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 --- .../standard/blogs.smithsonianmag.com.txt | 26 +++++++++++----------- 1 file changed, 13 insertions(+), 13 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt (limited to 'inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt') diff --git a/inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt b/inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt old mode 100644 new mode 100755 index ba8bc6e7..1bc65e77 --- a/inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt +++ b/inc/3rdparty/site_config/standard/blogs.smithsonianmag.com.txt @@ -1,15 +1,15 @@ -# metadata -author://div[@class = 'post']/div[@class='meta']/a[1] -date://div[@id = 'rap']/h2[1] -body://div[@class = 'post'] - -# wrapping caption and image -wrap_in(fieldset)://div[contains(@class, 'wp-caption')] - - -# clean up -strip://div[@class = 'post']/h3[@class = 'storytitle'] -strip://div[@class = 'post']/div[@class = 'social'] -strip://img[@style = 'display:none;'] +# metadata +author://div[@class = 'post']/div[@class='meta']/a[1] +date://div[@id = 'rap']/h2[1] +body://div[@class = 'post'] + +# wrapping caption and image +wrap_in(fieldset)://div[contains(@class, 'wp-caption')] + + +# clean up +strip://div[@class = 'post']/h3[@class = 'storytitle'] +strip://div[@class = 'post']/div[@class = 'social'] +strip://img[@style = 'display:none;'] strip://img[@height='0' and @width='0'] test_url: http://blogs.smithsonianmag.com/adventure/2011/10/tips-for-women-traveling-in-turkey/ \ No newline at end of file -- cgit v1.2.3