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/uni-watch.com.txt | 30 +++++++++++----------- 1 file changed, 15 insertions(+), 15 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/uni-watch.com.txt (limited to 'inc/3rdparty/site_config/standard/uni-watch.com.txt') diff --git a/inc/3rdparty/site_config/standard/uni-watch.com.txt b/inc/3rdparty/site_config/standard/uni-watch.com.txt old mode 100644 new mode 100755 index cbe87d19..4a5ae344 --- a/inc/3rdparty/site_config/standard/uni-watch.com.txt +++ b/inc/3rdparty/site_config/standard/uni-watch.com.txt @@ -1,17 +1,17 @@ -author: substring-before(substring-after(//div[@class='post-byline'], 'By '), ', on') -date: substring-after(//div[@class='post-byline'], ', on') - -# for some reason, the following is producing a "no text [48]" error -#title: //div[@class='post-headline'] - -# for some reason, the following doesn't appear to isolate just the body copy -body: //div[@class='post-bodycopy'] - -# we solve the above issue by stripping out everything else we don't want -# these can probably all be removed if the body: command above worked -strip_id_or_class: reply -strip_id_or_class: left -strip_id_or_class: post-headline -strip_id_or_class: post-byline +author: substring-before(substring-after(//div[@class='post-byline'], 'By '), ', on') +date: substring-after(//div[@class='post-byline'], ', on') + +# for some reason, the following is producing a "no text [48]" error +#title: //div[@class='post-headline'] + +# for some reason, the following doesn't appear to isolate just the body copy +body: //div[@class='post-bodycopy'] + +# we solve the above issue by stripping out everything else we don't want +# these can probably all be removed if the body: command above worked +strip_id_or_class: reply +strip_id_or_class: left +strip_id_or_class: post-headline +strip_id_or_class: post-byline strip_id_or_class: footer test_url: http://www.uni-watch.com/2011/10/18/the-curious-case-of-steve-debergs-microphone-and-speaker/ \ No newline at end of file -- cgit v1.2.3