_class: article-right-sidebar -strip_id_or_class: rsn-gigya-sharebar-container -strip_id_or_class: article-bottom -strip_id_or_class: hider -strip_id_or_class: footer -strip_id_or_class: masthead -strip_id_or_class: block-menu-menu-rsn-login-or-register -strip_id_or_class: block-menu-menu-header-links -strip_id_or_class: block-rsn-follow-bar-follow-bar -strip_id_or_class: block-rsn-weather-rsn-weather-scoreboard -strip_id_or_class: logo -strip_id_or_class: element-invisible -strip_id_or_class: site-name -strip: //div[contains(@style, 'none')] +# author's name is not isolated as a tag.... ugh +convert_double_br_tags: yes +body: //csn_blogST_main + +#junk above and around the article +strip: /html/body/div[4]/div[3]/div/div/div/section/div/div/div/div/div/div +strip: /html/body/div[4]/header +strip_id_or_class: article-right-sidebar +strip_id_or_class: rsn-gigya-sharebar-container +strip_id_or_class: article-bottom +strip_id_or_class: hider +strip_id_or_class: footer +strip_id_or_class: masthead +strip_id_or_class: block-menu-menu-rsn-login-or-register +strip_id_or_class: block-menu-menu-header-links +strip_id_or_class: block-rsn-follow-bar-follow-bar +strip_id_or_class: block-rsn-weather-rsn-weather-scoreboard +strip_id_or_class: logo +strip_id_or_class: element-invisible +strip_id_or_class: site-name +strip: //div[contains(@style, 'none')] test_url: http://www.csnphilly.com/eagles/can-stoutland-save-danny-watkins-career \ No newline at end of file -- cgit v1.2.3