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 --- inc/3rdparty/site_config/standard/bbc.co.uk.txt | 74 ++++++++++++++----------- 1 file changed, 42 insertions(+), 32 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/bbc.co.uk.txt (limited to 'inc/3rdparty/site_config/standard/bbc.co.uk.txt') diff --git a/inc/3rdparty/site_config/standard/bbc.co.uk.txt b/inc/3rdparty/site_config/standard/bbc.co.uk.txt old mode 100644 new mode 100755 index 9c5c3419..ef1f491a --- a/inc/3rdparty/site_config/standard/bbc.co.uk.txt +++ b/inc/3rdparty/site_config/standard/bbc.co.uk.txt @@ -1,32 +1,42 @@ -body: //div[@class="story-body"] -title: //h1[@class="story-header"] -date: //span[@class="story-date"]/span[@class='date'] - -# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055 -body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1'] - -#strip: //div[@class="story-feature narrow"] -#strip: //div[@class="story-feature wide"] -#strip: //div[@class="story-feature dslideshow-enclosure"] -strip: //div[contains(@class, "story-feature")] -strip: //span[@class="story-date"] -#strip: //div[@class="caption body-narrow-width"] -strip: //div[@class="warning"]//p -strip: //div[@id='page-bookmark-links-head'] -strip: //object -strip: //div[contains(@class, "bbccom_advert_placeholder")] -strip: //div[contains(@class, "embedded-hyper")] -strip: //div[contains(@class, 'market-data')] -strip: //a[contains(@class, 'hidden')] -strip: //div[contains(@class, 'hypertabs')] -strip: //div[contains(@class, 'related')] -strip: //form[@id='comment-form'] -strip: //div[contains(@class, 'comment-introduction')] - -replace_string(