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/huffingtonpost.com.txt | 37 ++++++++++++---------- 1 file changed, 21 insertions(+), 16 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/huffingtonpost.com.txt (limited to 'inc/3rdparty/site_config/standard/huffingtonpost.com.txt') diff --git a/inc/3rdparty/site_config/standard/huffingtonpost.com.txt b/inc/3rdparty/site_config/standard/huffingtonpost.com.txt old mode 100644 new mode 100755 index d40513b2..d4618c14 --- 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(