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/tasteofhome.com.txt | 26 +++++++++------------- 1 file changed, 11 insertions(+), 15 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/tasteofhome.com.txt (limited to 'inc/3rdparty/site_config/standard/tasteofhome.com.txt') diff --git a/inc/3rdparty/site_config/standard/tasteofhome.com.txt b/inc/3rdparty/site_config/standard/tasteofhome.com.txt old mode 100644 new mode 100755 index 77773363..f3234f34 --- a/inc/3rdparty/site_config/standard/tasteofhome.com.txt +++ b/inc/3rdparty/site_config/standard/tasteofhome.com.txt @@ -1,15 +1,11 @@ -title: //span[@id='ctl00_ctl00_MainContent_MainContent_RecipeImage1_lblRecipeTitle'] -body: //div[@id='RDNEW']//*[@class='Recipe-imgCon' or @class='Recipe-Intro' or @class='recipeDetails'] -strip_id_or_class: rec-ExRightPanel -strip_id_or_class: divCarousel -strip_id_or_class: preptimeOuter -strip_id_or_class: cooktimeOuter -strip_id_or_class: durationOuter -strip_id_or_class: divImageFooter -strip_id_or_class: microFormatFnIngred -strip: //span[@class='Recipe-Intro']//*[@class='link' or @class='rating'] - -prune: no -tidy: no - -test_url: http://www.tasteofhome.com/recipes/Grinch-Punch \ No newline at end of file +title: //div[@id='ctl00_MainContent_ctl00_Div1']//h2 +body: //div[@id='ctl00_MainContent_ctl00_Div1'] + +single_page_link: //div[contains(@class, 'recipeHeader')]//a[contains(@href, '/print')] + +strip_image_src: tohPrintL.png + +prune: no + +test_url: http://www.tasteofhome.com/recipes/Grinch-Punch +test_url: http://www.tasteofhome.com/recipes/lactose-free-chocolate-chip-cookies \ No newline at end of file -- cgit v1.2.3