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/thepioneerwoman.com.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/thepioneerwoman.com.txt (limited to 'inc/3rdparty/site_config/standard/thepioneerwoman.com.txt') diff --git a/inc/3rdparty/site_config/standard/thepioneerwoman.com.txt b/inc/3rdparty/site_config/standard/thepioneerwoman.com.txt old mode 100644 new mode 100755 index f89f3a87..75583cd3 --- a/inc/3rdparty/site_config/standard/thepioneerwoman.com.txt +++ b/inc/3rdparty/site_config/standard/thepioneerwoman.com.txt @@ -1,11 +1,11 @@ -title: //h1[@class='post-title'] -body: //div[@class='post'] -author: //p[@class='posted-by'] -date: //div[@class='sprite post-date'] - -# The body of the post doesn't have it's own div so we have to strip out the metadata -strip: //div[@class='author_avatar'] -strip: //div[@class='sprite post-date'] -strip: //h1[@class='post-title'] +title: //h1[@class='post-title'] +body: //div[@class='post'] +author: //p[@class='posted-by'] +date: //div[@class='sprite post-date'] + +# The body of the post doesn't have it's own div so we have to strip out the metadata +strip: //div[@class='author_avatar'] +strip: //div[@class='sprite post-date'] +strip: //h1[@class='post-title'] strip: //p[@class='posted-by'] test_url: http://thepioneerwoman.com/cooking/2011/08/pie-fats-a-comparison/ \ No newline at end of file -- cgit v1.2.3