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/visir.is.txt | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/visir.is.txt (limited to 'inc/3rdparty/site_config/standard/visir.is.txt') diff --git a/inc/3rdparty/site_config/standard/visir.is.txt b/inc/3rdparty/site_config/standard/visir.is.txt old mode 100644 new mode 100755 index 0f03198e..04e09102 --- a/inc/3rdparty/site_config/standard/visir.is.txt +++ b/inc/3rdparty/site_config/standard/visir.is.txt @@ -1,14 +1,14 @@ -# Author's name, when present, has 'skrifar:' ('writes:') appended to it. -# In case of multiple authors, this would be 'skrifa:', hence only 7 characters -# are stripped off. -author: substring(//div[@class='paragraph']/div[@class='meta'], 0, string-length(//div[@class='paragraph']/div[@class='meta']) - 7) - -date: //span[@class='date'] -title: //h1 -body: //div[@class='paragraph'] - -# Strip out author string when present -strip: //div[@class='paragraph']/div[@class='meta'] - +# Author's name, when present, has 'skrifar:' ('writes:') appended to it. +# In case of multiple authors, this would be 'skrifa:', hence only 7 characters +# are stripped off. +author: substring(//div[@class='paragraph']/div[@class='meta'], 0, string-length(//div[@class='paragraph']/div[@class='meta']) - 7) + +date: //span[@class='date'] +title: //h1 +body: //div[@class='paragraph'] + +# Strip out author string when present +strip: //div[@class='paragraph']/div[@class='meta'] + convert_double_br_tags: yes test_url: http://visir.is/esb,-ipa,-bhm-og-bsrb/article/2012701319997 \ No newline at end of file -- cgit v1.2.3